7778 lines
487 KiB
XML
7778 lines
487 KiB
XML
<?xml version="1.0"?>
|
||
<doc>
|
||
<assembly>
|
||
<name>Microsoft.ML.Transforms</name>
|
||
</assembly>
|
||
<members>
|
||
<member name="T:Microsoft.ML.CategoricalCatalog">
|
||
<summary>
|
||
Collection of extension methods for <see cref="T:Microsoft.ML.TransformsCatalog.CategoricalTransforms"/> to create categorical
|
||
transformer components.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CategoricalCatalog.OneHotEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,System.String,System.String,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality,Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.OneHotEncodingEstimator"/>, which converts the input column specified by <paramref name="inputColumnName"/>
|
||
into a column of one-hot encoded vectors named <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<param name="catalog">The transform catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a vector of <see cref="T:System.Single"/> if <paramref name="outputKind"/> is
|
||
<see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag"/>, <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator"/>, and <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Binary"/>.
|
||
If <paramref name="outputKind"/> is <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Key"/>, this column's data type will be a key in the case of a scalar input column
|
||
or a vector of keys in the case of a vector input column.</param>
|
||
<param name="inputColumnName">Name of column to convert to one-hot vectors. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/>
|
||
will be used as source. This column's data type can be scalar or vector of numeric, text, boolean, <see cref="T:System.DateTime"/> or <see cref="T:System.DateTimeOffset"/>,</param>
|
||
<param name="outputKind">Output kind: Bag (multi-set vector), Indicator (indicator vector), Key (index), or Binary encoded indicator vector.</param>
|
||
<param name="maximumNumberOfKeys">Maximum number of terms to keep per column when auto-training.</param>
|
||
<param name="keyOrdinality">How items should be ordered when vectorized. If <see cref="F:Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality.ByOccurrence"/>
|
||
choosen they will be in the order encountered. If <see cref="F:Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality.ByValue"/>,
|
||
items are sorted according to their default comparison, for example, text sorting will be case sensitive (for example, 'A' then 'Z' then 'a').</param>
|
||
<param name="keyData">Specifies an ordering for the encoding. If specified, this should be a single column data view,
|
||
and the key-values will be taken from that column. If unspecified, the ordering will be determined from the input data upon fitting.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CategoricalCatalog.OneHotEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,Microsoft.ML.InputOutputColumnPair[],Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality,Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.OneHotEncodingEstimator"/>, which converts one or more input text columns specified in <paramref name="columns"/>
|
||
into as many columns of one-hot encoded vectors.
|
||
</summary>
|
||
<remarks>If multiple columns are passed to the estimator, all of the columns will be processed in a single pass over the data.
|
||
Therefore, it is more efficient to specify one estimator with many columns than it is to specify many estimators each with a single column.</remarks>
|
||
<param name="catalog">The transform catalog.</param>
|
||
<param name="columns">The pairs of input and output columns. The output columns' data type will be a vector of <see cref="T:System.Single"/> if <paramref name="outputKind"/> is
|
||
<see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag"/>, <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator"/>, and <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Binary"/>.
|
||
If <paramref name="outputKind"/> is <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Key"/>, the output columns' data type will be a key in the case of scalar input column
|
||
or a vector of keys in the case of a vector input column.</param>
|
||
<param name="outputKind">Output kind: Bag (multi-set vector), Ind (indicator vector), Key (index), or Binary encoded indicator vector.</param>
|
||
<param name="maximumNumberOfKeys">Maximum number of terms to keep per column when auto-training.</param>
|
||
<param name="keyOrdinality">How items should be ordered when vectorized. If <see cref="F:Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality.ByOccurrence"/>
|
||
choosen they will be in the order encountered. If <see cref="F:Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality.ByValue"/>,
|
||
items are sorted according to their default comparison, for example, text sorting will be case sensitive (for example, 'A' then 'Z' then 'a').</param>
|
||
<param name="keyData">Specifies an ordering for the encoding. If specified, this should be a single column data view,
|
||
and the key-values will be taken from that column. If unspecified, the ordering will be determined from the input data upon fitting.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CategoricalCatalog.OneHotEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,Microsoft.ML.Transforms.OneHotEncodingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Convert several text column into one-hot encoded vectors.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The column settings.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CategoricalCatalog.OneHotEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,Microsoft.ML.Transforms.OneHotEncodingEstimator.ColumnOptions[],Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Convert several text column into one-hot encoded vectors.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The column settings.</param>
|
||
<param name="keyData">Specifies an ordering for the encoding. If specified, this should be a single column data view,
|
||
and the key-values will be taken from that column. If unspecified, the ordering will be determined from the input data upon fitting.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CategoricalCatalog.OneHotHashEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,System.String,System.String,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.OneHotHashEncodingEstimator"/>, which converts a text column specified by <paramref name="inputColumnName"/>
|
||
into a hash-based one-hot encoded vector column named <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<param name="catalog">The transform catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a vector of <see cref="T:System.Single"/> if <paramref name="outputKind"/> is
|
||
<see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag"/>, <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator"/>, and <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Binary"/>.
|
||
If <paramref name="outputKind"/> is <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Key"/>, this column's data type will be a key in the case of a scalar input column
|
||
or a vector of keys in the case of a vector input column. </param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This column's data type can be scalar or vector of numeric, text, boolean, <see cref="T:System.DateTime"/> or <see cref="T:System.DateTimeOffset"/>.</param>
|
||
<param name="outputKind">The conversion mode.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each term should be included in the hash.</param>
|
||
<param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CategoricalCatalog.OneHotHashEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,Microsoft.ML.InputOutputColumnPair[],Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.OneHotHashEncodingEstimator"/>, which converts one or more input text columns specified by <paramref name="columns"/>
|
||
into as many columns of hash-based one-hot encoded vectors.
|
||
</summary>
|
||
<remarks>If multiple columns are passed to the estimator, all of the columns will be processed in a single pass over the data.
|
||
Therefore, it is more efficient to specify one estimator with many columns than it is to specify many estimators each with a single column.
|
||
</remarks>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The pairs of input and output columns. The output columns' data type will be a vector of <see cref="T:System.Single"/> if <paramref name="outputKind"/> is
|
||
<see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag"/>, <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator"/>, and <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Binary"/>.
|
||
If <paramref name="outputKind"/> is <see cref="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Key"/>, the output columns' data type will be a key in the case of scalar input column
|
||
or a vector of keys in the case of a vector input column.</param>
|
||
<param name="outputKind">The conversion mode.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each term should be included in the hash.</param>
|
||
<param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column. Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CategoricalCatalog.OneHotHashEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,Microsoft.ML.Transforms.OneHotHashEncodingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Convert several text column into hash-based one-hot encoded vectors.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The column settings.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CountFeatureSelectingEstimator">
|
||
<summary>
|
||
Selects the slots for which the count of non-default values is greater than or equal to a threshold.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< data types|
|
||
| Output column data type | Same as the input column|
|
||
| Exportable to ONNX | Yes |
|
||
|
||
This transform uses a set of aggregators to count the number of values for each slot (vector element)
|
||
that are non-default and non-missing (for the definitions of default and missing, refer to the remarks section
|
||
in <xref:Microsoft.ML.Data.DataKind>). If the count value is less than the provided count parameter, that slot is dropped.
|
||
This transform is useful when applied together with a <xref:Microsoft.ML.Transforms.OneHotHashEncodingTransformer>.
|
||
It can remove the features generated by the hash transform that have no data in the examples.
|
||
|
||
For example, if we set the count parameter to 3 and fit the estimator, apply the transformer to the following Features column,
|
||
we would see the second slot, containing: NaN (missing value), 5, 5, 0 (default value) values being dropped because that slot
|
||
has only two non-default and non-missing values, i.e. the two 5 values.
|
||
The third slot is being kept, because it has the values 6, 6, 6, NaN; so it has 3 non-default and non-missing.
|
||
|
||
| Features |
|
||
| -- |
|
||
|4,NaN,6 |
|
||
|4,5,6 |
|
||
|4,5,6 |
|
||
|4,0,NaN|
|
||
|
||
This is how the dataset above would look, after the transformation.
|
||
|
||
| Features |
|
||
| -- |
|
||
|4,6 |
|
||
|4,6 |
|
||
|4,6 |
|
||
|4,NaN|
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnCount(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,Microsoft.ML.InputOutputColumnPair[],System.Int64)"/>
|
||
<seealso cref="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnCount(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,System.String,System.String,System.Int64)"/>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.ColumnOptions.Name">
|
||
<summary> Name of the column resulting from the transformation of <see cref="F:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.ColumnOptions.InputColumnName"/>.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.ColumnOptions.InputColumnName">
|
||
<summary> Name of the column to transform.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.ColumnOptions.Count">
|
||
<summary>If the count of non-default values for a slot is greater than or equal to this threshold in the training data, the slot is preserved.</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.ColumnOptions.#ctor(System.String,System.String,System.Int64)">
|
||
<summary>
|
||
Describes the parameters of the feature selection process for a column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="count">If the count of non-default values for a slot is greater than or equal to this threshold in the training data, the slot is preserved.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.CountFeatureSelectingEstimator.ColumnOptions[])">
|
||
<member name="CountFeatureSelection">
|
||
<summary>
|
||
Selects the slots for which the count of non-default values is greater than or equal to a threshold.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
This transform uses a set of aggregators to count the number of non-default values for each slot and
|
||
instantiates a <see cref="T:Microsoft.ML.Transforms.SlotsDroppingTransformer" /> to actually drop the slots.
|
||
This transform is useful when applied together with a <see cref="T:Microsoft.ML.Transforms.OneHotHashEncodingTransformer" />.
|
||
The count feature selection can remove those features generated by the hash transform that have no data in the examples.
|
||
</para>
|
||
</remarks>
|
||
</member>
|
||
<param name="env">The environment to use.</param>
|
||
<param name="columns">Describes the parameters of the feature selection process for each column pair.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Int64)">
|
||
<member name="CountFeatureSelection">
|
||
<summary>
|
||
Selects the slots for which the count of non-default values is greater than or equal to a threshold.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
This transform uses a set of aggregators to count the number of non-default values for each slot and
|
||
instantiates a <see cref="T:Microsoft.ML.Transforms.SlotsDroppingTransformer" /> to actually drop the slots.
|
||
This transform is useful when applied together with a <see cref="T:Microsoft.ML.Transforms.OneHotHashEncodingTransformer" />.
|
||
The count feature selection can remove those features generated by the hash transform that have no data in the examples.
|
||
</para>
|
||
</remarks>
|
||
</member>
|
||
<param name="env">The environment to use.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName" />.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null" />, the value of the <paramref name="outputColumnName" /> will be used as source.</param>
|
||
<param name="minCount">If the count of non-default values for a slot is greater than or equal to this threshold in the training data, the slot is preserved.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.ITransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountFeatureSelectingEstimator.Create(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.CountFeatureSelectingEstimator.Options,Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Create method corresponding to SignatureDataTransform.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountFeatureSelectionUtils.Train(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.String[],System.Int32[]@)">
|
||
<summary>
|
||
Returns the feature selection scores for each slot of each column.
|
||
</summary>
|
||
<param name="env">The host environment.</param>
|
||
<param name="input">The input dataview.</param>
|
||
<param name="columns">The columns for which to compute the feature selection scores.</param>
|
||
<param name="colSizes">Outputs an array containing the vector sizes of the input columns</param>
|
||
<returns>A list of scores.</returns>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CustomMappingFactoryAttributeAttribute">
|
||
<summary>
|
||
Place this attribute onto a type to cause it to be considered a custom mapping factory.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CustomMappingFactory`2">
|
||
<summary>
|
||
The base type for custom mapping factories.
|
||
</summary>
|
||
<typeparam name="TSrc">The type that describes what 'source' columns are consumed from the input <see cref="T:Microsoft.ML.IDataView"/>.</typeparam>
|
||
<typeparam name="TDst">The type that describes what new columns are added by this transform.</typeparam>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CustomMappingFactory`2.GetMapping">
|
||
<summary>
|
||
Returns the mapping delegate that maps from <typeparamref name="TSrc"/> inputs to <typeparamref name="TDst"/> outputs.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.StatefulCustomMappingFactory`3">
|
||
<summary>
|
||
The base type for stateful custom mapping factories.
|
||
</summary>
|
||
<typeparam name="TSrc">The type that describes what 'source' columns are consumed from the input <see cref="T:Microsoft.ML.IDataView"/>.</typeparam>
|
||
<typeparam name="TDst">The type that describes what new columns are added by this transform.</typeparam>
|
||
<typeparam name="TState">The type that describes the state object the mapping uses.</typeparam>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulCustomMappingFactory`3.GetMapping">
|
||
<summary>
|
||
Returns the mapping delegate that maps from a <typeparamref name="TSrc"/> input and a state object of type <typeparamref name="TState"/>,
|
||
to a <typeparamref name="TDst"/> output.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulCustomMappingFactory`3.GetStateInitAction">
|
||
<summary>
|
||
Returns an action that is called once before the row cursor is initialized, to initialize the state object used by the cursor.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CustomMappingTransformer`2">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting an <see cref="T:Microsoft.ML.Transforms.CustomMappingEstimator`2"/>.
|
||
</summary>
|
||
<typeparam name="TSrc">The type that describes what 'source' columns are consumed from the input <see cref="T:Microsoft.ML.IDataView"/>.</typeparam>
|
||
<typeparam name="TDst">The type that describes what new columns are added by this transform.</typeparam>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.CustomMappingTransformer`2.Microsoft#ML#ITransformer#IsRowToRowMapper">
|
||
<summary>
|
||
Whether a call to <see cref="M:Microsoft.ML.ITransformer.GetRowToRowMapper(Microsoft.ML.DataViewSchema)"/> should succeed, on an
|
||
appropriate schema.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CustomMappingTransformer`2.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.Action{`0,`1},System.String,Microsoft.ML.Data.SchemaDefinition,Microsoft.ML.Data.SchemaDefinition)">
|
||
<summary>
|
||
Create a custom mapping of input columns to output columns.
|
||
</summary>
|
||
<param name="env">The host environment</param>
|
||
<param name="mapAction">The action by which we map source to destination columns</param>
|
||
<param name="contractName">The name of the action (will be saved to the model).</param>
|
||
<param name="inputSchemaDefinition">Additional parameters for schema mapping between <typeparamref name="TSrc"/> and input data.</param>
|
||
<param name="outputSchemaDefinition">Additional parameters for schema mapping between <typeparamref name="TDst"/> and output data.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CustomMappingTransformer`2.GetOutputSchema(Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.DataViewSchema"/> which would be produced by the transformer applied to
|
||
an input data with schema <paramref name="inputSchema"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CustomMappingTransformer`2.Transform(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Take the data in, make transformations, output the data.
|
||
Note that <see cref="T:Microsoft.ML.IDataView"/>'s are lazy, so no actual transformations happen here, just schema validation.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CustomMappingTransformer`2.Microsoft#ML#ITransformer#GetRowToRowMapper(Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Constructs a row-to-row mapper based on an input schema. If <see cref="P:Microsoft.ML.ITransformer.IsRowToRowMapper"/>
|
||
is <c>false</c>, then an exception is thrown. If the <paramref name="inputSchema"/> is in any way
|
||
unsuitable for constructing the mapper, an exception is likewise thrown.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CustomMappingEstimator`2">
|
||
<summary>
|
||
Applies a custom mapping function to the specified input columns. The result will be in output columns.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
|
||
### Estimator Characteristics
|
||
| | |
|
||
| -- | -- |
|
||
| Does this estimator need to look at the data to train its parameters? | No |
|
||
| Input column data type | Any |
|
||
| Output column data type | Any |
|
||
| Exportable to ONNX | No |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.CustomMappingTransformer`2> applies a user defined mapping
|
||
to one or more input columns and produces one or more output columns. This transformation doesn't change the number of rows,
|
||
and can be seen as the result of applying the user's function to every row of the input data.
|
||
|
||
The provided custom function must be thread-safe and free from side effects.
|
||
The order with which it is applied to the rows of data cannot be guaranteed.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.CustomMappingCatalog.CustomMapping``2(Microsoft.ML.TransformsCatalog,System.Action{``0,``1},System.String,Microsoft.ML.Data.SchemaDefinition,Microsoft.ML.Data.SchemaDefinition)"/>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CustomMappingEstimator`2.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.Action{`0,`1},System.String,Microsoft.ML.Data.SchemaDefinition,Microsoft.ML.Data.SchemaDefinition)">
|
||
<summary>
|
||
Create a custom mapping of input columns to output columns.
|
||
</summary>
|
||
<param name="env">The host environment</param>
|
||
<param name="mapAction">The mapping action. This must be thread-safe and free from side effects.</param>
|
||
<param name="contractName">The contract name, used by ML.NET for loading the model. If <c>null</c> is specified, such a trained model would not be save-able.</param>
|
||
<param name="inputSchemaDefinition">Additional parameters for schema mapping between <typeparamref name="TSrc"/> and input data.</param>
|
||
<param name="outputSchemaDefinition">Additional parameters for schema mapping between <typeparamref name="TDst"/> and output data.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CustomMappingEstimator`2.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.ICountTable.GetCounts(System.Int64,System.Span{System.Single})">
|
||
<summary>
|
||
Populate the <paramref name="counts"/> array with the counts for the input key
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.ICountTable.GarbageThreshold">
|
||
<summary>
|
||
Garbage threshold the table is using
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.SignatureCountTableBuilder">
|
||
<summary>
|
||
Signature for CountTableBuilder.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CountTableBuilderBase">
|
||
<summary>
|
||
Builds a table that provides counts to the <see cref="T:Microsoft.ML.Transforms.CountTargetEncodingTransformer"/>
|
||
by going over the training data.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountTableBuilderBase.CreateCMCountTableBuilder(System.Int32,System.Int32)">
|
||
<summary>
|
||
Create a builder that creates the count table using the count-min sketch structure, which has a smaller memory footprint,
|
||
at the expense of some possible overcounting due to collisions.
|
||
</summary>
|
||
<param name="depth">The depth of the count-min sketch table.</param>
|
||
<param name="width">The width of the count-min sketch table.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountTableBuilderBase.CreateDictionaryCountTableBuilder(System.Single)">
|
||
<summary>
|
||
Create a builder that creates the count table by building a dictionary containing the exact count of each
|
||
categorical feature value.
|
||
</summary>
|
||
<param name="garbageThreshold">The garbage threshold (counts below or equal to the threshold are assigned to the garbage bin).</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CountTargetEncodingEstimator">
|
||
<summary>
|
||
Transforms a categorical column into a set of features that includes the count of each label class,
|
||
the log-odds for each label class and the back-off indicator.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
### Estimator Characteristics
|
||
| | |
|
||
| -- | -- |
|
||
| Does this estimator need to look at the data to train its parameters? | Yes |
|
||
| Input column data type | Any |
|
||
| Output column data type | Vector of <xref:System.Single>. |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.CountTargetEncodingTransformer> creates a new column, named as specified in the output column name parameters,
|
||
containing three parts: the count of each label class, the log-odds for each label class and the back-off indicator.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.Transforms.CountTargetEncodingCatalog.CountTargetEncode(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],Microsoft.ML.Transforms.CountTargetEncodingTransformer,System.String)" />
|
||
<seealso cref="M:Microsoft.ML.Transforms.CountTargetEncodingCatalog.CountTargetEncode(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.String,Microsoft.ML.Transforms.CountTableBuilderBase,System.Single,System.Single,System.Boolean,System.Int32,System.Boolean,System.UInt32)" />
|
||
<seealso cref="M:Microsoft.ML.Transforms.CountTargetEncodingCatalog.CountTargetEncode(Microsoft.ML.TransformsCatalog,System.String,Microsoft.ML.Transforms.CountTargetEncodingTransformer,System.String,System.String)"/>
|
||
<seealso cref="M:Microsoft.ML.Transforms.CountTargetEncodingCatalog.CountTargetEncode(Microsoft.ML.TransformsCatalog,System.String,System.String,System.String,Microsoft.ML.Transforms.CountTableBuilderBase,System.Single,System.Single,System.Int32,System.Boolean,System.UInt32)"/>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CountTargetEncodingEstimator.Options">
|
||
<summary>
|
||
This is a merger of arguments for <see cref="T:Microsoft.ML.Transforms.CountTableTransformer"/> and <see cref="T:Microsoft.ML.Transforms.HashingTransformer"/>
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.CountTargetEncodingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator"/> or <see cref="T:Microsoft.ML.Transforms.CountTargetEncodingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountTargetEncodingCatalog.CountTargetEncode(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.String,Microsoft.ML.Transforms.CountTableBuilderBase,System.Single,System.Single,System.Boolean,System.Int32,System.Boolean,System.UInt32)">
|
||
<summary>
|
||
Transforms a categorical column into a set of features that includes the count of each label class,
|
||
the log-odds for each label class and the back-off indicator.
|
||
</summary>
|
||
<param name="catalog">The transforms catalog.</param>
|
||
<param name="columns">The input and output columns.</param>
|
||
<param name="labelColumn">The name of the label column.</param>
|
||
<param name="builder">The builder that creates the count tables from the training data.</param>
|
||
<param name="priorCoefficient">The coefficient with which to apply the prior smoothing to the features.</param>
|
||
<param name="laplaceScale">The Laplacian noise diversity/scale-parameter. Recommended values are between 0 and 1. Note that the noise
|
||
will only be applied if the estimator is part of an <see cref="T:Microsoft.ML.Data.EstimatorChain`1"/>, when fitting the next estimator in the chain.</param>
|
||
<param name="sharedTable">Indicates whether to keep counts for all columns and slots in one shared count table. If true, the keys in the count table
|
||
will include a hash of the column and slot indices.</param>
|
||
<param name="numberOfBits">The number of bits to hash the input into. Must be between 1 and 31, inclusive.</param>
|
||
<param name="combine">In case the input is a vector column, indicates whether the values should be combined into a single hash to create a single
|
||
count table, or be left as a vector of hashes with multiple count tables.</param>
|
||
<param name="hashingSeed">The seed used for hashing the input columns.</param>
|
||
<returns></returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountTargetEncodingCatalog.CountTargetEncode(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],Microsoft.ML.Transforms.CountTargetEncodingTransformer,System.String)">
|
||
<summary>
|
||
Transforms a categorical column into a set of features that includes the count of each label class,
|
||
the log-odds for each label class and the back-off indicator.
|
||
</summary>
|
||
<param name="catalog">The transforms catalog.</param>
|
||
<param name="columns">The input and output columns.</param>
|
||
<param name="initialCounts">A previously trained count table containing initial counts.</param>
|
||
<param name="labelColumn">The name of the label column.</param>
|
||
<returns></returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountTargetEncodingCatalog.CountTargetEncode(Microsoft.ML.TransformsCatalog,System.String,System.String,System.String,Microsoft.ML.Transforms.CountTableBuilderBase,System.Single,System.Single,System.Int32,System.Boolean,System.UInt32)">
|
||
<summary>
|
||
Transforms a categorical column into a set of features that includes the count of each label class,
|
||
the log-odds for each label class and the back-off indicator.
|
||
</summary>
|
||
<param name="catalog">The transforms catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="labelColumn">The name of the label column.</param>
|
||
<param name="builder">The builder that creates the count tables from the training data.</param>
|
||
<param name="priorCoefficient">The coefficient with which to apply the prior smoothing to the features.</param>
|
||
<param name="laplaceScale">The Laplacian noise diversity/scale-parameter. Recommended values are between 0 and 1. Note that the noise
|
||
will only be applied if the estimator is part of an <see cref="T:Microsoft.ML.Data.EstimatorChain`1"/>, when fitting the next estimator in the chain.</param>
|
||
<param name="numberOfBits">The number of bits to hash the input into. Must be between 1 and 31, inclusive.</param>
|
||
<param name="combine">In case the input is a vector column, indicates whether the values should be combined into a single hash to create a single
|
||
count table, or be left as a vector of hashes with multiple count tables.</param>
|
||
<param name="hashingSeed">The seed used for hashing the input columns.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.CountTargetEncodingCatalog.CountTargetEncode(Microsoft.ML.TransformsCatalog,System.String,Microsoft.ML.Transforms.CountTargetEncodingTransformer,System.String,System.String)">
|
||
<summary>
|
||
Transforms a categorical column into a set of features that includes the count of each label class,
|
||
the log-odds for each label class and the back-off indicator.
|
||
</summary>
|
||
<param name="catalog">The transforms catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="initialCounts">A previously trained count table containing initial counts.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="labelColumn">The name of the label column.</param>
|
||
<returns></returns>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MultiCountTableBuilderBase">
|
||
<summary>
|
||
Handles simultaneous counting for multiple columns and slots. Incapsulates the counting strategy:
|
||
either keep everything in one big count table, or have a count table per column and slot
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MultiCountTableBase">
|
||
<summary>
|
||
Incapsulates count tables (or one count table) for multiple columns and slots.
|
||
Handles (de)serialization and featurization.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.ParallelMultiCountTableBuilder">
|
||
<summary>
|
||
Implements the multi count table builder logic by keeping a count table per column and per slot
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.BagMultiCountTableBuilder">
|
||
<summary>
|
||
Implements the multi count table builder by creating one count table for everything
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.BagMultiCountTableBuilder.MultiCountTable.ProxyCountTable">
|
||
<summary>
|
||
Mixes the column and slot index into the key, and then passes it to the wrapped count table
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextAnalytics">
|
||
<summary>
|
||
Entry points for text anylytics transforms.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.LatentDirichletAllocationTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.LatentDirichletAllocationTransformer.ModelParameters">
|
||
<summary>
|
||
Provide details about the topics discovered by <a href="https://arxiv.org/abs/1412.1576">LightLDA.</a>
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.LatentDirichletAllocationTransformer.GetLdaDetails(System.Int32)">
|
||
<summary>
|
||
Method to provide details about the topics discovered by LightLDA
|
||
</summary>
|
||
<param name="columnIndex">index of column options pair</param>
|
||
<returns></returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.LatentDirichletAllocationTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.LatentDirichletAllocationTransformer.LdaState[],System.Collections.Generic.List{Microsoft.ML.Data.VBuffer{System.ReadOnlyMemory{System.Char}}},Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Initializes a new <see cref="T:Microsoft.ML.Transforms.Text.LatentDirichletAllocationTransformer"/> object.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="ldas">An array of LdaState objects, where ldas[i] is learnt from the i-th element of <paramref name="columns"/>.</param>
|
||
<param name="columnMappings">A list of mappings, where columnMapping[i] is a map of slot names for the i-th element of <paramref name="columns"/>.</param>
|
||
<param name="columns">Describes the parameters of the LDA process for each column pair.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator">
|
||
<summary>
|
||
The LDA transform implements <a href="https://arxiv.org/abs/1412.1576">LightLDA</a>, a state-of-the-art implementation of Latent Dirichlet Allocation.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< algorithm that infers semantic structure from text data,
|
||
and ultimately helps answer the question on "what is this document about?".
|
||
It can be used to featurize any text fields as low-dimensional topical vectors.
|
||
LightLDA is an extremely efficient implementation of LDA that incorporates a number of
|
||
optimization techniques.
|
||
With the LDA transform, ML.NET users can train a topic model to produce 1 million topics with 1 million words vocabulary
|
||
on a 1-billion-token document set one a single machine in a few hours(typically, LDA at this scale takes days and requires large clusters).
|
||
The most significant innovation is a super-efficient $O(1)$. [Metropolis-Hastings sampling algorithm](https://en.wikipedia.org/wiki/Metropolis–Hastings_algorithm),
|
||
whose running cost is agnostic of model size, allowing it to converges nearly an order of magnitude faster than other [Gibbs samplers](https://en.wikipedia.org/wiki/Gibbs_sampling).
|
||
|
||
In an ML.NET pipeline, this estimator requires the output of some preprocessing, as its input.
|
||
A typical pipeline operating on text would require text normalization, tokenization and producing n-grams to supply to the LDA estimator.
|
||
See the example usage in the See Also section for usage suggestions.
|
||
|
||
If we have the following three examples of text, as data points, and use the LDA transform with the number of topics set to 3,
|
||
we would get the results displayed in the table below. Example documents:
|
||
* I like to eat bananas.
|
||
* I eat bananas everyday.
|
||
* First celebrated in 1970, Earth Day now includes events in more than 193 countries,
|
||
which are now coordinated globally by the Earth Day Network.
|
||
|
||
Notice the similarity in values of the first and second row, compared to the third,
|
||
and see how those values are indicative of similarities between those two (small) bodies of text.
|
||
|
||
| Topic1 | Topic2 | Topic 3 |
|
||
| ------- | ------- | ------- |
|
||
| 0.5714 | 0.0000 | 0.4286 |
|
||
| 0.5714 | 0.0000 | 0.4286 |
|
||
| 0.2400 | 0.3200 | 0.4400 |
|
||
|
||
For more technical details you can consult the following papers.
|
||
* [LightLDA: Big Topic Models on Modest Computer Clusters](https://arxiv.org/abs/1412.1576)
|
||
* [LightLDA](https://github.com/Microsoft/LightLDA)
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.LatentDirichletAllocation(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Single,System.Single,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Boolean)"/>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Int32,System.Single,System.Single,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Boolean,System.Boolean)">
|
||
<!-- No matching elements were found for the following include tag --><include file="doc.xml" path="doc/members/member[@name="LightLDA"]/*" />
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName" />.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null" />, the value of the <paramref name="outputColumnName" /> will be used as source.</param>
|
||
<param name="numberOfTopics">The number of topics.</param>
|
||
<param name="alphaSum">Dirichlet prior on document-topic vectors.</param>
|
||
<param name="beta">Dirichlet prior on vocab-topic vectors.</param>
|
||
<param name="samplingStepCount">Number of Metropolis Hasting step.</param>
|
||
<param name="maximumNumberOfIterations">Number of iterations.</param>
|
||
<param name="numberOfThreads">The number of training threads. Default value depends on number of logical processors.</param>
|
||
<param name="maximumTokenCountPerDocument">The threshold of maximum count of tokens per doc.</param>
|
||
<param name="numberOfSummaryTermsPerTopic">The number of words to summarize the topic.</param>
|
||
<param name="likelihoodInterval">Compute log likelihood over local dataset on this iteration interval.</param>
|
||
<param name="numberOfBurninIterations">The number of burn-in iterations.</param>
|
||
<param name="resetRandomGenerator">Reset the random number generator for each document.</param>
|
||
<param name="outputTopicWordSummary">Whether to output the topic-word summary in text format when saving the model to disk.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions[])">
|
||
<!-- No matching elements were found for the following include tag --><include file="doc.xml" path="doc/members/member[@name="LightLDA"]/*" />
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Describes the parameters of the LDA process for each column pair.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.Name">
|
||
<summary>
|
||
Name of the column resulting from the transformation of <cref see="InputColumnName"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.InputColumnName">
|
||
<summary>
|
||
Name of column to transform.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.NumberOfTopics">
|
||
<summary>
|
||
The number of topics.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.AlphaSum">
|
||
<summary>
|
||
Dirichlet prior on document-topic vectors.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.Beta">
|
||
<summary>
|
||
Dirichlet prior on vocab-topic vectors.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.SamplingStepCount">
|
||
<summary>
|
||
Number of Metropolis Hasting step.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.NumberOfIterations">
|
||
<summary>
|
||
Number of iterations.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.LikelihoodInterval">
|
||
<summary>
|
||
Compute log likelihood over local dataset on this iteration interval.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.NumberOfThreads">
|
||
<summary>
|
||
The number of training threads.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.MaximumTokenCountPerDocument">
|
||
<summary>
|
||
The threshold of maximum count of tokens per doc.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.NumberOfSummaryTermsPerTopic">
|
||
<summary>
|
||
The number of words to summarize the topic.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.NumberOfBurninIterations">
|
||
<summary>
|
||
The number of burn-in iterations.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.ResetRandomGenerator">
|
||
<summary>
|
||
Reset the random number generator for each document.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.OutputTopicWordSummary">
|
||
<summary>
|
||
Whether to output the topic-word summary in text format when saving the model to disk.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions.#ctor(System.String,System.String,System.Int32,System.Single,System.Single,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Boolean,System.Boolean)">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">The column containing the output scores over a set of topics, represented as a vector of floats. </param>
|
||
<param name="inputColumnName">The column representing the document as a vector of floats.A null value for the column means <paramref name="inputColumnName"/> is replaced. </param>
|
||
<param name="numberOfTopics">The number of topics.</param>
|
||
<param name="alphaSum">Dirichlet prior on document-topic vectors.</param>
|
||
<param name="beta">Dirichlet prior on vocab-topic vectors.</param>
|
||
<param name="samplingStepCount">Number of Metropolis Hasting step.</param>
|
||
<param name="maximumNumberOfIterations">Number of iterations.</param>
|
||
<param name="likelihoodInterval">Compute log likelihood over local dataset on this iteration interval.</param>
|
||
<param name="numberOfThreads">The number of training threads. Default value depends on number of logical processors.</param>
|
||
<param name="maximumTokenCountPerDocument">The threshold of maximum count of tokens per doc.</param>
|
||
<param name="numberOfSummaryTermsPerTopic">The number of words to summarize the topic.</param>
|
||
<param name="numberOfBurninIterations">The number of burn-in iterations.</param>
|
||
<param name="resetRandomGenerator">Reset the random number generator for each document.</param>
|
||
<param name="outputTopicWordSummary">Whether to output the topic-word summary in text format when saving the model to disk.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.Transforms.Text.LatentDirichletAllocationTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramHashingTransformer">
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>.
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramHashingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Constructor for case where you don't need to 'train' transform on data, for example, MaximumNumberOfInverts for all columns set to zero.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="columns">Description of dataset columns and how to process them.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingTransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< type. |
|
||
| Output column data type | Vector of known size of <xref:System.Single> |
|
||
| Exportable to ONNX | No |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.Text.NgramHashingTransformer> creates a new column, named as specified in the output column name parameters, and
|
||
produces a vector of n-gram counts (sequences of consecutive words of length 1-n) from a given data.
|
||
It does so by hashing each n-gram and using the hash value as the index in the bag.
|
||
|
||
<xref:Microsoft.ML.Transforms.Text.NgramHashingEstimator> is different from <xref:Microsoft.ML.Transforms.Text.WordHashBagEstimator>
|
||
in a way that The former takes tokenized text as input while the latter tokenizes text internally.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.ProduceHashedNgrams(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32,System.Boolean)" />
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one pair of mulitple inputs - singular output columns.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.Name">
|
||
<summary>Name of the column resulting from the transformation of <see cref="P:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.InputColumnNames"/>.</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.InputColumnNames">
|
||
<summary>Names of the columns to transform.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.NgramLength">
|
||
<summary>Maximum n-gram length.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.SkipLength">
|
||
<summary>Maximum number of tokens to skip when constructing an n-gram.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.UseAllLengths">
|
||
<summary>Whether to store all n-gram lengths up to <see cref="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.NgramLength"/>, or only <see cref="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.NgramLength"/>.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.NumberOfBits">
|
||
<summary>Number of bits to hash into. Must be between 1 and 31, inclusive.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.Seed">
|
||
<summary>Hashing seed.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.UseOrderedHashing">
|
||
<summary>Whether the position of each term should be included in the hash.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.MaximumNumberOfInverts">
|
||
<summary>
|
||
During hashing we constuct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.
|
||
Hashing, as such, can map many initial values to one.
|
||
<see cref="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.MaximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.RehashUnigrams">
|
||
<summary>Whether to rehash unigrams.</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.#ctor(System.String,System.String[],System.Int32,System.Int32,System.Boolean,System.Int32,System.UInt32,System.Boolean,System.Int32,System.Boolean)">
|
||
<summary>
|
||
Describes how the transformer maps several input columns, <paramref name="inputColumnNames"/>, to a output column, <paramref name="name"/>.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnNames"/>.</param>
|
||
<param name="inputColumnNames">Names of the columns to transform. </param>
|
||
<param name="ngramLength">Maximum n-gram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to store all n-gram lengths up to <paramref name="ngramLength"/>, or only <paramref name="ngramLength"/>.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 31, inclusive.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each term should be included in the hash.</param>
|
||
<param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.
|
||
Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
<param name="rehashUnigrams">Whether to rehash unigrams.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramHashingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Produces a bag of counts of hashed n-grams in <paramref name="inputColumnName"/>
|
||
and outputs n-gram vector as <paramref name="outputColumnName"/>
|
||
|
||
<see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> in a way that <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>
|
||
takes tokenized text as input while <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> tokenizes text internally.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of output column, will contain the n-gram vector. Null means <paramref name="inputColumnName"/> is replaced.</param>
|
||
<param name="inputColumnName">Name of input column containing tokenized text.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramHashingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String[],System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Produces a bag of counts of hashed n-grams in <paramref name="inputColumnNames"/>
|
||
and outputs n-gram vector as <paramref name="outputColumnName"/>
|
||
|
||
<see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> in a way that <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>
|
||
takes tokenized text as input while <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> tokenizes text internally.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of output column, will contain the n-gram vector.</param>
|
||
<param name="inputColumnNames">Name of input columns containing tokenized text.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramHashingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Produces a bag of counts of hashed n-grams in <paramref name="columns.inputs.inputs"/>
|
||
and outputs n-gram vector for each output in <paramref name="columns.output.output"/>
|
||
|
||
<see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> in a way that <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>
|
||
takes tokenized text as input while <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> tokenizes text internally.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Array of columns which specifies the behavior of the transformation.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramHashingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramHashingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramExtractingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting an <see cref="T:Microsoft.ML.Transforms.Text.NgramExtractingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramExtractingEstimator">
|
||
<summary>
|
||
Produces a vector of counts of n-grams (sequences of consecutive words) encountered in the input text.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< type. |
|
||
| Output column data type | Known-sized vector of <xref:System.Single> |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.Text.NgramExtractingTransformer>
|
||
creates a new column, named as specified in the output column name parameters, where each
|
||
input vector is mapped to a vector of counts of n-grams (sequences of consecutive words) encountered in the input text.
|
||
|
||
The estimator builds a dictionary of n-grams and the <xref:Microsoft.ML.Transforms.Text.NgramExtractingTransformer>
|
||
uses the id in the dictionary as the index in the count vector that it produces.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.ProduceNgrams(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria)"/>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria">
|
||
<summary>
|
||
A statistical measure used to evaluate how important a word is to a document in a corpus.
|
||
This enumeration is serialized.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria.Tf">
|
||
<summary>Term Frequency. Calculated based on the number of occurrences in the document.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria.Idf">
|
||
<summary>
|
||
Inverse Document Frequency. A ratio (the logarithm of inverse relative frequency)
|
||
that measures the information a slot provides by determining how common or rare it is across the entire corpus.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria.TfIdf">
|
||
<summary>The product of the term frequency and the inverse document frequency.</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria)">
|
||
<summary>
|
||
Produces a bag of counts of n-grams (sequences of consecutive words) in <paramref name="inputColumnName"/>
|
||
and outputs bag of word vector as <paramref name="outputColumnName"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="weighting">Statistical measure used to evaluate how important a word is to a document in a corpus.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[],System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria)">
|
||
<summary>
|
||
Produces a bag of counts of n-grams (sequences of consecutive words) in <paramref name="columns.inputs.inputs"/>
|
||
and outputs bag of word vector for each output in <paramref name="columns.output.output"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to compute bag of word vector.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="weighting">Statistical measure used to evaluate how important a word is to a document in a corpus.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Produces a bag of counts of n-grams (sequences of consecutive words) in <paramref name="columns.inputs.inputs"/>
|
||
and outputs bag of word vector for each output in <paramref name="columns.output.output"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Array of columns with information how to transform data.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.Transforms.Text.NgramExtractingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.Name">
|
||
<summary>Name of the column resulting from the transformation of <see cref="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.InputColumnName"/>.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.InputColumnName">
|
||
<summary>Name of column to transform.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.NgramLength">
|
||
<summary>Maximum n-gram length.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.SkipLength">
|
||
<summary>Maximum number of tokens to skip when constructing an n-gram.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.UseAllLengths">
|
||
<summary>Whether to store all n-gram lengths up to ngramLength, or only ngramLength.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.Weighting">
|
||
<summary>The weighting criteria.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions._maximumNgramsCounts">
|
||
<summary>
|
||
Underlying state of <see cref="P:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.MaximumNgramsCounts"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.MaximumNgramsCounts">
|
||
<summary>
|
||
Contains the maximum number of terms (that is, n-grams) to store in the dictionary, for each level of n-grams,
|
||
from n=1 (in position 0) up to n=<see cref="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.NgramLength"/> (in position <see cref="F:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.NgramLength"/>-1)
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions.#ctor(System.String,System.String,System.Int32,System.Int32,System.Boolean,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria,System.Int32)">
|
||
<summary>
|
||
Describes how the transformer handles one Gcn column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="ngramLength">Maximum n-gram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to store all n-gram lengths up to ngramLength, or only ngramLength.</param>
|
||
<param name="weighting">The weighting criteria.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramExtractingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.SentimentAnalyzingTransformer">
|
||
<summary>
|
||
Uses a pretrained sentiment model to score input strings.
|
||
</summary><remarks>
|
||
<para>The Sentiment transform returns the probability that the sentiment of a natural text is positive. </para>
|
||
<para>
|
||
The model was trained with the <a href="https://anthology.aclweb.org/P/P14/P14-1146.pdf">Sentiment-specific word embedding (SSWE)</a> and NGramFeaturizer on Twitter sentiment data,
|
||
similarly to the sentiment analysis part of the
|
||
<a href="https://www.microsoft.com/cognitive-services/en-us/text-analytics-api">Text Analytics cognitive service</a>.
|
||
The transform outputs a score between 0 and 1 as a sentiment prediction
|
||
(where 0 is a negative sentiment and 1 is a positive sentiment).</para>
|
||
<para>Currently it supports only English.</para>
|
||
</remarks>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.SentimentAnalyzingTransformer.AliasIfNeeded(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.String[],System.Collections.Generic.KeyValuePair{System.String,System.String}[]@)">
|
||
<summary>
|
||
If any column names in <param name="colNames" /> are present in <param name="input" />, this
|
||
method will create a transform that copies them to temporary columns. It will populate <param name="hiddenNames" />
|
||
with an array of string pairs containing the original name and the generated temporary column name, respectively.
|
||
</summary>
|
||
<param name="env"></param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.StopWordsRemovingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.StopWordsRemovingTransformer.Columns">
|
||
<summary>
|
||
Defines the behavior of the transformer.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.StopWordsRemovingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Stopword remover removes language-specific list of stop words (most common words).
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to remove stop words from.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingTransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< |
|
||
| Output column data type | Variable-sized vector of [Text](xref:Microsoft.ML.Data.TextDataViewType) |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.Text.StopWordsRemovingTransformer> creates a new column, named as specified in the output column name parameter,
|
||
and fills it with a vector of words containing all of the words in the input column **except the predefined list of stopwords for the specified language.
|
||
All text comparison made by casting predefined text and text from input column to lower case using casing rules of invariant culture.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.RemoveDefaultStopWords(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Language)" />
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Options">
|
||
<summary>
|
||
Use stop words remover that can remove language-specific list of stop words (most common words) already defined in the system.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Options.Language">
|
||
<summary>
|
||
Language of the text dataset. 'English' is default.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.ColumnOptions.Name">
|
||
<summary>Name of the column resulting from the transformation of <see cref="F:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.ColumnOptions.InputColumnName"/>.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.ColumnOptions.InputColumnName">
|
||
<summary>Name of the column to transform.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.ColumnOptions.Language">
|
||
<summary>Language-specific stop words list.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.ColumnOptions.LanguageColumn">
|
||
<summary>Optional column to use for languages. This overrides language value.</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.ColumnOptions.#ctor(System.String,System.String,Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Language,System.String)">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="language">Language-specific stop words list.</param>
|
||
<param name="languageColumn">Optional column to use for languages. This overrides language value.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Language">
|
||
<summary>
|
||
Stopwords language. This enumeration is serialized.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Language)">
|
||
<summary>
|
||
Removes stop words from incoming token streams in <paramref name="inputColumnName"/>
|
||
and outputs the token streams without stopwords as <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="language">Langauge of the input text column <paramref name="inputColumnName"/>.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[],Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Language)">
|
||
<summary>
|
||
Removes stop words from incoming token streams in input columns
|
||
and outputs the token streams without stop words as output columns.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to remove stop words on.</param>
|
||
<param name="language">Langauge of the input text columns <paramref name="columns"/>.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingTransformer.Columns">
|
||
<summary>
|
||
The names of the input output column pairs on which this transformation is applied.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String[],System.ValueTuple{System.String,System.String}[])">
|
||
<summary>
|
||
Custom stopword remover removes specified list of stop words.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="stopwords">Array of words to remove.</param>
|
||
<param name="columns">Pairs of columns to remove stop words from.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingTransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< |
|
||
| Output column data type | Vector of [Text](xref:Microsoft.ML.Data.TextDataViewType) |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingTransformer> creates a new column, named as specified by the output column name parameter, and
|
||
fills it with a vector of words containing all of the words in the input column except those given by the stopwords parameter.
|
||
All text comparison made by casting provided words and words from input column to lower case using casing rules of invariant culture.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.RemoveStopWords(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.String[])" />
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator.Options">
|
||
<summary>
|
||
Use stop words remover that can removes language-specific list of stop words (most common words) already defined in the system.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator.Options.StopWords">
|
||
<summary>
|
||
List of stop words to remove.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.String[])">
|
||
<summary>
|
||
Removes stop words from incoming token streams in <paramref name="inputColumnName"/>
|
||
and outputs the token streams without stopwords as <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="stopwords">Array of words to remove.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[],System.String[])">
|
||
<summary>
|
||
Removes stop words from incoming token streams in input columns
|
||
and outputs the token streams without stop words as output columns.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to remove stop words on.</param>
|
||
<param name="stopwords">Array of words to remove.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.IStopWordsRemoverOptions">
|
||
<summary>
|
||
Defines the different type of stop words remover supported.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator">
|
||
<summary>
|
||
An estimator that turns a collection of text documents into numerical feature vectors.
|
||
The feature vectors are normalized counts of word and/or character n-grams (based on the options supplied).
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< |
|
||
| Output column data type | Vector of <xref:System.Single> |
|
||
| Exportable to ONNX | No |
|
||
|
||
This estimator gives the user one-stop solution for doing:
|
||
* Language Detection
|
||
* [Tokenization](https://en.wikipedia.org/wiki/Lexical_analysis#Tokenization)
|
||
* [Text normalization](https://en.wikipedia.org/wiki/Text_normalization)
|
||
* [Predefined and custom stopwords removal](https://en.wikipedia.org/wiki/Stop_words)
|
||
* [Word-based or character-based Ngram extraction and SkipGram extraction (through the advanced [options](xref:Microsoft.ML.Transforms.TextFeaturizingEstimator.Options.WordFeatureExtractor))](https://en.wikipedia.org/wiki/N-gram)
|
||
* [TF, IDF or TF-IDF](https://en.wikipedia.org/wiki/Tf%E2%80%93idf)
|
||
* [L-p vector normalization](xref: Microsoft.ML.Transforms.LpNormNormalizingTransformer)
|
||
|
||
By default the features are made of (word/character) n-grams/skip-grams and the number of features are equal to the vocabulary size found by analyzing the data.
|
||
To output an additional column with the tokens generated, use [OutputTokensColumnName](xref:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.OutputTokensColumnName).
|
||
The number of features can also be specified by selecting the maximum number of n-gram to keep in the <xref:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options>, where the estimator can be further tuned.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.FeaturizeText(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options,System.String[])"/>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.FeaturizeText(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String)"/>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Language">
|
||
<summary>
|
||
Text language. This enumeration is serialized.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.NormFunction">
|
||
<summary>
|
||
Text vector normalizer kind.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.NormFunction.None">
|
||
<summary>
|
||
Use this to disable normalization.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.NormFunction.L1">
|
||
<summary>
|
||
L1-norm.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.NormFunction.L2">
|
||
<summary>
|
||
L2-norm.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.NormFunction.Infinity">
|
||
<summary>
|
||
Infinity-norm.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options">
|
||
<summary>
|
||
Advanced options for the <see cref="T:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options._stopWordsRemoverOptions">
|
||
<summary>
|
||
The underlying state of <see cref="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.StopWordsRemover"/> and <see cref="P:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.StopWordsRemoverOptions"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.StopWordsRemoverOptions">
|
||
<summary>
|
||
Option to set type of stop word remover to use.
|
||
The following options are available
|
||
<list type="bullet">
|
||
<item>
|
||
<description>The <see cref="T:Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Options"/> removes the language specific list of stop words from the input.</description>
|
||
</item>
|
||
<item>
|
||
<description>The <see cref="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator.Options"/> uses user provided list of stop words.</description>
|
||
</item>
|
||
</list>
|
||
Setting this to 'null' does not remove stop words from the input.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options._wordFeatureExtractor">
|
||
<summary>
|
||
The underlying state of <see cref="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.WordFeatureExtractorFactory"/> and <see cref="P:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.WordFeatureExtractor"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.Norm">
|
||
<summary>
|
||
Norm of the output vector. It will be normalized to one.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.WordFeatureExtractor">
|
||
<summary>
|
||
Ngram feature extractor to use for words (WordBag/WordHashBag).
|
||
Set to <see langword="null" /> to turn off n-gram generation for words.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options._charFeatureExtractor">
|
||
<summary>
|
||
The underlying state of <see cref="F:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.CharFeatureExtractorFactory"/> and <see cref="P:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.CharFeatureExtractor"/>
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options.CharFeatureExtractor">
|
||
<summary>
|
||
Ngram feature extractor to use for characters (WordBag/WordHashBag).
|
||
Set to <see langword="null" /> to turn off n-gram generation for characters.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.TransformApplierParams">
|
||
<summary>
|
||
A distilled version of the TextFeaturizingEstimator Arguments, with all fields marked readonly and
|
||
only the exact set of information needed to construct the transforms preserved.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.ITransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextNormalizingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.Text.TextNormalizingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.TextNormalizingTransformer.Columns">
|
||
<summary>
|
||
The names of the output and input column pairs on which the transformation is applied.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TextNormalizingTransformer.Mapper.IsCombiningDiacritic(System.Char)">
|
||
<summary>
|
||
Whether a character is a combining diacritic character or not.
|
||
Combining diacritic characters are the set of diacritics intended to modify other characters.
|
||
The list is provided by Office NL team.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextNormalizingEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.Transforms.Text.TextNormalizingTransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><|
|
||
| Output column data type | Scalar or variable-sized Vector of [Text](xref:Microsoft.ML.Data.TextDataViewType)|
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.Text.TextNormalizingTransformer> creates a new column, named as specified
|
||
in the output column name parameters, and normalizes the textual input data by changing case, removing diacritical marks,
|
||
punctuation marks and/or numbers.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.NormalizeText(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,Microsoft.ML.Transforms.Text.TextNormalizingEstimator.CaseMode,System.Boolean,System.Boolean,System.Boolean)" />
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TextNormalizingEstimator.CaseMode">
|
||
<summary>
|
||
Case normalization mode of text. This enumeration is serialized.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextNormalizingEstimator.CaseMode.Lower">
|
||
<summary>
|
||
Make the output characters lowercased.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextNormalizingEstimator.CaseMode.Upper">
|
||
<summary>
|
||
Make the output characters uppercased.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.TextNormalizingEstimator.CaseMode.None">
|
||
<summary>
|
||
Do not change the case of output characters.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TextNormalizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,Microsoft.ML.Transforms.Text.TextNormalizingEstimator.CaseMode,System.Boolean,System.Boolean,System.Boolean)">
|
||
<summary>
|
||
Normalizes incoming text in <paramref name="inputColumnName"/> by changing case, removing diacritical marks, punctuation marks and/or numbers
|
||
and outputs new text as <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="caseMode">Casing text using the rules of the invariant culture.</param>
|
||
<param name="keepDiacritics">Whether to keep diacritical marks or remove them.</param>
|
||
<param name="keepPunctuations">Whether to keep punctuation marks or remove them.</param>
|
||
<param name="keepNumbers">Whether to keep numbers or remove them.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TextNormalizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.TextNormalizingEstimator.CaseMode,System.Boolean,System.Boolean,System.Boolean,System.ValueTuple{System.String,System.String}[])">
|
||
<summary>
|
||
Normalizes incoming text in input columns by changing case, removing diacritical marks, punctuation marks and/or numbers
|
||
and outputs new text as output columns.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="caseMode">Casing text using the rules of the invariant culture.</param>
|
||
<param name="keepDiacritics">Whether to keep diacritical marks or remove them.</param>
|
||
<param name="keepPunctuations">Whether to keep punctuation marks or remove them.</param>
|
||
<param name="keepNumbers">Whether to keep numbers or remove them.</param>
|
||
<param name="columns">Pairs of columns to run the text normalization on.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TextNormalizingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TokenizingByCharactersTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.Text.TokenizingByCharactersEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TokenizingByCharactersTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.Boolean,System.ValueTuple{System.String,System.String}[])">
|
||
<summary>
|
||
Tokenize incoming text in input columns and output the tokens as output columns.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="useMarkerCharacters">Whether to prepend a marker character, <see langword="0x02"/>, to the beginning,
|
||
and append another marker character, <see langword="0x03"/>, to the end of the output vector of characters.</param>
|
||
<param name="columns">Pairs of columns to run the tokenization on.</param>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.TokenizingByCharactersTransformer.Columns">
|
||
<summary>
|
||
The names of the output and input column pairs on which the transformation is applied.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TokenizingByCharactersTransformer.Mapper.GetKeyValues(System.Int32,Microsoft.ML.Data.VBuffer{System.ReadOnlyMemory{System.Char}}@)">
|
||
<summary>
|
||
Get the key values (chars) corresponding to keys in the output columns.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TokenizingByCharactersEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.Transforms.Text.TokenizingByCharactersTransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< |
|
||
| Output column data type | Variable-sized vector of [key](xref:Microsoft.ML.Data.KeyDataViewType) type. |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The estimator tokenizes characters by splitting text into sequences of characters using a sliding window.
|
||
During training, the estimator builds a key-value pair dictionary with the encountered sequences of characters.
|
||
|
||
The <xref:Microsoft.ML.Transforms.Text.TokenizingByCharactersTransformer> resulting from fitting the estimator
|
||
creates a new column, named as specified in the output column name parameters, which contains the keys of the
|
||
sequences of characters that were encountered in the input.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.TokenizeIntoCharactersAsKeys(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Boolean)" />
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TokenizingByCharactersEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Boolean)">
|
||
<summary>
|
||
Tokenize incoming text in <paramref name="inputColumnName"/> and output the tokens as <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="useMarkerCharacters">Whether to prepend a marker character, <see langword="0x02"/>, to the beginning,
|
||
and append another marker character, <see langword="0x03"/>, to the end of the output vector of characters.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TokenizingByCharactersEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.Boolean,System.ValueTuple{System.String,System.String}[])">
|
||
<summary>
|
||
Tokenize incoming text in input columns and output the tokens as output columns.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="useMarkerCharacters">Whether to prepend a marker character, <see langword="0x02"/>, to the beginning,
|
||
and append another marker character, <see langword="0x03"/>, to the end of the output vector of characters.</param>
|
||
<param name="columns">Pairs of columns to run the tokenization on.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.TokenizingByCharactersEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.SignatureNgramExtractorFactory">
|
||
<summary>
|
||
Signature for creating an INgramExtractorFactory.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.ExtractorColumn">
|
||
<summary>
|
||
A many-to-one column common to both <see cref="T:Microsoft.ML.Transforms.Text.NgramExtractorTransform"/>
|
||
and <see cref="T:Microsoft.ML.Transforms.Text.NgramHashExtractingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordBagBuildingTransformer.TextExpandingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.ModelLoadContext)">
|
||
<summary>
|
||
Factory method for SignatureLoadModel.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordBagBuildingTransformer.TextExpandingTransformer.Create(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.ModelLoadContext,Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Factory method for SignatureLoadRowMapper.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordBagBuildingTransformer.TextExpandingTransformer.Create(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.ModelLoadContext,Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Factory method for SignatureLoadDataTransform.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramExtractorTransform">
|
||
<summary>
|
||
A transform that turns a collection of tokenized text (vector of ReadOnlyMemory), or vectors of keys into numerical
|
||
feature vectors. The feature vectors are counts of n-grams (sequences of consecutive *tokens* -words or keys-
|
||
of length 1-n).
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramExtractorTransform.ArgumentsBase">
|
||
<summary>
|
||
This class is a merger of <see cref="T:Microsoft.ML.Transforms.ValueToKeyMappingTransformer.Options"/> and
|
||
<see cref="T:Microsoft.ML.Transforms.Text.NgramExtractingTransformer.Options"/>, with the allLength option removed.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.TermLoaderArguments">
|
||
<summary>
|
||
Arguments for defining custom list of terms or data file containing the terms.
|
||
The class includes a subset of <see cref="T:Microsoft.ML.Transforms.ValueToKeyMappingTransformer"/>'s arguments.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.INgramExtractorFactory">
|
||
<summary>
|
||
An n-gram extractor factory interface to create an n-gram extractor transform.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.INgramExtractorFactory.UseHashingTrick">
|
||
<summary>
|
||
Whether the extractor transform created by this factory uses the hashing trick
|
||
(by using <see cref="T:Microsoft.ML.Transforms.HashingTransformer"/> or <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingTransformer"/>, for example).
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramExtractorFactory">
|
||
<summary>
|
||
An implementation of <see cref="T:Microsoft.ML.Transforms.Text.INgramExtractorFactory"/> to create <see cref="T:Microsoft.ML.Transforms.Text.NgramExtractorTransform"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramHashExtractorFactory">
|
||
<summary>
|
||
An implementation of <see cref="T:Microsoft.ML.Transforms.Text.INgramExtractorFactory"/> to create <see cref="T:Microsoft.ML.Transforms.Text.NgramHashExtractingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.NgramExtractionUtils.GenerateUniqueSourceNames(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Data.ManyToOneColumn[],Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Generates and returns unique names for columns source. Each element of the returned array is
|
||
an array of unique source names per specific column.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting an <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind)">
|
||
<summary>
|
||
Instantiates <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer"/> using the pretrained word embedding model specified by <paramref name="modelKind"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="modelKind">The pretrained word embedding model.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.String)">
|
||
<summary>
|
||
Instantiates <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer"/> using the custom word embedding model by loading it from the file specified by the <paramref name="customModelFile"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="customModelFile">Filename for custom word embedding model.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Instantiates <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer"/> using the pretrained word embedding model specified by <paramref name="modelKind"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="modelKind">The pretrained word embedding model.</param>
|
||
<param name="columns">Input/Output columns.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Instantiates <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer"/> using the custom word embedding model by loading it from the file specified by the <paramref name="customModelFile"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="customModelFile">Filename for custom word embedding model.</param>
|
||
<param name="columns">Input/Output columns.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator">
|
||
<summary>
|
||
Text featurizer which converts vectors of text tokens into a numerical vector using a pre-trained embeddings model.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< |
|
||
| Output column data type | Known-sized vector of <xref:System.Single> |
|
||
| Exportable to ONNX | No |
|
||
|
||
The <xref:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer> produces a new column,
|
||
named as specified in the output column name parameters, where each input vector is mapped to a numerical vector
|
||
with size of 3 * dimensionality of the embedding model used. Notice that this is independent of the size of the input vector.
|
||
|
||
For example, when using GloVe50D, which itself is 50 dimensional, the output column is a vector of size 150.
|
||
The first third of slots contains the minimum values across the embeddings corresponding to each string in the input vector.
|
||
The second third contains the average of the embeddings. The last third of slots contains maximum values
|
||
of the encountered embeddings. The min/max provides a bounding hyper-rectangle for the words in the word embedding space.
|
||
This can assist for longer phrases where the average of many words drowns out the useful signal.
|
||
|
||
The user can specify a custom pre-trained embeddings model or one of the available pre-trained models.
|
||
The available options are various versions of [GloVe Models](https://nlp.stanford.edu/projects/glove/),
|
||
[FastText](https://en.wikipedia.org/wiki/FastText), and [SSWE](https://anthology.aclweb.org/P/P14/P14-1146.pdf).
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.ApplyWordEmbedding(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind)"/>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.ApplyWordEmbedding(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.String)"/>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind)">
|
||
<summary>
|
||
Extracts word embeddings.
|
||
Output three times more values than dimension of the model specified in <paramref name="modelKind"/>
|
||
First set of values represent minumum encountered values (for each dimension), second set represent average (for each dimension)
|
||
and third one represent maximum encountered values (for each dimension).
|
||
</summary>
|
||
<param name="env">The local instance of <see cref="T:Microsoft.ML.Runtime.IHostEnvironment"/></param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="modelKind">The embeddings <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind"/> to use. </param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.String)">
|
||
<summary>
|
||
Extracts word embeddings.
|
||
Output three times more values than dimension of the model specified in <paramref name="customModelFile"/>
|
||
First set of values represent minimum encountered values (for each dimension), second set represent average (for each dimension)
|
||
and third one represent maximum encountered values (for each dimension).
|
||
</summary>
|
||
<param name="env">The local instance of <see cref="T:Microsoft.ML.Runtime.IHostEnvironment"/></param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="customModelFile">The path of the pre-trained embeddings model to use. </param>
|
||
<param name="inputColumnName">Name of the column to transform. </param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Extracts word embeddings.
|
||
Output three times more values than dimension of the model specified in <paramref name="modelKind"/>
|
||
First set of values represent minimum encountered values (for each dimension), second set represent average (for each dimension)
|
||
and third one represent maximum encountered values (for each dimension).
|
||
</summary>
|
||
<param name="env">The local instance of <see cref="T:Microsoft.ML.Runtime.IHostEnvironment"/></param>
|
||
<param name="modelKind">The embeddings <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind"/> to use. </param>
|
||
<param name="columns">The array columns, and per-column configurations to extract embeddings from.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind">
|
||
<summary>
|
||
Specifies which word embeddings to use.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.GloVe50D">
|
||
<summary>
|
||
GloVe 50 dimensional word embeddings.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.GloVe100D">
|
||
<summary>
|
||
GloVe 100 dimensional word embeddings.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.GloVe200D">
|
||
<summary>
|
||
GloVe 200 dimensional word embeddings.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.GloVe300D">
|
||
<summary>
|
||
GloVe 300 dimensional word embeddings.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.GloVeTwitter25D">
|
||
<summary>
|
||
GloVe 25 dimensional word embeddings trained on Twitter data.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.GloVeTwitter50D">
|
||
<summary>
|
||
GloVe 50 dimensional word embeddings trained on Twitter data.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.GloVeTwitter100D">
|
||
<summary>
|
||
GloVe 100 dimensional word embeddings trained on Twitter data.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.GloVeTwitter200D">
|
||
<summary>
|
||
GloVe 200 dimensional word embeddings trained on Twitter data.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.FastTextWikipedia300D">
|
||
<summary>
|
||
FastText 300 dimensional word embeddings trained on Wikipedia.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind.SentimentSpecificWordEmbedding">
|
||
<summary>
|
||
Word embeddings trained on sentiment analysis tasks.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.ColumnOptions">
|
||
<summary>
|
||
Information for each column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.ColumnOptions.Name">
|
||
<summary>
|
||
Name of the column resulting from the transformation of <cref see="InputColumnName"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.ColumnOptions.InputColumnName">
|
||
<summary>
|
||
Name of column to transform.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.ColumnOptions.#ctor(System.String,System.String)">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <cref see="inputColumnName"/>. </param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/> <cref see="name"/> will be used as source.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramHashExtractingTransformer">
|
||
<summary>
|
||
A transform that turns a collection of tokenized text (vector of ReadOnlyMemory) into numerical feature vectors
|
||
using the hashing trick.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.NgramHashExtractingTransformer.ArgumentsBase">
|
||
<summary>
|
||
This class is a merger of <see cref="T:Microsoft.ML.Transforms.HashingTransformer.Options"/> and
|
||
<see cref="T:Microsoft.ML.Transforms.Text.NgramHashingTransformer.Options"/>, with the ordered option,
|
||
the rehashUnigrams option and the allLength option removed.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordTokenizingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting an <see cref="T:Microsoft.ML.Transforms.Text.WordTokenizingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordTokenizingEstimator">
|
||
<summary>
|
||
Tokenizes input text using specified delimiters.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< |
|
||
| Output column data type | Variable-size vector of [Text](xref:Microsoft.ML.Data.TextDataViewType) |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.Text.WordTokenizingTransformer> creates a new column,
|
||
named as specified in the output column name parameters, where each input string is mapped to a vector of substrings obtained
|
||
by splitting the input string according to the user defined delimiters. The space character is the default delimiter.
|
||
|
||
Empty strings and strings containing only spaces are dropped.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.TokenizeIntoWords(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Char[])"/>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Char[])">
|
||
<summary>
|
||
Tokenize incoming text in <paramref name="inputColumnName"/> and output the tokens as <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The output column is of type variable vector of string.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This column should be of type string.</param>
|
||
<param name="separators">The separators to use (uses space character by default).</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[],System.Char[])">
|
||
<summary>
|
||
Tokenize incoming text in input columns and output the tokens.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to run the tokenization on.</param>
|
||
<param name="separators">The separators to use (uses space character by default).</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Tokenize incoming text in input columns and output the tokens.
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to run the tokenization on.</param>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions.Name">
|
||
<summary>
|
||
Output column name that will be used to store the tokenization result of <see cref="F:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions.InputColumnName"/> column.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions.InputColumnName">
|
||
<summary>
|
||
Input column name that will be tokenized into words.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions.Separators">
|
||
<summary>
|
||
Seperator list used to tokenize input string. If not specified, space will be used.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions.SeparatorsArray">
|
||
<summary>
|
||
State of <see cref="P:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions.Separators"/>. Since <see langword="char"/>[] is multable, it's not safe to directly expose this field to users.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions.#ctor(System.String,System.String,System.Char[])">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="separators">Casing text using the rules of the invariant culture. If not specified, space will be used as separator.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordTokenizingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordBagEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.ITransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< |
|
||
| Output column data type | Vector of known-size of <xref:System.Single> |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.ITransformer> creates a new column, named as specified in the output column name parameters, and
|
||
produces a vector of n-gram counts (sequences of n consecutive words) from a given data.
|
||
It does so by building a dictionary of n-grams and using the id in the dictionary as the index in the bag.
|
||
|
||
<xref:Microsoft.ML.Transforms.Text.WordBagEstimator> is different from <xref:Microsoft.ML.Transforms.Text.NgramExtractingEstimator>
|
||
in that the former takes tokenizes text internally while the latter takes tokenized text as input.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.ProduceWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria)" />
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.ProduceWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String[],System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria)" />
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordBagEstimator.Options">
|
||
<summary>
|
||
Options for how the n-grams are extracted.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordBagEstimator.Options.NgramLength">
|
||
<summary>
|
||
Maximum n-gram length.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordBagEstimator.Options.SkipLength">
|
||
<summary>
|
||
Maximum number of tokens to skip when constructing an n-gram.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordBagEstimator.Options.UseAllLengths">
|
||
<summary>
|
||
Whether to store all n-gram lengths up to ngramLength, or only ngramLength.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordBagEstimator.Options.MaximumNgramsCount">
|
||
<summary>
|
||
The maximum number of grams to store in the dictionary, for each level of n-grams,
|
||
from 1 (in position 0) up to ngramLength (in position ngramLength-1)
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.Text.WordBagEstimator.Options.Weighting">
|
||
<summary>
|
||
The weighting criteria.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordBagEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria,System.Char,System.Char)">
|
||
<summary>
|
||
Produces a bag of counts of n-grams (sequences of consecutive words) in <paramref name="inputColumnName"/>
|
||
and outputs bag of word vector as <paramref name="outputColumnName"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="weighting">Statistical measure used to evaluate how important a word is to a document in a corpus.</param>
|
||
<param name="termSeparator">Separator used to separate terms/frequency pairs.</param>
|
||
<param name="freqSeparator">Separator used to separate terms from their frequency.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordBagEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String[],System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria,System.Char,System.Char)">
|
||
<summary>
|
||
Produces a bag of counts of n-grams (sequences of consecutive words) in <paramref name="inputColumnNames"/>
|
||
and outputs bag of word vector as <paramref name="outputColumnName"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">The column containing output tokens.</param>
|
||
<param name="inputColumnNames">The columns containing text to compute bag of word vector.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="weighting">Statistical measure used to evaluate how important a word is to a document in a corpus.</param>
|
||
<param name="termSeparator">Separator used to separate terms/frequency pairs.</param>
|
||
<param name="freqSeparator">Separator used to separate terms from their frequency.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordBagEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String[]}[],System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria,System.Char,System.Char)">
|
||
<summary>
|
||
Produces a bag of counts of n-grams (sequences of consecutive words) in <paramref name="columns.inputs.inputs"/>
|
||
and outputs bag of word vector for each output in <paramref name="columns.output.output"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to compute bag of word vector.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="weighting">Statistical measure used to evaluate how important a word is to a document in a corpus.</param>
|
||
<param name="termSeparator">Separator used to separate terms/frequency pairs.</param>
|
||
<param name="freqSeparator">Separator used to separate terms from their frequency.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordBagEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary> Trains and returns a <see cref="T:Microsoft.ML.ITransformer"/>.</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordBagEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Schema propagation for estimators.
|
||
Returns the output schema shape of the estimator, if the input schema shape is like the one provided.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.ITransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< |
|
||
| Output column data type | Vector of known-size of <xref:System.Single> |
|
||
| Exportable to ONNX | No |
|
||
|
||
The resulting <xref:Microsoft.ML.ITransformer> creates a new column, named as specified in the output column name parameters, and
|
||
produces a vector of n-gram counts (sequences of n consecutive words) from a given data.
|
||
It does so by hashing each n-gram and using the hash value as the index in the bag.
|
||
|
||
<xref:Microsoft.ML.Transforms.Text.WordHashBagEstimator> is different from <xref:Microsoft.ML.Transforms.Text.NgramHashingEstimator>
|
||
in that the former takes tokenizes text internally while the latter takes tokenized text as input.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.ProduceHashedWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)" />
|
||
<seealso cref="M:Microsoft.ML.TextCatalog.ProduceHashedWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String[],System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)" />
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordHashBagEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Produces a bag of counts of hashed n-grams in <paramref name="inputColumnName"/>
|
||
and outputs bag of word vector as <paramref name="outputColumnName"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">The column containing bag of word vector. Null means <paramref name="inputColumnName"/> is replaced.</param>
|
||
<param name="inputColumnName">The column containing text to compute bag of word vector.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we construct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the annotations for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordHashBagEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String[],System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Produces a bag of counts of hashed n-grams in <paramref name="inputColumnNames"/>
|
||
and outputs bag of word vector as <paramref name="outputColumnName"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">The column containing output tokens.</param>
|
||
<param name="inputColumnNames">The columns containing text to compute bag of word vector.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordHashBagEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String[]}[],System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Produces a bag of counts of hashed n-grams in <paramref name="columns.inputs.inputs"/>
|
||
and outputs bag of word vector for each output in <paramref name="columns.output.output"/>
|
||
</summary>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to compute bag of word vector.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we constuct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordHashBagEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary> Trains and returns a <see cref="T:Microsoft.ML.ITransformer"/>.</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Text.WordHashBagEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Schema propagation for estimators.
|
||
Returns the output schema shape of the estimator, if the input schema shape is like the one provided.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.ExpressionEstimator">
|
||
<summary>
|
||
This estimator applies a user provided expression (specified as a string) to input column values to produce new output column values.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< creates a new column,
|
||
named as specified in the output column name parameters, where the expression is applied to the input values.
|
||
At most one of the input columns can be of type [VectorDataViewType](xref:Microsoft.ML.Data.VectorDataViewType), and when the input contains a vector column, the expression
|
||
is computed independently on each element of the vector, to create a vector output with the same length as that input.
|
||
|
||
[!include[algorithm](~/../docs/samples/docs/api-reference/expression-estimator.md)]
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.ExpressionCatalog.Expression(Microsoft.ML.TransformsCatalog,System.String,System.String,System.String[])"/>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.ExpressionEstimator.ColumnOptions.Name">
|
||
<summary>Name of the column resulting from the transformation of <see cref="F:Microsoft.ML.Transforms.ExpressionEstimator.ColumnOptions.InputColumnNames"/>.</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.FunctionProviderUtils.IsNA(System.Object)">
|
||
<summary>
|
||
Returns whether the given object is non-null and an NA value for one of the standard types.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.FunctionProviderUtils.GetNA(System.Type)">
|
||
<summary>
|
||
Returns the standard NA value for the given standard type.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.FunctionProviderUtils.Ret(System.Reflection.MethodInfo[])">
|
||
<summary>
|
||
Helper method to bundle one or more MethodInfos into an array.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.FunctionProviderUtils.Fn``1(System.Func{``0})">
|
||
<summary>
|
||
Returns the MethodInfo for the given delegate.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.FunctionProviderUtils.Fn``2(System.Func{``0,``1})">
|
||
<summary>
|
||
Returns the MethodInfo for the given delegate.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.FunctionProviderUtils.Fn``3(System.Func{``0,``1,``2})">
|
||
<summary>
|
||
Returns the MethodInfo for the given delegate.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.FunctionProviderUtils.Fn``4(System.Func{``0,``1,``2,``3})">
|
||
<summary>
|
||
Returns the MethodInfo for the given delegate.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.BuiltinFunctions">
|
||
<summary>
|
||
The standard builtin functions for ExprTransform.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.BuiltinFunctions.Id``1">
|
||
<summary>
|
||
Returns the MethodInfo for <see cref="M:Microsoft.ML.Transforms.BuiltinFunctions.Id``1(``0)"/>
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.BuiltinFunctions.NormalizeIndex(System.Int32,System.Int32)">
|
||
<summary>
|
||
Given an index meant to index into a given sequence normalize it according to
|
||
these rules: negative indices get <paramref name="len"/> added to them, and
|
||
then the index is clamped the range 0 to <paramref name="len"/> inclusive,
|
||
and that result is returned. (For those familiar with Python, this is the same
|
||
as the logic for slice normalization.)
|
||
</summary>
|
||
<param name="i">The index to normalize</param>
|
||
<param name="len">The length of the sequence</param>
|
||
<returns>The normalized version of the index, a non-positive value no greater
|
||
than <paramref name="len"/>.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.BuiltinFunctions.Pow(System.Int32,System.Int32)">
|
||
<summary>
|
||
Raise a to the b power. Special cases:
|
||
* a^(negative value) => 0
|
||
* In case of overflow, return I4.MinValue or I4.MaxValue, based on whether the result would have been
|
||
negative or positive.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.BuiltinFunctions.Pow(System.Int64,System.Int64)">
|
||
<summary>
|
||
Raise a to the b power. Special cases:
|
||
* a^(negative value) => 0
|
||
* In case of overflow, return I8.MinValue or I8.MaxValue, based on whether the result would have been
|
||
negative or positive.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LambdaCompiler.Visitor.CachedWithLocal.Value">
|
||
<summary>
|
||
The IL local containing the computed value.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LambdaCompiler.Visitor.CachedWithLocal.Flag">
|
||
<summary>
|
||
The boolean local indicating whether the value has been computed yet.
|
||
If the value is pre-computed, this is null.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaCompiler.Visitor.GenRaw(Microsoft.ML.Transforms.ExprNode)">
|
||
<summary>
|
||
Get the raw bits from an expression node. If the node is constant, this avoids the
|
||
silly "convert to dv type" followed by "extract raw bits". Returns whether the expression
|
||
is a constant NA, with null meaning "don't know".
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaCompiler.Visitor.GenBrNa(Microsoft.ML.Transforms.ExprNode,System.Reflection.Emit.Label,System.Boolean)">
|
||
<summary>
|
||
Generate code to branch to labNa if the top stack element is NA.
|
||
Note that this leaves the element on the stack (duplicates before comparing).
|
||
If rev is true, this branches when NOT NA.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaCompiler.Visitor.GenBrNaCore(Microsoft.ML.Transforms.ExprNode,Microsoft.ML.Transforms.ExprTypeKind,System.Reflection.Emit.Label,System.Boolean)">
|
||
<summary>
|
||
Generate code to branch to labNa if the top stack element is NA.
|
||
If dup is true, this leaves the element on the stack (duplicates before comparing).
|
||
If rev is true, this branches when NOT NA.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaCompiler.Visitor.GenCmpBool(Microsoft.ML.Transforms.CompareOp,System.Boolean)">
|
||
<summary>
|
||
Generate a bool from comparing the raw bits. The values are guaranteed to not be NA.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaCompiler.Visitor.GenCmpInt(Microsoft.ML.Transforms.CompareOp,System.Boolean)">
|
||
<summary>
|
||
Generate a bool from comparing the raw bits. The values are guaranteed to not be NA.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaCompiler.Visitor.GenCmpFloat(Microsoft.ML.Transforms.CompareOp,System.Boolean)">
|
||
<summary>
|
||
Generate a bool from comparing the raw bits. The values are guaranteed to not be NA.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Exec">
|
||
<summary>
|
||
This class contains static helper methods needed for execution.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Exec.#ctor">
|
||
<summary>
|
||
Currently this class is not intended to be instantiated. However the methods generated
|
||
by ExprTransform need to be associated with some public type. This one serves that
|
||
purpose as well as containing static helpers.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.IFunctionProvider">
|
||
<summary>
|
||
This interface enables extending the ExprTransform language with additional functions.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.IFunctionProvider.NameSpace">
|
||
<summary>
|
||
The namespace for this provider. This should be a legal identifier in the expression language.
|
||
Multiple providers may contribute to the same namespace.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.IFunctionProvider.Lookup(System.String)">
|
||
<summary>
|
||
Returns an array of overloads for the given function name. This may return null instead of an
|
||
empty array. The returned MethodInfos should be public static methods that can be freely invoked
|
||
by IL in a different assembly. They should also be "pure" functions - with the output only
|
||
depending on the inputs and NOT on any global state.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.IFunctionProvider.ResolveToConstant(System.String,System.Reflection.MethodInfo,System.Object[])">
|
||
<summary>
|
||
If the function's value can be determined by the given subset of its arguments, this should
|
||
return the resulting value. Note that this should only be called if values is non-empty and
|
||
contains at least one null. If all the arguments are non-null, then the MethodInfo will be
|
||
invoked to produce the value.
|
||
</summary>
|
||
<param name="name">The name of the function.</param>
|
||
<param name="meth">The MethodInfo provided by Lookup. When there are multiple overloads of
|
||
a function with a given name, this can be used to determine which overload is being used.</param>
|
||
<param name="values">The values of the input arguments, with null for the non-constant arguments. This should
|
||
only be called if there is at least one null.</param>
|
||
<returns>The constant value, when it can be determined; null otherwise.</returns>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.ILGeneratorExtensions">
|
||
<summary>
|
||
Helper extension methods for using ILGenerator.
|
||
Rather than typing out something like:
|
||
il.Emit(OpCodes.Ldarg_0);
|
||
il.Emit(OpCodes.Ldarg_1);
|
||
il.Emit(OpCodes.Ldc_I4, i);
|
||
il.Emit(OpCodes.Ldelem_Ref);
|
||
il.Emit(OpCodes.Stfld, literalFields[i]);
|
||
You can do:
|
||
il
|
||
.Ldarg(0)
|
||
.Ldarg(1)
|
||
.Ldc_I4(i)
|
||
.Ldelem_Ref()
|
||
.Stfld(literalFields[i]);
|
||
It also provides some type safety over the Emit methods by ensuring
|
||
that you don't pass any args when using Add or that you only
|
||
pass a Label when using Br.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.KeyWordTable">
|
||
<summary>
|
||
Maps from normalized string to keyword token kind. A lexer must be provided with one of these.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaBinder.Run(Microsoft.ML.Runtime.IHostEnvironment,System.Collections.Generic.List{Microsoft.ML.Transforms.Error}@,Microsoft.ML.Transforms.LambdaNode,System.Action{System.String})">
|
||
<summary>
|
||
Run Lambda binder on LambdaNode and populate Expr values.
|
||
The errors contain list of user errors that occurred during binding.
|
||
The printError delegate is only used for reporting issues with function provider implementations, which are programmer errors.
|
||
In particular, it is NOT used to report user errors in the lambda expression.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaBinder.ReconcileNumericTypes(Microsoft.ML.Transforms.ExprNode,Microsoft.ML.Transforms.ExprNode,Microsoft.ML.Transforms.ExprTypeKind@)">
|
||
<summary>
|
||
Reconcile the types of the two ExprNodes. Favor numeric types in cases
|
||
where the types can't be reconciled. This does not guarantee that
|
||
the resulting kind is numeric, eg, if both a and b are of type Text, it
|
||
simply sets kind to Text.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaBinder.Candidate.IsApplicable(Microsoft.ML.Transforms.ExprTypeKind[],System.Int32@)">
|
||
<summary>
|
||
Returns whether this candidate is applicable to the given argument types.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaBinder.Candidate.CompareSignatures(Microsoft.ML.Transforms.LambdaBinder.Candidate)">
|
||
<summary>
|
||
Returns -1 if 'this' is better than 'other', 0 if they are the same, +1 otherwise.
|
||
Non-variable is always better than variable. When both are variable, longer prefix is
|
||
better than shorter prefix.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaBinder.CanConvert(Microsoft.ML.Transforms.ExprTypeKind,Microsoft.ML.Transforms.ExprTypeKind)">
|
||
<summary>
|
||
Returns whether the given source type can be converted to the given destination type,
|
||
for the purposes of function invocation. Returns true if src is null and dst is any
|
||
valid type.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaBinder.Convert(Microsoft.ML.Transforms.ExprNode,Microsoft.ML.Transforms.ExprTypeKind)">
|
||
<summary>
|
||
Convert the given ExprNode to the given type and get its value, when constant.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaBinder.GetBestOverload(Microsoft.ML.Transforms.CallNode,System.Collections.Generic.List{Microsoft.ML.Transforms.LambdaBinder.Candidate})">
|
||
<summary>
|
||
Multiple applicable candidates; pick the best one. We use a simplification of
|
||
C#'s rules, only considering the types TX, BL, I4, I8, R4, R8. Basically, parameter
|
||
type X is better than parameter type Y if X can be converted to Y. The conversions are:
|
||
I4 => I8, I4 => R4, I4 => R8, I8 => R8, R4 => R8.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaBinder.MapKindToIndex(Microsoft.ML.Transforms.ExprTypeKind)">
|
||
<summary>
|
||
Maps numeric type kinds to an index 0,1,2,3. All others map to -1.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LexStartKind">
|
||
<summary>
|
||
Indicates which lex routine should be called when this character is the first
|
||
character of a token. Each character is associated with exactly one of these values.
|
||
Some associations may at first be surprising. For example, dot (.) uses NumLit and
|
||
slash (/) uses Comment.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LexCharUtils">
|
||
<summary>
|
||
Encapsulates information needed to map characters to tokens.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LexCharUtils.UniCatFlags">
|
||
<summary>
|
||
Bit masks of the UnicodeCategory enum. A couple extra values are defined
|
||
for convenience for the C# lexical grammar.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LexCharUtils.LexCharKind">
|
||
<summary>
|
||
Indicates the different roles a character may have (as non-leading character). This is used for
|
||
subsequent (not first) characters in a token. For example, digits all have the Ident flag set.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LexCharUtils.LexCharInfo">
|
||
<summary>
|
||
Information for each character. We have a table of these for all characters less than 0x80.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LexCharUtils.StartKind(System.Char)">
|
||
<summary>
|
||
Returns the lexical character type of the given character.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LexCharUtils.GetUniEscape(System.UInt32)">
|
||
<summary>
|
||
Convert the given uint to a unicode escape.
|
||
Note that the uint contains raw hex - not a surrogate pair.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Lexer">
|
||
<summary>
|
||
The lexer. This is effectively a template. Call LexSource to get an Enumerable of tokens.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.#ctor(Microsoft.ML.Internal.Utilities.NormStr.Pool,Microsoft.ML.Transforms.KeyWordTable)">
|
||
<summary>
|
||
The constructor. Caller must provide the name pool and key word table.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Lexer.LexerImpl.Eof">
|
||
<summary>
|
||
Whether we've hit the end of input yet. If this returns true, ChCur will be zero.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Lexer.LexerImpl.ChCur">
|
||
<summary>
|
||
The current character. Zero if we've hit the end of input.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.ChNext">
|
||
<summary>
|
||
Advance to the next character and return it.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.StartTok">
|
||
<summary>
|
||
Marks the beginning of the current token.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.ReportError(Microsoft.ML.Transforms.ErrId)">
|
||
<summary>
|
||
Called to embed an error token in the stream.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.GetNextToken">
|
||
<summary>
|
||
Form and return the next token. Returns null to signal end of input.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.GetEof">
|
||
<summary>
|
||
Call once GetNextToken returns null if you need an Eof token.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexPunc">
|
||
<summary>
|
||
Called to lex a punctuator (operator). Asserts the current character lex type
|
||
is LexCharType.Punc.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexNumLit">
|
||
<summary>
|
||
Called to lex a numeric literal or a Dot token. Asserts the current
|
||
character lex type is LexCharType.NumLit.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexHexInt">
|
||
<summary>
|
||
Lex a hex literal optionally followed by an integer suffix. Asserts the current
|
||
character is a hex digit.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexDecInt(Microsoft.ML.Transforms.IntLitKind)">
|
||
<summary>
|
||
Lex a decimal integer literal. The digits must be in _sb.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexRealNum(System.Char)">
|
||
<summary>
|
||
Lex a real literal (float, double or decimal). The characters should be in _sb.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexIntSuffix">
|
||
<summary>
|
||
Lex an optional integer suffix (U and/or L).
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexRealSuffix(System.Boolean)">
|
||
<summary>
|
||
Lex an optional real suffix (F, D, M).
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexStrLit">
|
||
<summary>
|
||
Lex a string or character literal.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.FLexEscChar(System.Boolean,System.UInt32@)">
|
||
<summary>
|
||
Lex a character escape. Returns true if successful (ch is valid).
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.ConvertToSurrogatePair(System.UInt32,System.Char@,System.Char@)">
|
||
<summary>
|
||
Convert the pair of characters to a surrogate pair.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexIdent">
|
||
<summary>
|
||
Lex an identifier.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexComment">
|
||
<summary>
|
||
Lex a comment.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexSpace">
|
||
<summary>
|
||
Lex a sequence of spacing characters.
|
||
Always returns null.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexLineTerm(System.Text.StringBuilder)">
|
||
<summary>
|
||
Lex a line termination character. Transforms CRLF into a single LF.
|
||
Updates the line mapping. When this "drops" a character and sb is not
|
||
null, it adds the character to sb. It does NOT add the returned character
|
||
to the sb.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.Lexer.LexerImpl.LexError">
|
||
<summary>
|
||
Skip over an error character. Always returns null.
|
||
REVIEW: Should we skip over multiple?
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MethodGenerator">
|
||
<summary>
|
||
MethodGenerator is used to build a method by specifying the IL.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MethodGenerator.CreateDelegate(System.Type)">
|
||
<summary>
|
||
Create and return a delegate of the given "delegateType" and currying the
|
||
given "thisObj". Note that "thisObj" may be null and "delegateType" should
|
||
match the types indicated when the MethodGenerator was created.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MethodGenerator.Dispose">
|
||
<summary>
|
||
This is idempotent (calling multiple times has the same affect as calling once).
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MethodGenerator.Temporary">
|
||
<summary>
|
||
Represents a temporary local. A MethodGenerator maintains a cache of temporary locals.
|
||
Clients can 'check-out' temporaries from the cache, use them, then release (Dispose) when
|
||
they are no longer needed so other clients can reuse the temporary to cut down on the number
|
||
of locals created. Note that Temporary is a struct, but should NOT be copied around. It is
|
||
critical that a stray copy of a Temporary is not disposed!
|
||
|
||
We have two 'types' of temporaries: 'Regular' and 'Ref'. 'Ref' temporaries are special in that
|
||
they should be used when you need to use ldloca. Grouping this way should help the JIT optimize
|
||
local usage.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MethodGenerator.ReleaseLocal(System.Reflection.Emit.LocalBuilder,System.Boolean)">
|
||
<summary>
|
||
Called by the Temporary struct's Dispose method, through the _tempDisposer delegate.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.ConditionalNode">
|
||
<summary>
|
||
Node for the ternary conditional operator.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.WithNode">
|
||
<summary>
|
||
The parse node for a "with" expression. The grammar is:
|
||
|
||
WithNode :
|
||
with ( WithLocalNode [ , WithLocalNode ]* ; Expr )
|
||
|
||
Note that a with expression with multiple WithLocalNodes gets expanded to multiple
|
||
nested WithNodes. This makes the code much simpler and easily allows a with-local to
|
||
reference all previous with-locals.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.WithLocalNode">
|
||
<summary>
|
||
The with-expression local assignment node. This contains both the name of the local and the
|
||
value expression.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.TokenCursor.TokPeek(System.Int32)">
|
||
<summary>
|
||
This expects that ItokCur + ditok is either within the buffered token range or just
|
||
at the end of it. In other words, it does not support skipping tokens.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.SignatureKernelBase">
|
||
<summary>
|
||
Signature for a <see cref="T:Microsoft.ML.Transforms.KernelBase"/> constructor.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.KernelBase">
|
||
<summary>
|
||
This class indicates which kernel should be approximated by the <see cref="T:Microsoft.ML.Transforms.ApproximatedKernelTransformer"/>.
|
||
<seealso cref="T:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.KernelBase.Distance(Microsoft.ML.Data.VBuffer{System.Single}@,Microsoft.ML.Data.VBuffer{System.Single}@)">
|
||
<summary>
|
||
The kernels deriving from this class are shift-invariant, and each of them depends on a different distance between
|
||
its inputs. The <see cref="T:Microsoft.ML.Transforms.GaussianKernel"/> depends on the L2 distance, and the <see cref="T:Microsoft.ML.Transforms.LaplacianKernel"/> depends
|
||
on the L1 distance.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.KernelBase.GetRandomNumberGenerator(System.Single)">
|
||
<summary>
|
||
This method returns an object that can sample from the non-negative measure that is the Fourier transform of this kernel.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.FourierRandomNumberGeneratorBase">
|
||
<summary>
|
||
The Fourier transform of a continuous positive definite kernel is a non-negative measure
|
||
(<a href="https://en.wikipedia.org/wiki/Bochner%27s_theorem">Bochner's theorem</a>). This class
|
||
samples numbers from the non-negative measure corresponding to the given kernel.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.GaussianKernel">
|
||
<summary>
|
||
The Gaussian kernel.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
- The Gaussian kernel is defined as $k(x,y) = \exp(-\gamma||x-y||^2)$.
|
||
]]></format>
|
||
</remarks>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GaussianKernel.#ctor(System.Single)">
|
||
<summary>
|
||
Create a new instance of a GaussianKernel.
|
||
</summary>
|
||
<param name="gamma">The coefficient in the exponent of the kernel function. It should be positive.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LaplacianKernel">
|
||
<summary>
|
||
The Laplacian kernel.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
- The Laplacian kernel is defined as $k(x,y)=\exp(-a||x-y||)$.
|
||
]]></format>
|
||
</remarks>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LaplacianKernel.#ctor(System.Single)">
|
||
<summary>
|
||
Create a new instance of a LaplacianKernel.
|
||
</summary>
|
||
<param name="a">The coefficient in the exponent of the kernel function.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LpNormNormalizingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator"/> or <see cref="T:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.LpNormNormalizingTransformer.Columns">
|
||
<summary>
|
||
The objects describing how the transformation is applied on the input data.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.LpNormNormalizingTransformer"/> that takes multiple pairs of columns.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingTransformer.Mapper.StdDev(System.ReadOnlySpan{System.Single},System.Int32)">
|
||
<summary>
|
||
Compute Standard Deviation. In case of both subMean and useStd are true, we technically need to compute variance
|
||
based on centered values (i.e. after subtracting the mean). But since the centered
|
||
values mean is approximately zero, we can use variance of non-centered values.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingTransformer.Mapper.StdDev(System.ReadOnlySpan{System.Single},System.Int32,System.Single)">
|
||
<summary>
|
||
Compute Standard Deviation.
|
||
We have two overloads of StdDev instead of one with <see cref="T:System.Nullable`1"/> mean for perf reasons.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingTransformer.Mapper.L2Norm(System.ReadOnlySpan{System.Single},System.Single)">
|
||
<summary>
|
||
Compute L2-norm. L2-norm computation doesn't subtract the mean from the source values.
|
||
However, we substract the mean here in case subMean is true (if subMean is false, mean is zero).
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingTransformer.Mapper.L1Norm(System.ReadOnlySpan{System.Single},System.Single)">
|
||
<summary>
|
||
Compute L1-norm. L1-norm computation doesn't subtract the mean from the source values.
|
||
However, we substract the mean here in case subMean is true (if subMean is false, mean is zero).
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingTransformer.Mapper.LInfNorm(System.ReadOnlySpan{System.Single},System.Single)">
|
||
<summary>
|
||
Compute LInf-norm. LInf-norm computation doesn't subtract the mean from the source values.
|
||
However, we substract the mean here in case subMean is true (if subMean is false, mean is zero).
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase">
|
||
<summary>
|
||
Base estimator class for <see cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator"/> and <see cref="T:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator"/> normalizers.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction">
|
||
<summary>
|
||
The kind of unit norm vectors are rescaled to. This enumeration is serialized.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction.L2">
|
||
<summary>
|
||
L2-norm.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation">
|
||
<summary>
|
||
Standard deviation of a vector by viewing all its coordinates as a random variable.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction.L1">
|
||
<summary>
|
||
L1-norm.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction.Infinity">
|
||
<summary>
|
||
Infinity-norm.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase">
|
||
<summary>
|
||
Describes base class for one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase.Name">
|
||
<summary>
|
||
Name of the column resulting from the transformation of <see cref="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase.InputColumnName"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase.InputColumnName">
|
||
<summary>
|
||
Name of column to transform.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase.Norm">
|
||
<summary>
|
||
The norm to use to normalize each sample.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase.EnsureZeroMean">
|
||
<summary>
|
||
Subtract mean from each value before normalizing.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase.Scale">
|
||
<summary>
|
||
Scale features by this value.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.ColumnOptionsBase[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase"/> that takes multiple pairs of columns.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator">
|
||
<summary>
|
||
Normalizes (scales) vectors in the input column to the unit norm. The type of norm that is used can be specified by the user.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
|
||
### Estimator Characteristics
|
||
| | |
|
||
| -- | -- |
|
||
| Does this estimator need to look at the data to train its parameters? | No |
|
||
| Input column data type | Vector of <xref:System.Single> |
|
||
| Output column data type | Vector of <xref:System.Single> |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.LpNormNormalizingTransformer> normalizes vectors in the input column individually
|
||
by rescaling them to the unit norm.
|
||
|
||
Let $x$ be the input vector, $n$ the size of the vector, $L(x)$ the norm function selected by the user.
|
||
Let $\mu(x) = \sum_i x_i / n$ be the mean of the values of vector $x$. The <xref:Microsoft.ML.Transforms.LpNormNormalizingTransformer>
|
||
performs the following operation on each input vector $x$:
|
||
$y = \frac{x - \mu(x)}{L(x)}$
|
||
if the user specifies that the mean should be zero, or otherwise:
|
||
$y = \frac{x}{L(x)}$
|
||
|
||
There are four types of norm that can be selected by the user to be applied on input vector $x$. They are defined as follows:
|
||
- <xref:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction.L1>: $L_1(x) = \sum_i |x_i|$
|
||
- <xref:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction.L2>: $L_2(x) = \sqrt{\sum_i x_i^2}$
|
||
- <xref:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction.Infinity>: $L_{\infty}(x) = \max_i\{|x_i|\}$
|
||
- <xref:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction.StandardDeviation>: $L_\sigma(x)$ is defined as the
|
||
standard deviation of the elements of the input vector $x$
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.NormalizationCatalog.NormalizeLpNorm(Microsoft.ML.TransformsCatalog,System.String,System.String,Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction,System.Boolean)"/>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingEstimator.ColumnOptions.#ctor(System.String,System.String,Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction,System.Boolean)">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="norm">Type of norm to use to normalize each sample. The indicated norm of the resulted vector will be normalized to one.</param>
|
||
<param name="ensureZeroMean">If <see langword="true"/>, subtract mean from each value before normalizing and use the raw input otherwise.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction,System.Boolean)">
|
||
<!-- No matching elements were found for the following include tag --><include file="doc.xml" path="doc/members/member[@name="LpNormalize"]/*" />
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName" />.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null" />, the value of the <paramref name="outputColumnName" /> will be used as source.</param>
|
||
<param name="norm">Type of norm to use to normalize each sample. The indicated norm of the resulted vector will be normalized to one.</param>
|
||
<param name="ensureZeroMean">If <see langword="true" />, subtract mean from each value before normalizing and use the raw input otherwise.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[],Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction,System.Boolean)">
|
||
<!-- No matching elements were found for the following include tag --><include file="doc.xml" path="doc/members/member[@name="LpNormalize"]/*" />
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to run the normalization on.</param>
|
||
<param name="norm">Type of norm to use to normalize each sample. The indicated norm of the resulted vector will be normalized to one.</param>
|
||
<param name="ensureZeroMean">If <see langword="true" />, subtract mean from each value before normalizing and use the raw input otherwise.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LpNormNormalizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.LpNormNormalizingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator"/> that takes multiple pairs of columns.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator">
|
||
<summary>
|
||
Normalizes (scales) vectors in the input column applying the global contrast normalization.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
|
||
### Estimator Characteristics
|
||
| | |
|
||
| -- | -- |
|
||
| Does this estimator need to look at the data to train its parameters? | No |
|
||
| Input column data type | Vector of <xref:System.Single> |
|
||
| Output column data type | Vector of <xref:System.Single> |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.LpNormNormalizingTransformer> normalizes vectors in the input column individually,
|
||
rescaling them by applying global contrast normalization. The transform performs the following operation on each input vector $x$:
|
||
$y = \frac{s * x - \mu(x)}{L(x)}$.
|
||
Where $s$ is a user provided scaling factor, $\mu(x)$ is the mean of the elements of vector $x$, and $L(x)$ is the $L_2$ norm or the
|
||
standard deviation of the elements of vector $x$. These settings can be specified by the user when the
|
||
<xref:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator> is initialized.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.NormalizationCatalog.NormalizeGlobalContrast(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Boolean,System.Boolean,System.Single)"/>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one Gcn column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator.ColumnOptions.#ctor(System.String,System.String,System.Boolean,System.Boolean,System.Single)">
|
||
<summary>
|
||
Describes how the transformer handles one Gcn column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="ensureZeroMean">If <see langword="true"/>, subtract mean from each value before normalizing and use the raw input otherwise.</param>
|
||
<param name="ensureUnitStandardDeviation">If <see langword="true"/>, resulted vector's standard deviation would be one. Otherwise, resulted vector's L2-norm would be one.</param>
|
||
<param name="scale">Scale features by this value.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Boolean,System.Boolean,System.Single)">
|
||
<summary>
|
||
<para>Performs a global contrast normalization on input values:</para>
|
||
<para>Y = (s * X - M) / D</para>
|
||
<para>where s is a scale, M is mean and D is either the L2 norm or standard deviation.</para>
|
||
</summary><remarks>
|
||
Scaling inputs to unit norms is a common operation for text classification or clustering.
|
||
For more information see:
|
||
<a href="https://www.cs.stanford.edu/~acoates/papers/coatesleeng_aistats_2011.pdf">An Analysis of Single-Layer Networks in Unsupervised Feature Learning</a>
|
||
</remarks><seealso cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator" /><example>
|
||
<code language="csharp">
|
||
pipeline.Add(new GlobalContrastNormalizer("FeatureCol")
|
||
{
|
||
SubMean= false
|
||
});
|
||
</code>
|
||
</example>
|
||
<param name="env">The environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName" />.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null" />, the value of the <paramref name="outputColumnName" /> will be used as source.</param>
|
||
<param name="ensureZeroMean">If <see langword="true" />, subtract mean from each value before normalizing and use the raw input otherwise.</param>
|
||
<param name="ensureUnitStandardDeviation">If <see langword="true" />, resulted vector's standard deviation would be one. Otherwise, resulted vector's L2-norm would be one.</param>
|
||
<param name="scale">Scale features by this value.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[],System.Boolean,System.Boolean,System.Single)">
|
||
<summary>
|
||
<para>Performs a global contrast normalization on input values:</para>
|
||
<para>Y = (s * X - M) / D</para>
|
||
<para>where s is a scale, M is mean and D is either the L2 norm or standard deviation.</para>
|
||
</summary><remarks>
|
||
Scaling inputs to unit norms is a common operation for text classification or clustering.
|
||
For more information see:
|
||
<a href="https://www.cs.stanford.edu/~acoates/papers/coatesleeng_aistats_2011.pdf">An Analysis of Single-Layer Networks in Unsupervised Feature Learning</a>
|
||
</remarks><seealso cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator" /><example>
|
||
<code language="csharp">
|
||
pipeline.Add(new GlobalContrastNormalizer("FeatureCol")
|
||
{
|
||
SubMean= false
|
||
});
|
||
</code>
|
||
</example>
|
||
<param name="env">The environment.</param>
|
||
<param name="columns">Pairs of columns to run the normalization on.</param>
|
||
<param name="ensureZeroMean">If <see langword="true" />, subtract mean from each value before normalizing and use the raw input otherwise.</param>
|
||
<param name="ensureUnitStandardDeviation">If <see langword="true" />, resulted vector's standard deviation would be one. Otherwise, resulted vector's L2-norm would be one.</param>
|
||
<param name="scale">Scale features by this value.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator"/> that takes multiple pairs of columns.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.GroupTransform">
|
||
<summary>
|
||
A Trasforms that groups values of a scalar column into a vector, by a contiguous group ID.
|
||
</summary>
|
||
<remarks>
|
||
<p>This transform essentially performs the following SQL-like operation:</p>
|
||
<p>SELECT GroupKey1, GroupKey2, ... GroupKeyK, LIST(Value1), LIST(Value2), ... LIST(ValueN)
|
||
FROM Data
|
||
GROUP BY GroupKey1, GroupKey2, ... GroupKeyK.</p>
|
||
|
||
<p>It assumes that the group keys are contiguous (if a new group key sequence is encountered, the group is over).
|
||
The GroupKeyN and ValueN columns can be of any primitive types. The code requires that every raw type T of the group key column
|
||
is an <see cref="T:System.IEquatable`1"/>, which is currently true for all existing primitive types.
|
||
The produced ValueN columns will be variable-length vectors of the original value column types.</p>
|
||
|
||
<p>The order of ValueN entries in the lists is preserved.</p>
|
||
|
||
<example><code>
|
||
Example:
|
||
User Item
|
||
Pete Book
|
||
Tom Table
|
||
Tom Kitten
|
||
Pete Chair
|
||
Pete Cup
|
||
|
||
Result:
|
||
User Item
|
||
Pete [Book]
|
||
Tom [Table, Kitten]
|
||
Pete [Chair, Cup]
|
||
</code></example>
|
||
</remarks>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GroupTransform.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.String,System.String[])">
|
||
<summary>
|
||
Initializes a new instance of <see cref="T:Microsoft.ML.Transforms.GroupTransform"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="input">Input <see cref="T:Microsoft.ML.IDataView"/>. This is the output from previous transform or loader.</param>
|
||
<param name="groupKey">Columns to group by</param>
|
||
<param name="columns">Columns to group together</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.GroupTransform.GroupBinding">
|
||
<summary>
|
||
This class describes the relation between <see cref="T:Microsoft.ML.Transforms.GroupTransform"/>'s input <see cref="T:Microsoft.ML.DataViewSchema"/>,
|
||
<see cref="F:Microsoft.ML.Transforms.GroupTransform.GroupBinding._inputSchema"/>, and output <see cref="T:Microsoft.ML.DataViewSchema"/>, <see cref="P:Microsoft.ML.Transforms.GroupTransform.GroupBinding.OutputSchema"/>.
|
||
|
||
The <see cref="P:Microsoft.ML.Transforms.GroupTransform.GroupBinding.OutputSchema"/> contains columns used to group columns and columns being aggregated from input data.
|
||
In <see cref="P:Microsoft.ML.Transforms.GroupTransform.GroupBinding.OutputSchema"/>, group columns are followed by aggregated columns. For example, if column "Age" is used to group "UserId" column,
|
||
the first column and the second column in <see cref="P:Microsoft.ML.Transforms.GroupTransform.GroupBinding.OutputSchema"/> produced by <see cref="T:Microsoft.ML.Transforms.GroupTransform"/> would be "Age" and "UserId," respectively.
|
||
Note that "Age" is a group column while "UserId" is an aggregated (also call keep) column.
|
||
|
||
For group columns, the schema information is intact. For aggregated columns, the type is Vector of original type and variable length.
|
||
The only metadata preserved is the KeyNames and IsNormalized. All other columns are dropped. Please see
|
||
<see cref="M:Microsoft.ML.Transforms.GroupTransform.GroupBinding.BuildOutputSchema(Microsoft.ML.DataViewSchema)"/> how this idea got implemented.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.GroupTransform.GroupBinding.GroupColumnIndexes">
|
||
<summary>
|
||
<see cref="F:Microsoft.ML.Transforms.GroupTransform.GroupBinding.GroupColumnIndexes"/>[i] is the i-th group(-key) column's column index in the source schema.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.GroupTransform.GroupBinding.KeepColumnIndexes">
|
||
<summary>
|
||
<see cref="F:Microsoft.ML.Transforms.GroupTransform.GroupBinding.KeepColumnIndexes"/>[i] is the i-th aggregated column's column index in the source schema.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.GroupTransform.GroupBinding.OutputSchema">
|
||
<summary>
|
||
Output <see cref="T:Microsoft.ML.DataViewSchema"/> of <see cref="T:Microsoft.ML.Transforms.GroupTransform"/> when input schema is <see cref="F:Microsoft.ML.Transforms.GroupTransform.GroupBinding._inputSchema"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GroupTransform.GroupBinding.BuildOutputSchema(Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Compute the output schema of a <see cref="T:Microsoft.ML.Transforms.GroupTransform"/> given a input schema.
|
||
</summary>
|
||
<param name="sourceSchema">Input schema.</param>
|
||
<returns>The associated output schema produced by <see cref="T:Microsoft.ML.Transforms.GroupTransform"/>.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GroupTransform.GroupBinding.GetColumnIds(Microsoft.ML.DataViewSchema,System.String[],System.Func{System.String,System.Exception})">
|
||
<summary>
|
||
Given column names, extract and return column indexes from source schema.
|
||
</summary>
|
||
<param name="schema">Source schema</param>
|
||
<param name="names">Column names</param>
|
||
<param name="except">Marked exception function</param>
|
||
<returns>column indexes</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GroupTransform.GroupBinding.CheckColumnInRange(System.Int32)">
|
||
<summary>
|
||
Determine if output column index is valid to <see cref="P:Microsoft.ML.Transforms.GroupTransform.GroupBinding.OutputSchema"/>. A valid output column index should be greater than or
|
||
equal 0 and smaller than # of output columns.
|
||
</summary>
|
||
<param name="col">Column index of <see cref="P:Microsoft.ML.Transforms.GroupTransform.GroupBinding.OutputSchema"/></param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.GroupTransform.Cursor">
|
||
<summary>
|
||
This cursor will create two cursors on the input data view:
|
||
- The leading cursor will activate all the group columns, and will advance until it hits the end of the contiguous group.
|
||
- The trailing cursor will activate all the requested columns, and will go through the group
|
||
(as identified by the leading cursor), and aggregate the keep columns.
|
||
|
||
The getters are as follows:
|
||
- The group column getters are taken directly from the trailing cursor.
|
||
- The keep column getters are provided by the aggregators.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.GroupTransform.Cursor.GroupKeyColumnChecker">
|
||
<summary>
|
||
This class keeps track of the previous group key and tests the current group key against the previous one.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.GroupTransform.Cursor.KeepColumnAggregator">
|
||
<summary>
|
||
This class handles the aggregation of one 'keep' column into a vector. It wraps around an <see cref="T:Microsoft.ML.DataViewRow"/>'s
|
||
column, reads the data and aggregates.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GroupTransform.Cursor.IsColumnActive(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns whether the given column is active in this row.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.GroupTransform.Cursor.GetGetter``1(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns a value getter delegate to fetch the value of column with the given columnIndex, from the row.
|
||
This throws if the column is not active in this row, or if the type
|
||
<typeparamref name="TValue"/> differs from this column's type.
|
||
</summary>
|
||
<typeparam name="TValue"> is the column's content type.</typeparam>
|
||
<param name="column"> is the output column whose getter should be returned.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.HashJoiningTransform">
|
||
<summary>
|
||
This transform hashes its input columns. Each column is hashed separately, and within each
|
||
column there is an option to specify which slots should be hashed together into one output slot.
|
||
This transform can be applied either to single valued columns or to known length vector columns.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.ColumnOptions.GetItemType(System.Int32)">
|
||
<summary>
|
||
Constructs the correct KeyType for the given hash bits.
|
||
Because of array size limitation, if numberOfBits = 31, the key type is not contiguous (not transformable into indicator array)
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.String,System.String,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Initializes a new instance of <see cref="T:Microsoft.ML.Transforms.HashJoiningTransform"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="input">Input <see cref="T:Microsoft.ML.IDataView"/>. This is the output from previous transform or loader.</param>
|
||
<param name="name">Name of the output column.</param>
|
||
<param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
|
||
<param name="join">Whether the values need to be combined for a single hash.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 31, inclusive.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.HashJoiningTransform.Arguments,Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Converts multiple column values into hashes.
|
||
This transform accepts both numeric and text inputs, both single and vector-valued columns.
|
||
</summary><remarks>
|
||
This transform can be helpful for ranking and cross-validation. In the case of ranking, where the GroupIdColumn column is required,
|
||
and needs to be of a key type you can use the <see cref="T:Microsoft.ML.Transforms.CategoricalHashOneHotVectorizer" /> to hash the text value of a single GroupID column into a key value.
|
||
If the GroupID is the combination of the values from multiple columns, you can use the HashConverter to hash multiple text columns into one key column.
|
||
Similarly with CrossValidator and the StratificationColumn.
|
||
</remarks>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.ComposeGetterOneToOne``1(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Getter generator for inputs of type <typeparamref name="TSrc"/>
|
||
</summary>
|
||
<typeparam name="TSrc">Input type. Must be a non-vector</typeparam>
|
||
<param name="input">Row inout</param>
|
||
<param name="iinfo">Index of the getter</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.ComposeGetterVecToVec``1(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Getter generator for inputs of type <typeparamref name="TSrc"/>, where output type is a vector of hashes
|
||
</summary>
|
||
<typeparam name="TSrc">Input type. Must be a vector</typeparam>
|
||
<param name="input">Row input</param>
|
||
<param name="iinfo">Index of the getter</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.ComposeGetterVecToOne``1(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Getter generator for inputs of type <typeparamref name="TSrc"/>, where output type is a single hash
|
||
</summary>
|
||
<typeparam name="TSrc">Input type. Must be a vector</typeparam>
|
||
<param name="input">Row input</param>
|
||
<param name="iinfo">Index of the getter</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.ComposeHashDelegate``1">
|
||
<summary>
|
||
Generic hash function
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.ComposeFloatHashDelegate">
|
||
<summary>
|
||
Generate a specialized hash function for floats
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.HashJoiningTransform.ComposeDoubleHashDelegate">
|
||
<summary>
|
||
Generate a specialized hash function for doubles
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.KeyToBinaryVectorMappingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.KeyToBinaryVectorMappingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.KeyToBinaryVectorMappingTransformer.Columns">
|
||
<summary>
|
||
The names of the output and input column pairs on which the transformation is performed.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.KeyToBinaryVectorMappingTransformer.Mapper.MakeGetterOne(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
This is for the scalar case.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.KeyToBinaryVectorMappingTransformer.Mapper.MakeGetterInd(Microsoft.ML.DataViewRow,System.Int32,Microsoft.ML.Data.VectorDataViewType)">
|
||
<summary>
|
||
This is for the indicator case - vector input and outputs should be concatenated.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.KeyToBinaryVectorMappingEstimator">
|
||
<summary>
|
||
Estimator for <see cref="T:Microsoft.ML.Transforms.KeyToBinaryVectorMappingTransformer"/>. Converts key types to their corresponding binary representation of the original value.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< or a known-size vector of keys. |
|
||
| Output column data type | A known-size vector of [System.Single](xref:System.Single). |
|
||
| Exportable to ONNX | No |
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.ConversionsCatalog.MapKeyToBinaryVector(Microsoft.ML.TransformsCatalog.ConversionTransforms,System.String,System.String)"/>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.KeyToBinaryVectorMappingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LambdaTransform">
|
||
<summary>
|
||
Utility class for creating transforms easily.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaTransform.CreateMap``3(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.Action{``0,``1,``2},System.Action{``2},Microsoft.ML.Data.SchemaDefinition,Microsoft.ML.Data.SchemaDefinition)">
|
||
<summary>
|
||
This is a 'stateful non-savable' version of the map transform: the mapping function is guaranteed to be invoked once per
|
||
every row of the data set, in sequence; one user-defined state object will be allocated per cursor and passed to the
|
||
map function every time. If <typeparamref name="TSrc"/>, <typeparamref name="TDst"/>, or
|
||
<typeparamref name="TState"/> implement the <see cref="T:System.IDisposable" /> interface, they will be disposed after use.
|
||
</summary>
|
||
<typeparam name="TSrc">The type that describes what 'source' columns are consumed from the
|
||
input <see cref="T:Microsoft.ML.IDataView"/>.</typeparam>
|
||
<typeparam name="TState">The type of the state object to allocate per cursor.</typeparam>
|
||
<typeparam name="TDst">The type that describes what new columns are added by this transform.</typeparam>
|
||
<param name="env">The host environment to use.</param>
|
||
<param name="source">The input data to apply transformation to.</param>
|
||
<param name="mapAction">The function that performs the transformation. The function should transform its <typeparamref name="TSrc"/>
|
||
argument into its <typeparamref name="TDst"/> argument and can utilize the per-cursor <typeparamref name="TState"/> state.</param>
|
||
<param name="initStateAction">The function that is called once per cursor to initialize state. Can be null.</param>
|
||
<param name="inputSchemaDefinition">The optional input schema. If <c>null</c>, the schema is
|
||
inferred from the <typeparamref name="TSrc"/> type.</param>
|
||
<param name="outputSchemaDefinition">The optional output schema. If <c>null</c>, the schema is
|
||
inferred from the <typeparamref name="TDst"/> type.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LambdaTransform.CreateFilter``2(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.Func{``0,``1,System.Boolean},System.Action{``1},Microsoft.ML.Data.SchemaDefinition)">
|
||
<summary>
|
||
This creates a filter transform that can 'accept' or 'decline' any row of the data based on the contents of the row
|
||
or state of the cursor.
|
||
This is a 'stateful non-savable' version of the filter: the filter function is guaranteed to be invoked once per
|
||
every row of the data set, in sequence (non-parallelizable); one user-defined state object will be allocated per cursor and passed to the
|
||
filter function every time.
|
||
If <typeparamref name="TSrc"/> or <typeparamref name="TState"/> implement the <see cref="T:System.IDisposable" /> interface, they will be disposed after use.
|
||
</summary>
|
||
<typeparam name="TSrc">The type that describes what 'source' columns are consumed from the
|
||
input <see cref="T:Microsoft.ML.IDataView"/>.</typeparam>
|
||
<typeparam name="TState">The type of the state object to allocate per cursor.</typeparam>
|
||
<param name="env">The host environment to use.</param>
|
||
<param name="source">The input data to apply transformation to.</param>
|
||
<param name="filterFunc">The user-defined function that determines whether to keep the row or discard it. First parameter
|
||
is the current row's contents, the second parameter is the cursor-specific state object.</param>
|
||
<param name="initStateAction">The function that is called once per cursor to initialize state. Can be null.</param>
|
||
<param name="inputSchemaDefinition">The optional input schema. If <c>null</c>, the schema is
|
||
inferred from the <typeparamref name="TSrc"/> type.</param>
|
||
<returns></returns>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LearnerFeatureSelectionTransform">
|
||
<summary>
|
||
Selects the slots for which the absolute value of the corresponding weight in a linear learner
|
||
is greater than a threshold.
|
||
Instantiates a DropSlots transform to actually drop the slots.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LearnerFeatureSelectionTransform.Train(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,Microsoft.ML.Transforms.LearnerFeatureSelectionTransform.Options,Microsoft.ML.Data.VBuffer{System.Single}@)">
|
||
<summary>
|
||
Returns a score for each slot of the features column.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.LoadTransform">
|
||
<summary>
|
||
Load specific transforms from the specified model file. Allows one to 'cherry pick' transforms from
|
||
a serialized chain, or to apply a pre-trained transform to a different (but still compatible) data view.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.LoadTransform.Create(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.String,System.String[],System.Boolean)">
|
||
<summary>
|
||
A helper method to create <see cref="T:Microsoft.ML.Transforms.LoadTransform"/> for public facing API.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="input">Input <see cref="T:Microsoft.ML.IDataView"/>. This is the output from previous transform or loader.</param>
|
||
<param name="modelFile">Model file to load the transforms from.</param>
|
||
<param name="tag">The tags (comma-separated) to be loaded (or omitted, if complement is true).</param>
|
||
<param name="complement">Whether to load all transforms except those marked by tags.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueDroppingTransformer">
|
||
<member name="NADrop">
|
||
<summary>
|
||
Removes missing values from vector type columns.
|
||
</summary>
|
||
</member>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.MissingValueDroppingTransformer.Columns">
|
||
<summary>
|
||
The names of the input columns of the transformation and the corresponding names for the output columns.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueDroppingTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[])">
|
||
<summary>
|
||
Initializes a new instance of <see cref="T:Microsoft.ML.Transforms.MissingValueDroppingTransformer"/>
|
||
</summary>
|
||
<param name="env">The environment to use.</param>
|
||
<param name="columns">The names of the input columns of the transformation and the corresponding names for the output columns.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueDroppingTransformer.SaveModel(Microsoft.ML.ModelSaveContext)">
|
||
<summary>
|
||
Saves the transform.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueHandlingTransformer">
|
||
<!-- No matching elements were found for the following include tag --><include file="doc.xml" path="doc/members/member[@name="NAHandle"]" />
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueHandlingTransformer.ReplacementKind.DefaultValue">
|
||
<summary>
|
||
Replace with the default value of the column based on its type. For example, 'zero' for numeric and 'empty' for string/text columns.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueHandlingTransformer.ReplacementKind.Mean">
|
||
<summary>
|
||
Replace with the mean value of the column. Supports only numeric/time span/ DateTime columns.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueHandlingTransformer.ReplacementKind.Minimum">
|
||
<summary>
|
||
Replace with the minimum value of the column. Supports only numeric/time span/ DateTime columns.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueHandlingTransformer.ReplacementKind.Maximum">
|
||
<summary>
|
||
Replace with the maximum value of the column. Supports only numeric/time span/ DateTime columns.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueHandlingTransformer.Create(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.String,System.String,Microsoft.ML.Transforms.MissingValueHandlingTransformer.ReplacementKind)">
|
||
<summary>
|
||
A helper method to create <see cref="T:Microsoft.ML.Transforms.MissingValueHandlingTransformer"/> for public facing API.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="input">Input <see cref="T:Microsoft.ML.IDataView"/>. This is the output from previous transform or loader.</param>
|
||
<param name="outputColumnName">Name of the output column.</param>
|
||
<param name="inputColumnName">Name of the column to be transformed. If this is null '<paramref name="outputColumnName"/>' will be used.</param>
|
||
<param name="replaceWith">The replacement method to utilize.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueHandlingTransformer.Create(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.MissingValueHandlingTransformer.Options,Microsoft.ML.IDataView)">
|
||
Factory method for SignatureDataTransform.
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorTransform.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.MissingValueIndicatorTransform.Arguments,Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Public constructor corresponding to SignatureDataTransform.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueIndicatorTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.MissingValueIndicatorEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.MissingValueIndicatorTransformer.Columns">
|
||
<summary>
|
||
The names of the output and input column pairs for the transformation.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorTransformer.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[])">
|
||
<summary>
|
||
Initializes a new instance of <see cref="T:Microsoft.ML.Transforms.MissingValueIndicatorTransformer"/>
|
||
</summary>
|
||
<param name="env">The environment to use.</param>
|
||
<param name="columns">The names of the input columns of the transformation and the corresponding names for the output columns.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorTransformer.SaveModel(Microsoft.ML.ModelSaveContext)">
|
||
<summary>
|
||
Saves the transform.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorTransformer.Mapper.GetIsNADelegate(Microsoft.ML.Data.DataViewType)">
|
||
<summary>
|
||
Returns the isNA predicate for the respective type.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorTransformer.Mapper.ComposeGetterOne(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Getter generator for single valued inputs.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorTransformer.Mapper.ComposeGetterVec(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Getter generator for vector valued inputs.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorTransformer.Mapper.FindNAs``1(Microsoft.ML.Data.VBuffer{``0}@,Microsoft.ML.Data.InPredicate{``0},System.Boolean,System.Collections.Generic.List{System.Int32},System.Boolean@)">
|
||
<summary>
|
||
Adds all NAs (or non-NAs) to the indices List. Whether NAs or non-NAs have been added is indicated by the bool sense.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorTransformer.Mapper.FillValues(System.Int32,Microsoft.ML.Data.VBuffer{System.Boolean}@,System.Collections.Generic.List{System.Int32},System.Boolean)">
|
||
<summary>
|
||
Fills indicator values for vectors. The indices is a list that either holds all of the NAs or all
|
||
of the non-NAs, indicated by sense being true or false respectively.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueIndicatorEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.Transforms.MissingValueIndicatorTransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
### Estimator Characteristics
|
||
| | |
|
||
| -- | -- |
|
||
| Does this estimator need to look at the data to train its parameters? | No |
|
||
| Input column data type | Vector or scalar value of <xref:System.Single> or <xref:System.Double> |
|
||
| Output column data type | If input column was scalar then <xref:System.Boolean> otherwise vector of <xref:System.Boolean>. |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.MissingValueIndicatorTransformer> creates a new column, named as specified in the output column name parameters, and
|
||
fills it with vector of bools where `true` in the i-th position in array indicates the i-th element in input column has missing value and `false` otherwise.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.ExtensionsCatalog.IndicateMissingValues(Microsoft.ML.TransformsCatalog,System.String,System.String)" />
|
||
<seealso cref="M:Microsoft.ML.ExtensionsCatalog.IndicateMissingValues(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[])" />
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.ValueTuple{System.String,System.String}[])">
|
||
<summary>
|
||
Initializes a new instance of <see cref="T:Microsoft.ML.Transforms.MissingValueIndicatorEstimator"/>
|
||
</summary>
|
||
<param name="env">The environment to use.</param>
|
||
<param name="columns">The names of the input columns of the transformation and the corresponding names for the output columns.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String)">
|
||
<summary>
|
||
Initializes a new instance of <see cref="T:Microsoft.ML.Transforms.MissingValueIndicatorEstimator"/>
|
||
</summary>
|
||
<param name="env">The environment to use.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueIndicatorEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.MissingValueReplacingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.GetReplacementValues(Microsoft.ML.IDataView,Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions[],System.Object[]@,System.Collections.BitArray[]@,Microsoft.ML.Data.DataViewType[]@)">
|
||
<summary>
|
||
Fill the repValues array with the correct replacement values based on the user-given replacement kinds.
|
||
Vectors default to by-slot imputation unless otherwise specified, except for unknown sized vectors
|
||
which force across-slot imputation.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.GetIsNADelegate(Microsoft.ML.Data.DataViewType)">
|
||
<summary>
|
||
Returns the isNA predicate for the respective type.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.GetSpecifiedValue(System.String,Microsoft.ML.Data.DataViewType,System.Delegate)">
|
||
<summary>
|
||
Converts a string to its respective value in the corresponding type.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.Mapper.ComposeGetterOne(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Getter generator for single valued inputs.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.Mapper.ComposeGetterOne``1(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Replaces NA values for scalars.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.Mapper.ComposeGetterVec(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Getter generator for vector valued inputs.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.Mapper.ComposeGetterVec``1(Microsoft.ML.DataViewRow,System.Int32)">
|
||
<summary>
|
||
Replaces NA values for vectors.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.Mapper.FillValues``1(Microsoft.ML.Data.VBuffer{``0}@,Microsoft.ML.Data.VBuffer{``0}@,Microsoft.ML.Data.InPredicate{``0},``0,System.Boolean)">
|
||
<summary>
|
||
Fills values for vectors where there is one replacement value.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingTransformer.Mapper.FillValues``1(Microsoft.ML.Data.VBuffer{``0}@,Microsoft.ML.Data.VBuffer{``0}@,Microsoft.ML.Data.InPredicate{``0},``0[],System.Collections.BitArray)">
|
||
<summary>
|
||
Fills values for vectors where there is slot-wise replacement values.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer.StatAggregator">
|
||
<summary>
|
||
The base class for stat aggregators for imputing mean, min, and max for the NAReplaceTransform.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer.StatAggregator`2">
|
||
<summary>
|
||
The base class for stat aggregators with knowledge of types.
|
||
</summary>
|
||
<typeparam name="TValue">The type for the column being aggregated.</typeparam>
|
||
<typeparam name="TStat">The type of the stat being computed by the stat aggregator.</typeparam>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.MissingValueReplacingTransformer.StatAggregator`2.RowCount">
|
||
<summary>
|
||
Returns the number of times that ProcessRow has been called.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.MissingValueReplacingTransformer.StatAggregatorAcrossSlots`2.ValueCount">
|
||
<summary>
|
||
Returns the number of values that have been processed so far.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.MissingValueReplacingTransformer.MinMaxAggregatorAcrossSlots`2.ValuesProcessed">
|
||
<summary>
|
||
Returns the number of times that ProcessValue has been called.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer.ModeStat`1">
|
||
<summary>
|
||
A mutable struct for keeping the appropriate statistics for mode calculations, whose scope is restricted
|
||
and only exists as an instance in a field or an array, utilizing the mutation of the struct correctly.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer.MeanStatDouble">
|
||
<summary>
|
||
This is a mutable struct (so is evil). However, its scope is restricted
|
||
and the only instances are in a field or an array, so the mutation does
|
||
the right thing.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer.MeanStatInt">
|
||
<summary>
|
||
A mutable struct for keeping the appropriate statistics for mean calculations for IX types, TS, and DT,
|
||
whose scope is restricted and only exists as an instance in a field or an array, utilizing the mutation
|
||
of the struct correctly.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingEstimator">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.IEstimator`1"/> for the <see cref="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer"/>.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
|
||
### Estimator Characteristics
|
||
| | |
|
||
| -- | -- |
|
||
| Does this estimator need to look at the data to train its parameters? | Yes |
|
||
| Input column data type | Vector or scalar of <xref:System.Single> or <xref:System.Double> |
|
||
| Output column data type | The same as the data type in the input column |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.MissingValueReplacingTransformer"/> creates a new column, named as specified in the output column name parameters, and
|
||
copies the data from the input column to this new column with exception what missing values in data would be replaced according to chosen strategy.
|
||
|
||
Check the See Also section for links of usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.ExtensionsCatalog.ReplaceMissingValues(Microsoft.ML.TransformsCatalog,System.String,System.String,Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode,System.Boolean)" />
|
||
<seealso cref="M:Microsoft.ML.ExtensionsCatalog.ReplaceMissingValues(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode,System.Boolean)" />
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode">
|
||
<summary>
|
||
The possible ways to replace missing values.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode.DefaultValue">
|
||
<summary>
|
||
Replace with the default value of the column based on its type.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode.Mean">
|
||
<summary>
|
||
Replace with the mean value of the column.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode.Minimum">
|
||
<summary>
|
||
Replace with the minimum value of the column.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode.Maximum">
|
||
<summary>
|
||
Replace with the maximum value of the column.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode.Mode">
|
||
<summary>
|
||
Replace with the most frequent value of the column.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions.Name">
|
||
<summary> Name of the column resulting from the transformation of <see cref="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions.InputColumnName"/>.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions.InputColumnName">
|
||
<summary> Name of column to transform. </summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions.ImputeBySlot">
|
||
<summary>
|
||
If true, per-slot imputation of replacement is performed.
|
||
Otherwise, replacement value is imputed for the entire vector column. This setting is ignored for scalars and variable vectors,
|
||
where imputation is always for the entire column.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions.Replacement">
|
||
<summary> How to replace the missing values.</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions.ReplacementString">
|
||
<summary> Replacement value for missing values (only used in entrypoing and command line API).</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions.#ctor(System.String,System.String,Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode,System.Boolean)">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="replacementMode">How to replace the missing values.</param>
|
||
<param name="imputeBySlot">If true, per-slot imputation of replacement is performed.
|
||
Otherwise, replacement value is imputed for the entire vector column. This setting is ignored for scalars and variable vectors,
|
||
where imputation is always for the entire column.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions.#ctor(System.String,System.String,Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode,System.Boolean,System.String)">
|
||
<summary>
|
||
This constructor is used internally to convert from <see cref="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer.Options"/> to <see cref="T:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions"/>
|
||
as we support <paramref name="replacementString"/> in command line and entrypoint API only.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MissingValueReplacingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.Transforms.MissingValueReplacingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator">
|
||
<summary>
|
||
Selects the top k slots across all specified columns ordered by their mutual information with the label column
|
||
(what you can learn about the label by observing the value of the specified column).
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown">< or [key](xref:Microsoft.ML.Data.KeyDataViewType) data types|
|
||
| Output column data type | Same as the input column|
|
||
| Exportable to ONNX | Yes |
|
||
|
||
Formally, the mutual information can be written as:
|
||
|
||
$\text{MI}(X,Y) = E_{x,y}[\log(P(x,y)) - \log(P(x)) - \log(P(y))]$ where $x$ and $y$ are observations of random variables $X$ and $Y$.
|
||
|
||
where the expectation E is taken over the joint distribution of X and Y.
|
||
Here P(x, y) is the joint probability density function of X and Y, P(x) and P(y) are the marginal probability density functions of X and Y respectively.
|
||
In general, a higher mutual information between the dependent variable(or label) and an independent variable(or feature) means
|
||
that the label has higher mutual dependence over that feature.
|
||
It keeps the top slots in output features with the largest mutual information with the label.
|
||
|
||
For example, for the following Features and Label column, if we specify that we want the top 2 slots(vector elements) that have the higher correlation
|
||
with the label column, the output of applying this Estimator would keep the first and the third slots only, because their values
|
||
are more correlated with the values in the Label column.
|
||
|
||
| Label | Features |
|
||
| -- | -- |
|
||
|True |4,6,0 |
|
||
|False|0,7,5 |
|
||
|True |4,7,0 |
|
||
|False|0,7,0 |
|
||
|
||
This is how the dataset above would look, after fitting the estimator, and transforming the data with the resulting transformer:
|
||
|
||
| Label | Features |
|
||
| -- | -- |
|
||
|True |4,0 |
|
||
|False|0,5 |
|
||
|True |4,0 |
|
||
|False|0,5 |
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnMutualInformation(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,Microsoft.ML.InputOutputColumnPair[],System.String,System.Int32,System.Int32)"/>
|
||
<seealso cref="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnMutualInformation(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,System.String,System.String,System.String,System.Int32,System.Int32)"/>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.Int32,System.Int32,System.ValueTuple{System.String,System.String}[])">
|
||
<summary>
|
||
Selects the top k slots across all specified columns ordered by their mutual information with the label column.
|
||
</summary><remarks>
|
||
<para>
|
||
The mutual information of two random variables X and Y is a measure of the mutual dependence between the variables.
|
||
Formally, the mutual information can be written as:
|
||
</para>
|
||
<para>I(X;Y) = E[log(p(x,y)) - log(p(x)) - log(p(y))]</para>
|
||
<para>where the expectation is taken over the joint distribution of X and Y.
|
||
Here p(x,y) is the joint probability density function of X and Y, p(x) and p(y) are the marginal probability density functions of X and Y respectively.
|
||
In general, a higher mutual information between the dependent variable (or label) and an independent variable (or feature) means
|
||
that the label has higher mutual dependence over that feature.
|
||
It keeps the top SlotsInOutput features with the largest mutual information with the label.
|
||
</para>
|
||
</remarks>
|
||
<param name="env">The environment to use.</param>
|
||
<param name="labelColumnName">Name of the column to use for labels.</param>
|
||
<param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
|
||
<param name="numberOfBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
|
||
<param name="columns">Specifies the names of the input columns for the transformation, and their respective output column names.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.String,System.Int32,System.Int32)">
|
||
<summary>
|
||
Selects the top k slots across all specified columns ordered by their mutual information with the label column.
|
||
</summary><remarks>
|
||
<para>
|
||
The mutual information of two random variables X and Y is a measure of the mutual dependence between the variables.
|
||
Formally, the mutual information can be written as:
|
||
</para>
|
||
<para>I(X;Y) = E[log(p(x,y)) - log(p(x)) - log(p(y))]</para>
|
||
<para>where the expectation is taken over the joint distribution of X and Y.
|
||
Here p(x,y) is the joint probability density function of X and Y, p(x) and p(y) are the marginal probability density functions of X and Y respectively.
|
||
In general, a higher mutual information between the dependent variable (or label) and an independent variable (or feature) means
|
||
that the label has higher mutual dependence over that feature.
|
||
It keeps the top SlotsInOutput features with the largest mutual information with the label.
|
||
</para>
|
||
</remarks>
|
||
<param name="env">The environment to use.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName" />.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null" />, the value of the <paramref name="outputColumnName" /> will be used as source.</param>
|
||
<param name="labelColumnName">Name of the column to use for labels.</param>
|
||
<param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
|
||
<param name="numBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.ITransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator.Create(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator.Options,Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Create method corresponding to SignatureDataTransform.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator.ComputeThreshold(System.Single[][],System.Int32,System.Int32@)">
|
||
<summary>
|
||
Computes the threshold for the scores such that the top k slots are preserved.
|
||
If there are less than k scores greater than zero, the threshold is set to zero and
|
||
the tiedScoresToKeep is set to zero, so that we only keep scores strictly greater than zero.
|
||
</summary>
|
||
<param name="scores">The score for each column and each slot.</param>
|
||
<param name="topk">How many slots to preserve.</param>
|
||
<param name="tiedScoresToKeep">If there are ties, how many of them to keep.</param>
|
||
<returns>The threshold.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.TrainCore(Microsoft.ML.Runtime.IHost,Microsoft.ML.IDataView,System.String,System.String[],System.Int32,System.Int32[])">
|
||
<summary>
|
||
Returns the feature selection scores for each slot of each column.
|
||
</summary>
|
||
<param name="host">The host.</param>
|
||
<param name="input">The input dataview.</param>
|
||
<param name="labelColumnName">The label column.</param>
|
||
<param name="columns">The columns for which to compute the feature selection scores.</param>
|
||
<param name="numBins">The number of bins to use for numeric features.</param>
|
||
<param name="colSizes">The columns' sizes before dropping any slots.</param>
|
||
<returns>A list of scores for each column and each slot.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.ComputeMutualInformation(Microsoft.ML.Data.Transposer,System.Int32)">
|
||
<summary>
|
||
Computes the mutual information for one column.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.ComputeMutualInformation``1(Microsoft.ML.Data.Transposer,System.Int32,Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.Mapper{``0})">
|
||
<summary>
|
||
Computes the mutual information for one column.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.ComputeMutualInformation(Microsoft.ML.Data.VBuffer{System.Int32}@,System.Int32,System.Int32)">
|
||
<summary>
|
||
Computes the mutual information for one slot.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.FillTable(Microsoft.ML.Data.VBuffer{System.Int32}@,System.Int32,System.Int32)">
|
||
<summary>
|
||
Fills the contingency table.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.BinKeys``1(Microsoft.ML.Data.DataViewType)">
|
||
<summary>
|
||
Maps from keys to ints.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.BinInts(Microsoft.ML.Data.VBuffer{System.Int32}@,Microsoft.ML.Data.VBuffer{System.Int32}@,System.Int32,System.Int32@,System.Int32@)">
|
||
<summary>
|
||
Maps Ints.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.BinSingles(Microsoft.ML.Data.VBuffer{System.Single}@,Microsoft.ML.Data.VBuffer{System.Int32}@,System.Int32,System.Int32@,System.Int32@)">
|
||
<summary>
|
||
Maps from Singles to ints. NaNs (and only NaNs) are mapped to the first bin.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.Impl.BinDoubles(Microsoft.ML.Data.VBuffer{System.Double}@,Microsoft.ML.Data.VBuffer{System.Int32}@,System.Int32,System.Int32@,System.Int32@)">
|
||
<summary>
|
||
Maps from Doubles to ints. NaNs (and only NaNs) are mapped to the first bin.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.MutualInformationFeatureSelectionUtils.CreateVectorMapper``2(Microsoft.ML.Data.ValueMapper{``0,``1})">
|
||
<summary>
|
||
Given a mapper from T to int, creates a mapper from VBuffer{T} to VBuffer<int>.
|
||
Assumes that the mapper maps default(TSrc) to default(TDst) so that the returned mapper preserves sparsity.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.NAHandling">
|
||
<summary>
|
||
Entry point methods for NA handling.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.OneHotEncodingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.OneHotEncodingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.OneHotEncodingEstimator">
|
||
<summary>
|
||
Converts one or more input columns of categorical values into as many output columns of one-hot encoded vectors.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><, <xref:System.DateTime> or [key](xref:Microsoft.ML.Data.KeyDataViewType) type. |
|
||
| Output column data type | Scalar or vector of [key](xref:Microsoft.ML.Data.KeyDataViewType), or vector of <xref:System.Single> type. |
|
||
| Exportable to ONNX | Yes |
|
||
|
||
The <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator> builds a dictionary of unique values appearing in the input column.
|
||
The resulting <xref:Microsoft.ML.Transforms.OneHotEncodingTransformer> converts one or more input columns into as many output
|
||
columns of one-hot encoded vectors.
|
||
|
||
The <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator> is often used to convert categorical data into a form that can be
|
||
provided to a machine learning algorithm.
|
||
|
||
The output of this transform is specified by <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind>:
|
||
|
||
- <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator> produces an [indicator vector](https://en.wikipedia.org/wiki/Indicator_vector).
|
||
Each slot in this vector corresponds to a category in the dictionary, so its length is the size of the built dictionary.
|
||
If a value is not found in the dictioray, the output is the zero vector.
|
||
|
||
- <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag> produces one vector such that each slot stores the number
|
||
of occurances of the corresponding value in the input vector.
|
||
Each slot in this vector corresponds to a value in the dictionary, so its length is the size of the built dictionary.
|
||
<xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator> and <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag>
|
||
differ simply in how the bit-vectors generated from individual slots in the input column are aggregated:
|
||
for Indicator they are concatenated and for Bag they are added. When the source column is a Scalar, the Indicator and Bag options are identical.
|
||
|
||
- <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Key> produces keys in a <xref:Microsoft.ML.Data.KeyDataViewType> column.
|
||
If the input column is a vector, the output contains a vectory [key](xref:Microsoft.ML.Data.KeyDataViewType) type, where each slot of the
|
||
vector corresponds to the respective slot of the input vector.
|
||
If a category is not found in the bulit dictionary, it is assigned the value zero.
|
||
|
||
- <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Binary> produces a binary encoded vector to represent the values found in the dictionary
|
||
that are present in the input column. If a value in the input column is not found in the dictionary, the output is the zero vector.
|
||
|
||
The OneHotEncodingTransformer can be applied to one or more columns, in which case it builds and uses a separate dictionary
|
||
for each column that it is applied to.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.CategoricalCatalog.OneHotEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,Microsoft.ML.InputOutputColumnPair[],Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality,Microsoft.ML.IDataView)"/>
|
||
<seealso cref="M:Microsoft.ML.CategoricalCatalog.OneHotEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,System.String,System.String,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality,Microsoft.ML.IDataView)"/>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag">
|
||
<summary>
|
||
Output is a bag (multi-set) vector
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator">
|
||
<summary>
|
||
Output is an indicator vector
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Key">
|
||
<summary>
|
||
Output is a key value
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Binary">
|
||
<summary>
|
||
Output is binary encoded
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.OneHotEncodingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotEncodingEstimator.ColumnOptions.#ctor(System.String,System.String,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality)">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="outputKind">Output kind: Bag (multi-set vector), Ind (indicator vector), Key (index), or Binary encoded indicator vector.</param>
|
||
<param name="maximumNumberOfKeys">Maximum number of terms to keep per column when auto-training.</param>
|
||
<param name="keyOrdinality">How items should be ordered when vectorized. If <see cref="F:Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality.ByOccurrence"/> choosen they will be in the order encountered.
|
||
If <see cref="F:Microsoft.ML.Transforms.ValueToKeyMappingEstimator.KeyOrdinality.ByValue"/>, items are sorted according to their default comparison, for example, text sorting will be case sensitive (for example, 'A' then 'Z' then 'a').</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotEncodingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind)">
|
||
Initializes an instance of the <see cref="T:Microsoft.ML.Transforms.OneHotEncodingEstimator"/>.
|
||
<param name="env">Host Environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="outputKind">The type of output expected.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotEncodingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotEncodingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.Transforms.OneHotEncodingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.OneHotHashEncodingTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting a <see cref="T:Microsoft.ML.Transforms.OneHotHashEncodingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.OneHotHashEncodingTransformer.Options">
|
||
<summary>
|
||
This class is a merger of <see cref="T:Microsoft.ML.Transforms.HashingTransformer.Options"/> and <see cref="T:Microsoft.ML.Transforms.KeyToVectorMappingTransformer.Options"/>
|
||
with join option removed
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotHashEncodingTransformer.Create(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.String,System.String,System.Int32,System.Int32,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind)">
|
||
<summary>
|
||
A helper method to create <see cref="T:Microsoft.ML.Transforms.OneHotHashEncodingTransformer"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="input">Input <see cref="T:Microsoft.ML.IDataView"/>. This is the output from previous transform or loader.</param>
|
||
<param name="name">Name of the output column.</param>
|
||
<param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="maximumNumberOfInverts">During hashing we construct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
<param name="outputKind">The type of output expected.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotHashEncodingTransformer.GetOutputSchema(Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Schema propagation for transformers. Returns the output schema of the data, if
|
||
the input schema is like the one provided.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotHashEncodingTransformer.Transform(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Take the data in, make transformations, output the data. Note that <see cref="T:Microsoft.ML.IDataView"/>
|
||
are lazy, so no actual transformations happen here, just schema validation.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.OneHotHashEncodingTransformer.Microsoft#ML#ITransformer#IsRowToRowMapper">
|
||
<summary>
|
||
Whether a call to <see cref="M:Microsoft.ML.ITransformer.GetRowToRowMapper(Microsoft.ML.DataViewSchema)"/> should succeed, on an appropriate schema.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotHashEncodingTransformer.Microsoft#ML#ITransformer#GetRowToRowMapper(Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Constructs a row-to-row mapper based on an input schema.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.OneHotHashEncodingEstimator">
|
||
<summary>
|
||
Converts one or more input columns of categorical values into as many output columns of hash-based one-hot encoded vectors.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><, or [key](xref:Microsoft.ML.Data.KeyDataViewType) type. |
|
||
| Output column data type | Scalar or vector of [key](xref:Microsoft.ML.Data.KeyDataViewType), or vector of <xref:System.Single> type. |
|
||
| Exportable to ONNX | No |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.OneHotEncodingTransformer> converts one or more input columns into as many output
|
||
columns of one-hot encoded vectors, where indexing is done by hashing the value and using the hash as an index.
|
||
|
||
The <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator> is often used to convert categorical data into a form that can be
|
||
provided to a machine learning algorithm.
|
||
|
||
The output of this transform is specified by <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind>:
|
||
|
||
- <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator> produces an [indicator vector](https://en.wikipedia.org/wiki/Indicator_vector).
|
||
Each slot in this vector corresponds to a category in the dictionary, so its length is the size of the built dictionary.
|
||
If a value is not found in the dictionary, the output is the zero vector.
|
||
|
||
- <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag> produces one vector such that each slot stores the number
|
||
of occurrences of the corresponding value in the input vector.
|
||
Each slot in this vector corresponds to a value in the dictionary, so its length is the size of the built dictionary.
|
||
<xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Indicator> and <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Bag>
|
||
differ simply in how the bit-vectors generated from individual slots in the input column are aggregated:
|
||
for Indicator they are concatenated and for Bag they are added. When the source column is a Scalar, the Indicator and Bag options are identical.
|
||
|
||
- <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Key> produces keys in a <xref:Microsoft.ML.Data.KeyDataViewType> column.
|
||
If the input column is a vector, the output contains a vector [key](xref:Microsoft.ML.Data.KeyDataViewType) type, where each slot of the
|
||
vector corresponds to the respective slot of the input vector.
|
||
If a category is not found in the built dictionary, it is assigned the value zero.
|
||
|
||
- <xref:Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind.Binary> produces a binary encoded vector to represent the values found in the dictionary
|
||
that are present in the input column. If a value in the input column is not found in the dictionary, the output is the zero vector.
|
||
|
||
The OneHotEncodingTransformer can be applied to one or more columns, in which case it builds and uses a separate dictionary
|
||
for each column that it is applied to.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]>
|
||
</format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.CategoricalCatalog.OneHotHashEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,System.String,System.String,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,System.UInt32,System.Boolean,System.Int32)"/>
|
||
<seealso cref="M:Microsoft.ML.CategoricalCatalog.OneHotHashEncoding(Microsoft.ML.TransformsCatalog.CategoricalTransforms,Microsoft.ML.InputOutputColumnPair[],Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,System.UInt32,System.Boolean,System.Int32)"/>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.OneHotHashEncodingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotHashEncodingEstimator.ColumnOptions.#ctor(System.String,System.String,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind,System.Int32,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="name"/> will be used as source.</param>
|
||
<param name="outputKind">Kind of output: bag, indicator vector etc.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 31, inclusive.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each term should be included in the hash.</param>
|
||
<param name="maximumNumberOfInverts">During hashing we construct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotHashEncodingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Int32,System.Int32,Microsoft.ML.Transforms.OneHotEncodingEstimator.OutputKind)">
|
||
<summary>
|
||
Instantiates a new instance of <see cref="T:Microsoft.ML.Transforms.OneHotHashEncodingEstimator"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform.
|
||
If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="maximumNumberOfInverts">During hashing we construct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the metadata for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
<param name="outputKind">The type of output expected.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotHashEncodingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OneHotHashEncodingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.Transforms.OneHotHashEncodingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.OptionalColumnTransform">
|
||
<summary>
|
||
Creates a new column with the specified type and default values.
|
||
</summary><remarks>
|
||
If the user wish to create additional columns with a particular type and default values, or replicated the values from one column to another, changing their type, they can do so using this transform.
|
||
This transform can be used as a workaround to create a Label column after deserializing a model, for prediction.
|
||
Some transforms in the serialized model operate on the Label column, and would throw errors during prediction if such a column is not found.
|
||
</remarks>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OptionalColumnTransform.Bindings.GetDependencies(System.Collections.Generic.IEnumerable{Microsoft.ML.DataViewSchema.Column})">
|
||
<summary>
|
||
Given a set of columns, return the input columns that are needed to generate those output columns.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OptionalColumnTransform.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.String[])">
|
||
<summary>
|
||
Initializes a new instance of <see cref="T:Microsoft.ML.Transforms.OptionalColumnTransform"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="input">Input <see cref="T:Microsoft.ML.IDataView"/>. This is the output from previous transform or loader.</param>
|
||
<param name="columns">Columns to transform.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OptionalColumnTransform.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.OptionalColumnTransform.Arguments,Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Public constructor corresponding to SignatureDataTransform.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OptionalColumnTransform.Cursor.IsColumnActive(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns whether the given column is active in this row.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.OptionalColumnTransform.Cursor.GetGetter``1(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns a value getter delegate to fetch the value of column with the given columnIndex, from the row.
|
||
This throws if the column is not active in this row, or if the type
|
||
<typeparamref name="TValue"/> differs from this column's type.
|
||
</summary>
|
||
<typeparam name="TValue"> is the column's content type.</typeparam>
|
||
<param name="column"> is the output column whose getter should be returned.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.PermutationFeatureImportance`3.PermuterState">
|
||
<summary>
|
||
This is used as a hack to force Lambda Transform behave sequentially.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.PermutationFeatureImportance`3.FeaturesBuffer">
|
||
<summary>
|
||
Helper structure used for features permutation in Lambda Transform.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.PermutationFeatureImportance`3.FeatureIndex">
|
||
<summary>
|
||
Helper class for report's Lambda transform.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.PermutationFeatureImportance`3.FeatureName">
|
||
<summary>
|
||
One more helper class for report's Lambda transform.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.ProduceIdTransform">
|
||
<summary>
|
||
Produces a column with the cursor's ID as a column. This can be useful for diagnostic purposes.
|
||
|
||
This class will obviously generate different data given different IDs. So, if you save data to
|
||
some other file, then apply this transform to that dataview, it may of course have a different
|
||
result. This is distinct from most transforms that produce results based on data alone.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.ProduceIdTransform.Cursor.IsColumnActive(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns whether the given column is active in this row.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.ProduceIdTransform.Cursor.GetGetter``1(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns a value getter delegate to fetch the value of column with the given columnIndex, from the row.
|
||
This throws if the column is not active in this row, or if the type
|
||
<typeparamref name="TValue"/> differs from this column's type.
|
||
</summary>
|
||
<typeparam name="TValue"> is the column's content type.</typeparam>
|
||
<param name="column"> is the output column whose getter should be returned.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.Properties.Resources">
|
||
<summary>
|
||
A strongly-typed resource class, for looking up localized strings, etc.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.ResourceManager">
|
||
<summary>
|
||
Returns the cached ResourceManager instance used by this class.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Culture">
|
||
<summary>
|
||
Overrides the current thread's CurrentUICulture property for all
|
||
resource lookups using this strongly typed resource class.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Arabic">
|
||
<summary>
|
||
Looks up a localized string similar to ب
|
||
ب
|
||
بعد
|
||
حتى
|
||
حين
|
||
دون
|
||
صباح
|
||
في
|
||
قبل
|
||
لكن
|
||
مساء
|
||
مع
|
||
من
|
||
نحو
|
||
واكد
|
||
وفي
|
||
ومن
|
||
اطار
|
||
و
|
||
اثر
|
||
اجل
|
||
احد
|
||
اذا
|
||
اكثر
|
||
اكد
|
||
التي
|
||
الثاني
|
||
الثانية
|
||
الذاتي
|
||
الذي
|
||
الذين
|
||
السابق
|
||
الف
|
||
الماضي
|
||
المقبل
|
||
الوقت
|
||
اليوم
|
||
امس
|
||
انه
|
||
باسم
|
||
بان
|
||
برس
|
||
بسبب
|
||
بشكل
|
||
بعض
|
||
بن
|
||
به
|
||
بها
|
||
بين
|
||
تم
|
||
ثلاثة
|
||
ثم
|
||
جميع
|
||
حاليا
|
||
حوالى
|
||
حول
|
||
حيث
|
||
خلال
|
||
ذلك
|
||
زيارة
|
||
سنة
|
||
سنوات
|
||
شخصا
|
||
صفر
|
||
ضد
|
||
ضمن
|
||
عام
|
||
عاما
|
||
عدة
|
||
عدد
|
||
عدم
|
||
عشر
|
||
عشرة
|
||
على
|
||
عليه
|
||
عليها
|
||
عن
|
||
عند
|
||
عندما
|
||
غدا
|
||
غير
|
||
فان
|
||
فيه
|
||
فيها
|
||
قال
|
||
قد
|
||
قوة
|
||
كان
|
||
كانت
|
||
كل
|
||
كلم
|
||
كما
|
||
لا
|
||
لدى
|
||
لقا [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Czech">
|
||
<summary>
|
||
Looks up a localized string similar to bude
|
||
budeš
|
||
byl
|
||
byla
|
||
byli
|
||
bylo
|
||
je
|
||
jsem
|
||
jsme
|
||
jsou
|
||
jste
|
||
aby
|
||
aj
|
||
ale
|
||
ani
|
||
asi
|
||
až
|
||
bez
|
||
bude-li
|
||
budeme
|
||
budeme-li
|
||
budete
|
||
budete-li
|
||
budeš-li
|
||
budou
|
||
budou-li
|
||
budu
|
||
budu-li
|
||
buď
|
||
buďme
|
||
buďte
|
||
by
|
||
byl-li
|
||
byla-li
|
||
bylas
|
||
byli-li
|
||
bylo-li
|
||
bylos
|
||
byls
|
||
byly
|
||
byly-li
|
||
byt
|
||
byv
|
||
byvše
|
||
byvši
|
||
být
|
||
býti
|
||
co
|
||
což
|
||
cz
|
||
další
|
||
design
|
||
dnes
|
||
do
|
||
email
|
||
ho
|
||
jak
|
||
jako
|
||
je-li
|
||
jeho
|
||
jej
|
||
jejich
|
||
její
|
||
jen
|
||
ještě
|
||
ji
|
||
jine
|
||
již
|
||
jsa
|
||
jsem-li
|
||
jsi
|
||
jsi-li
|
||
jsme-li
|
||
jsou-li
|
||
jsouc
|
||
jsouce
|
||
jste-li
|
||
kam
|
||
kde
|
||
[rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Danish">
|
||
<summary>
|
||
Looks up a localized string similar to af
|
||
andre
|
||
at
|
||
da
|
||
de
|
||
deres
|
||
dette
|
||
din
|
||
ej
|
||
en
|
||
ene
|
||
et
|
||
han
|
||
hans
|
||
i
|
||
ind
|
||
lille
|
||
ni
|
||
ny
|
||
otte
|
||
stor
|
||
store
|
||
syv
|
||
alle
|
||
andet
|
||
begge
|
||
den
|
||
denne
|
||
der
|
||
det
|
||
dig
|
||
dog
|
||
du
|
||
eller
|
||
end
|
||
eneste
|
||
enhver
|
||
fem
|
||
fire
|
||
flere
|
||
fleste
|
||
for
|
||
fordi
|
||
forrige
|
||
fra
|
||
få
|
||
før
|
||
god
|
||
har
|
||
hendes
|
||
her
|
||
hun
|
||
hvad
|
||
hvem
|
||
hver
|
||
hvilken
|
||
hvis
|
||
hvor
|
||
hvordan
|
||
hvorfor
|
||
hvornår
|
||
ikke
|
||
ingen
|
||
intet
|
||
jeg
|
||
jeres
|
||
kan
|
||
kom
|
||
kommer
|
||
lav
|
||
lidt
|
||
man
|
||
mand
|
||
mange
|
||
med
|
||
meget
|
||
men
|
||
mens
|
||
mere
|
||
mig
|
||
ned
|
||
nogen
|
||
noget
|
||
nyt
|
||
nær
|
||
næste
|
||
næsten
|
||
[rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Dutch">
|
||
<summary>
|
||
Looks up a localized string similar to aan
|
||
af
|
||
al
|
||
als
|
||
bij
|
||
dan
|
||
dat
|
||
die
|
||
dit
|
||
een
|
||
en
|
||
er
|
||
had
|
||
heb
|
||
hem
|
||
het
|
||
hij
|
||
hoe
|
||
hun
|
||
ik
|
||
in
|
||
is
|
||
je
|
||
kan
|
||
me
|
||
men
|
||
met
|
||
mij
|
||
nog
|
||
nu
|
||
of
|
||
ons
|
||
ook
|
||
te
|
||
tot
|
||
uit
|
||
van
|
||
was
|
||
wat
|
||
we
|
||
wel
|
||
wij
|
||
zal
|
||
ze
|
||
zei
|
||
zij
|
||
zo
|
||
zou
|
||
.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.English">
|
||
<summary>
|
||
Looks up a localized string similar to a
|
||
about
|
||
above
|
||
above
|
||
across
|
||
after
|
||
afterwards
|
||
again
|
||
against
|
||
all
|
||
almost
|
||
alone
|
||
along
|
||
already
|
||
also
|
||
although
|
||
always
|
||
am
|
||
among
|
||
amongst
|
||
amoungst
|
||
amount
|
||
an
|
||
and
|
||
another
|
||
any
|
||
anyhow
|
||
anyone
|
||
anything
|
||
anyway
|
||
anywhere
|
||
are
|
||
around
|
||
as
|
||
at
|
||
back
|
||
be
|
||
became
|
||
because
|
||
become
|
||
becomes
|
||
becoming
|
||
been
|
||
before
|
||
beforehand
|
||
behind
|
||
being
|
||
below
|
||
beside
|
||
besides
|
||
between
|
||
beyond
|
||
both
|
||
bottom
|
||
but
|
||
by
|
||
call
|
||
can
|
||
cannot
|
||
cant
|
||
co
|
||
con
|
||
could
|
||
couldnt
|
||
cry
|
||
de
|
||
describe
|
||
detail
|
||
do
|
||
done
|
||
down
|
||
due
|
||
du [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.French">
|
||
<summary>
|
||
Looks up a localized string similar to de
|
||
des
|
||
d'
|
||
la
|
||
du
|
||
l'
|
||
et
|
||
à
|
||
en
|
||
sur
|
||
aux
|
||
par
|
||
pour
|
||
au
|
||
dans
|
||
un
|
||
est
|
||
été
|
||
a
|
||
une
|
||
sous
|
||
ou
|
||
pas
|
||
entre
|
||
qui
|
||
nº
|
||
lès
|
||
plus
|
||
il
|
||
y
|
||
que
|
||
contre
|
||
je
|
||
non
|
||
n'
|
||
sans
|
||
vous
|
||
avec
|
||
ne
|
||
ce
|
||
son
|
||
ses
|
||
mon
|
||
moins
|
||
se
|
||
qu'
|
||
moi
|
||
j'
|
||
c'
|
||
si
|
||
ma
|
||
s'
|
||
être
|
||
tout
|
||
comme
|
||
sa
|
||
sont
|
||
ai
|
||
elle
|
||
autres
|
||
pendant
|
||
chez
|
||
mais
|
||
avant
|
||
nous
|
||
cette
|
||
après
|
||
vers
|
||
était
|
||
tous
|
||
autre
|
||
tu
|
||
très
|
||
même
|
||
ont
|
||
anti
|
||
puis
|
||
leur
|
||
où
|
||
lui
|
||
ça
|
||
suis
|
||
depuis
|
||
ni
|
||
mes
|
||
près
|
||
hors
|
||
outre
|
||
ils
|
||
votre
|
||
toi
|
||
lors
|
||
t'
|
||
aussi
|
||
donc
|
||
ces
|
||
toute
|
||
[rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.German">
|
||
<summary>
|
||
Looks up a localized string similar to a
|
||
ab
|
||
aber
|
||
aber
|
||
ach
|
||
acht
|
||
achte
|
||
achten
|
||
achter
|
||
achtes
|
||
ag
|
||
alle
|
||
allein
|
||
allem
|
||
allen
|
||
aller
|
||
allerdings
|
||
alles
|
||
allgemeinen
|
||
als
|
||
als
|
||
also
|
||
am
|
||
an
|
||
andere
|
||
anderen
|
||
andern
|
||
anders
|
||
au
|
||
auch
|
||
auch
|
||
auf
|
||
aus
|
||
ausser
|
||
außer
|
||
ausserdem
|
||
außerdem
|
||
b
|
||
bald
|
||
bei
|
||
beide
|
||
beiden
|
||
beim
|
||
beispiel
|
||
bekannt
|
||
bereits
|
||
besonders
|
||
besser
|
||
besten
|
||
bin
|
||
bis
|
||
bisher
|
||
bist
|
||
c
|
||
d
|
||
da
|
||
dabei
|
||
dadurch
|
||
dafür
|
||
dagegen
|
||
daher
|
||
dahin
|
||
dahinter
|
||
damals
|
||
damit
|
||
danach
|
||
daneben
|
||
dank
|
||
dann
|
||
daran
|
||
darauf
|
||
daraus
|
||
darf
|
||
darfst
|
||
[rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Italian">
|
||
<summary>
|
||
Looks up a localized string similar to a
|
||
adesso
|
||
ai
|
||
al
|
||
alla
|
||
allo
|
||
allora
|
||
altre
|
||
altri
|
||
altro
|
||
anche
|
||
ancora
|
||
avere
|
||
aveva
|
||
avevano
|
||
ben
|
||
buono
|
||
che
|
||
chi
|
||
cinque
|
||
comprare
|
||
con
|
||
consecutivi
|
||
consecutivo
|
||
cosa
|
||
cui
|
||
da
|
||
del
|
||
della
|
||
dello
|
||
dentro
|
||
deve
|
||
devo
|
||
di
|
||
doppio
|
||
due
|
||
e
|
||
ecco
|
||
fare
|
||
fine
|
||
fino
|
||
fra
|
||
gente
|
||
giù
|
||
ha
|
||
hai
|
||
hanno
|
||
ho
|
||
il
|
||
indietro
|
||
invece
|
||
io
|
||
la
|
||
lavoro
|
||
le
|
||
lei
|
||
lo
|
||
loro
|
||
lui
|
||
lungo
|
||
ma
|
||
me
|
||
meglio
|
||
molta
|
||
molti
|
||
molto
|
||
nei
|
||
nella
|
||
no
|
||
noi
|
||
nome
|
||
nostro
|
||
nove
|
||
nuovi
|
||
nuovo
|
||
o
|
||
oltre
|
||
ora
|
||
otto
|
||
peggio
|
||
pero
|
||
persone
|
||
più [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Japanese">
|
||
<summary>
|
||
Looks up a localized string similar to これ
|
||
それ
|
||
あれ
|
||
この
|
||
その
|
||
あの
|
||
ここ
|
||
そこ
|
||
あそこ
|
||
こちら
|
||
どこ
|
||
だれ
|
||
なに
|
||
なん
|
||
何
|
||
私
|
||
貴方
|
||
貴方方
|
||
我々
|
||
私達
|
||
あの人
|
||
あのかた
|
||
彼女
|
||
彼
|
||
です
|
||
あります
|
||
おります
|
||
います
|
||
は
|
||
が
|
||
の
|
||
に
|
||
を
|
||
で
|
||
え
|
||
から
|
||
まで
|
||
より
|
||
も
|
||
どの
|
||
と
|
||
し
|
||
それで
|
||
しかし
|
||
.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Norwegian_Bokmal">
|
||
<summary>
|
||
Looks up a localized string similar to alle
|
||
andre
|
||
arbeid
|
||
av
|
||
begge
|
||
bort
|
||
bra
|
||
bruke
|
||
da
|
||
denne
|
||
der
|
||
deres
|
||
det
|
||
din
|
||
disse
|
||
du
|
||
eller
|
||
en
|
||
ene
|
||
eneste
|
||
enhver
|
||
enn
|
||
er
|
||
et
|
||
folk
|
||
for
|
||
fordi
|
||
forsøke
|
||
fra
|
||
få
|
||
før
|
||
først
|
||
gjorde
|
||
gjøre
|
||
god
|
||
gå
|
||
ha
|
||
hadde
|
||
han
|
||
hans
|
||
hennes
|
||
her
|
||
hva
|
||
hvem
|
||
hver
|
||
hvilken
|
||
hvis
|
||
hvor
|
||
hvordan
|
||
hvorfor
|
||
i
|
||
ikke
|
||
inn
|
||
innen
|
||
kan
|
||
kunne
|
||
lage
|
||
lang
|
||
lik
|
||
like
|
||
makt
|
||
mange
|
||
med
|
||
meg
|
||
meget
|
||
men
|
||
mens
|
||
mer
|
||
mest
|
||
min
|
||
mye
|
||
må
|
||
måte
|
||
navn
|
||
nei
|
||
ny
|
||
nå
|
||
når
|
||
og
|
||
også
|
||
om
|
||
opp
|
||
oss
|
||
over
|
||
part
|
||
punkt
|
||
på
|
||
rett
|
||
rikti [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Polish">
|
||
<summary>
|
||
Looks up a localized string similar to ach
|
||
aj
|
||
albo
|
||
bardzo
|
||
bez
|
||
bo
|
||
być
|
||
ci
|
||
ciebie
|
||
cię
|
||
co
|
||
czy
|
||
daleko
|
||
dla
|
||
dlaczego
|
||
dlatego
|
||
do
|
||
dobrze
|
||
dokąd
|
||
dość
|
||
dużo
|
||
dwa
|
||
dwaj
|
||
dwie
|
||
dwoje
|
||
dzisiaj
|
||
dziś
|
||
gdyby
|
||
gdzie
|
||
go
|
||
ich
|
||
ile
|
||
im
|
||
inny
|
||
ja
|
||
jak
|
||
jakby
|
||
jaki
|
||
je
|
||
jeden
|
||
jedna
|
||
jedno
|
||
jego
|
||
jej
|
||
jemu
|
||
jest
|
||
jestem
|
||
jeśli
|
||
jeżeli
|
||
już
|
||
ją
|
||
każdy
|
||
kiedy
|
||
kierunku
|
||
kto
|
||
ku
|
||
lub
|
||
ma
|
||
mają
|
||
mam
|
||
mi
|
||
mnie
|
||
mną
|
||
moi
|
||
moja
|
||
moje
|
||
może
|
||
mu
|
||
my
|
||
mój
|
||
na
|
||
nam
|
||
nami
|
||
nas
|
||
nasi
|
||
nasz
|
||
nasza
|
||
nasze
|
||
natychmiast
|
||
nic
|
||
nich
|
||
nie
|
||
niego
|
||
niej
|
||
niemu
|
||
nigdy
|
||
n [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Portuguese">
|
||
<summary>
|
||
Looks up a localized string similar to último
|
||
é
|
||
acerca
|
||
agora
|
||
algumas
|
||
alguns
|
||
ali
|
||
ambos
|
||
antes
|
||
apontar
|
||
aquela
|
||
aquelas
|
||
aquele
|
||
aqueles
|
||
aqui
|
||
atrás
|
||
bem
|
||
bom
|
||
cada
|
||
caminho
|
||
cima
|
||
com
|
||
como
|
||
comprido
|
||
conhecido
|
||
corrente
|
||
das
|
||
debaixo
|
||
dentro
|
||
desde
|
||
desligado
|
||
deve
|
||
devem
|
||
deverá
|
||
direita
|
||
diz
|
||
dizer
|
||
dois
|
||
dos
|
||
e
|
||
ela
|
||
ele
|
||
eles
|
||
em
|
||
enquanto
|
||
então
|
||
está
|
||
estão
|
||
estado
|
||
estar
|
||
estará
|
||
este
|
||
estes
|
||
esteve
|
||
estive
|
||
estivemos
|
||
estiveram
|
||
eu
|
||
fará
|
||
faz
|
||
fazer
|
||
fazia
|
||
fez
|
||
fim
|
||
foi
|
||
fora
|
||
horas
|
||
iniciar
|
||
inicio
|
||
ir
|
||
irá
|
||
isto
|
||
ligado
|
||
maio [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Portuguese_Brazilian">
|
||
<summary>
|
||
Looks up a localized string similar to último
|
||
é
|
||
acerca
|
||
agora
|
||
algumas
|
||
alguns
|
||
ali
|
||
ambos
|
||
antes
|
||
apontar
|
||
aquela
|
||
aquelas
|
||
aquele
|
||
aqueles
|
||
aqui
|
||
atrás
|
||
bem
|
||
bom
|
||
cada
|
||
caminho
|
||
cima
|
||
com
|
||
como
|
||
comprido
|
||
conhecido
|
||
corrente
|
||
das
|
||
debaixo
|
||
dentro
|
||
desde
|
||
desligado
|
||
deve
|
||
devem
|
||
deverá
|
||
direita
|
||
diz
|
||
dizer
|
||
dois
|
||
dos
|
||
e
|
||
ela
|
||
ele
|
||
eles
|
||
em
|
||
enquanto
|
||
então
|
||
está
|
||
estão
|
||
estado
|
||
estar
|
||
estará
|
||
este
|
||
estes
|
||
esteve
|
||
estive
|
||
estivemos
|
||
estiveram
|
||
eu
|
||
fará
|
||
faz
|
||
fazer
|
||
fazia
|
||
fez
|
||
fim
|
||
foi
|
||
fora
|
||
horas
|
||
iniciar
|
||
inicio
|
||
ir
|
||
irá
|
||
isto
|
||
ligado
|
||
maio [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Russian">
|
||
<summary>
|
||
Looks up a localized string similar to а
|
||
е
|
||
и
|
||
ж
|
||
м
|
||
о
|
||
на
|
||
не
|
||
ни
|
||
об
|
||
но
|
||
он
|
||
мне
|
||
мои
|
||
мож
|
||
она
|
||
они
|
||
оно
|
||
мной
|
||
много
|
||
многочисленное
|
||
многочисленная
|
||
многочисленные
|
||
многочисленный
|
||
мною
|
||
мой
|
||
мог
|
||
могут
|
||
можно
|
||
может
|
||
можхо
|
||
мор
|
||
моя
|
||
моё
|
||
мочь
|
||
над
|
||
нее
|
||
оба
|
||
нам
|
||
нем
|
||
нами
|
||
ними
|
||
мимо
|
||
немного
|
||
одной
|
||
одного
|
||
менее
|
||
однажды
|
||
однако
|
||
меня
|
||
нему
|
||
меньше
|
||
ней
|
||
наверху
|
||
него
|
||
ниже
|
||
мало
|
||
надо
|
||
один
|
||
одиннадцать
|
||
одиннадцатый
|
||
назад
|
||
наиболее
|
||
недавно
|
||
миллионов
|
||
недалеко
|
||
между
|
||
низко
|
||
меля
|
||
нельзя
|
||
нибудь
|
||
непрерывно
|
||
наконец
|
||
никогда
|
||
ник [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Spanish">
|
||
<summary>
|
||
Looks up a localized string similar to ésa
|
||
ésta
|
||
éste
|
||
última
|
||
últimas
|
||
último
|
||
últimos
|
||
aún
|
||
a
|
||
la
|
||
vez
|
||
a.m.
|
||
abierto
|
||
abunda
|
||
acaba
|
||
además
|
||
ahora
|
||
al
|
||
algún
|
||
alguna
|
||
alguno
|
||
alrededor
|
||
alta
|
||
altas
|
||
alto
|
||
altos
|
||
am
|
||
ambas
|
||
ambos
|
||
antes
|
||
aquél
|
||
aquélla
|
||
aquí
|
||
aquel
|
||
aquella
|
||
aquellas
|
||
aquello
|
||
aquellos
|
||
así
|
||
atardecer
|
||
aunque
|
||
básicamente
|
||
b
|
||
c
|
||
cada
|
||
casi
|
||
celebran
|
||
centro
|
||
cercanía
|
||
cierta
|
||
ciertas
|
||
cierto
|
||
ciertos
|
||
común
|
||
comúnmente
|
||
como
|
||
complemento
|
||
complementos
|
||
completamente
|
||
comunes
|
||
con
|
||
conforme
|
||
considerable
|
||
considerada
|
||
consider [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.Properties.Resources.Swedish">
|
||
<summary>
|
||
Looks up a localized string similar to aderton
|
||
adertonde
|
||
adjö
|
||
aldrig
|
||
alla
|
||
allas
|
||
allt
|
||
alltid
|
||
alltså
|
||
än
|
||
andra
|
||
andras
|
||
annan
|
||
annat
|
||
ännu
|
||
artonde
|
||
arton
|
||
åtminstone
|
||
att
|
||
åtta
|
||
åttio
|
||
åttionde
|
||
åttonde
|
||
av
|
||
även
|
||
båda
|
||
bådas
|
||
bakom
|
||
bara
|
||
bäst
|
||
bättre
|
||
behöva
|
||
behövas
|
||
behövde
|
||
behövt
|
||
beslut
|
||
beslutat
|
||
beslutit
|
||
bland
|
||
blev
|
||
bli
|
||
blir
|
||
blivit
|
||
bort
|
||
borta
|
||
bra
|
||
då
|
||
dag
|
||
dagar
|
||
dagarna
|
||
dagen
|
||
där
|
||
därför
|
||
de
|
||
del
|
||
delen
|
||
dem
|
||
den
|
||
deras
|
||
dess
|
||
det
|
||
detta
|
||
dig
|
||
din
|
||
dina
|
||
dit
|
||
ditt
|
||
dock
|
||
du
|
||
efter
|
||
eftersom
|
||
elfte
|
||
eller
|
||
elva
|
||
en
|
||
enk [rest of string was truncated]";.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.ApproximatedKernelTransformer">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting an <see cref="T:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator">
|
||
<summary>
|
||
Maps vector columns to a low -dimensional feature space.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><
|
||
by Rahimi and Recht.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.KernelExpansionCatalog.ApproximatedKernelMap(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Int32,System.Boolean,Microsoft.ML.Transforms.KernelBase,System.Nullable{System.Int32})"/>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions">
|
||
<summary>
|
||
Describes how the transformer handles one Gcn column pair.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions.Name">
|
||
<summary>
|
||
Name of the column resulting from the transformation of <see cref="F:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions.InputColumnName"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions.InputColumnName">
|
||
<summary>
|
||
Name of the column to transform.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions.Generator">
|
||
<summary>
|
||
Which fourier generator to use.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions.Rank">
|
||
<summary>
|
||
The number of random Fourier features to create.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions.UseCosAndSinBases">
|
||
<summary>
|
||
If <see langword="true"/>, use both of cos and sin basis functions to create two features for every random Fourier frequency.
|
||
Otherwise, only cos bases would be used.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions.Seed">
|
||
<summary>
|
||
The seed of the random number generator for generating the new features (if unspecified, the global random is used).
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions.#ctor(System.String,System.Int32,System.Boolean,System.String,Microsoft.ML.Transforms.KernelBase,System.Nullable{System.Int32})">
|
||
<summary>
|
||
Describes how the transformer handles one column pair.
|
||
</summary>
|
||
<param name="name">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="rank">The number of random Fourier features to create.</param>
|
||
<param name="useCosAndSinBases">If <see langword="true"/>, use both of cos and sin basis functions to create two features for
|
||
every random Fourier frequency. Otherwise, only cos bases would be used.</param>
|
||
<param name="inputColumnName">Name of column to transform. </param>
|
||
<param name="generator">Which fourier generator to use.</param>
|
||
<param name="seed">The seed of the random number generator for generating the new features (if unspecified, the global random is used).</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.String,System.String,System.Int32,System.Boolean)">
|
||
<summary>
|
||
Convinence constructor for simple one column case.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="rank">The number of random Fourier features to create.</param>
|
||
<param name="useCosAndSinBases">Create two features for every random Fourier frequency? (one for cos and one for sin).</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.Fit(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Trains and returns a <see cref="T:Microsoft.ML.Transforms.ApproximatedKernelTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.StatefulCustomMappingTransformer`3">
|
||
<summary>
|
||
<see cref="T:Microsoft.ML.ITransformer"/> resulting from fitting an <see cref="T:Microsoft.ML.Transforms.StatefulCustomMappingEstimator`3"/>.
|
||
</summary>
|
||
<typeparam name="TSrc">The class defining which columns to take from the incoming data.</typeparam>
|
||
<typeparam name="TDst">The class defining which new columns are added to the data.</typeparam>
|
||
<typeparam name="TState">The type that describes per-cursor state.</typeparam>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.StatefulCustomMappingTransformer`3.Microsoft#ML#ITransformer#IsRowToRowMapper">
|
||
<summary>
|
||
Whether a call to <see cref="M:Microsoft.ML.ITransformer.GetRowToRowMapper(Microsoft.ML.DataViewSchema)"/> should succeed, on an
|
||
appropriate schema.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulCustomMappingTransformer`3.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.Action{`0,`1,`2},System.String,System.Action{`2})">
|
||
<summary>
|
||
Create a custom mapping of input columns to output columns.
|
||
</summary>
|
||
<param name="env">The host environment</param>
|
||
<param name="mapAction">The action by which we map source to destination columns</param>
|
||
<param name="contractName">The name of the action (will be saved to the model).</param>
|
||
<param name="stateInitAction">The action to initialize the state object, that is called once before the cursor is initialized.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulCustomMappingTransformer`3.GetOutputSchema(Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.DataViewSchema"/> which would be produced by the transformer applied to
|
||
an input data with schema <paramref name="inputSchema"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulCustomMappingTransformer`3.Transform(Microsoft.ML.IDataView)">
|
||
<summary>
|
||
Take the data in, make transformations, output the data.
|
||
Note that <see cref="T:Microsoft.ML.IDataView"/>'s are lazy, so no actual transformations happen here, just schema validation.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulCustomMappingTransformer`3.Microsoft#ML#ITransformer#GetRowToRowMapper(Microsoft.ML.DataViewSchema)">
|
||
<summary>
|
||
Constructs a row-to-row mapper based on an input schema. If <see cref="P:Microsoft.ML.ITransformer.IsRowToRowMapper"/>
|
||
is <c>false</c>, then an exception is thrown. If the <paramref name="inputSchema"/> is in any way
|
||
unsuitable for constructing the mapper, an exception is likewise thrown.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.StatefulCustomMappingEstimator`3">
|
||
<summary>
|
||
Applies a custom mapping function to the specified input columns, while allowing a per-cursor state. The result will be in output columns.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
|
||
### Estimator Characteristics
|
||
| | |
|
||
| -- | -- |
|
||
| Does this estimator need to look at the data to train its parameters? | No |
|
||
| Input column data type | Any |
|
||
| Output column data type | Any |
|
||
| Exportable to ONNX | No |
|
||
|
||
The resulting <xref:Microsoft.ML.Transforms.StatefulCustomMappingTransformer`3> applies a user defined mapping
|
||
to one or more input columns and produces one or more output columns. This transformation doesn't change the number of rows,
|
||
and can be seen as the result of applying the user's function to every row of the input data.
|
||
|
||
In addition to the input and output objects, the provided custom function is given a state object that it can look at and/or modify.
|
||
|
||
Check the See Also section for links to usage examples.
|
||
]]></format>
|
||
</remarks>
|
||
<seealso cref="M:Microsoft.ML.CustomMappingCatalog.StatefulCustomMapping``3(Microsoft.ML.TransformsCatalog,System.Action{``0,``1,``2},System.Action{``2},System.String)"/>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulCustomMappingEstimator`3.#ctor(Microsoft.ML.Runtime.IHostEnvironment,System.Action{`0,`1,`2},System.String,System.Action{`2})">
|
||
<summary>
|
||
Create a custom mapping of input columns to output columns.
|
||
</summary>
|
||
<param name="env">The host environment</param>
|
||
<param name="mapAction">The mapping action. This must be thread-safe and free from side effects.</param>
|
||
<param name="contractName">The contract name, used by ML.NET for loading the model. If <c>null</c> is specified, such a trained model would not be save-able.</param>
|
||
<param name="stateInitAction">The action to initialize the state object, that is called once before the cursor is initialized.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulCustomMappingEstimator`3.GetOutputSchema(Microsoft.ML.SchemaShape)">
|
||
<summary>
|
||
Returns the <see cref="T:Microsoft.ML.SchemaShape"/> of the schema which will be produced by the transformer.
|
||
Used for schema propagation and verification in a pipeline.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.StatefulFilterTransform`3">
|
||
<summary>
|
||
This transform is similar to <see cref="T:Microsoft.ML.Transforms.CustomMappingTransformer`2"/>, but it allows per-cursor state,
|
||
as well as the ability to 'accept' or 'filter out' some rows of the supplied <see cref="T:Microsoft.ML.IDataView"/>.
|
||
The downside is that the provided lambda is eagerly called on every row (not lazily when needed), and
|
||
parallel cursors are not allowed.
|
||
</summary>
|
||
<typeparam name="TSrc">The type that describes what 'source' columns are consumed from the input <see cref="T:Microsoft.ML.IDataView"/>.</typeparam>
|
||
<typeparam name="TDst">The type that describes what new columns are added by this transform.</typeparam>
|
||
<typeparam name="TState">The type that describes per-cursor state.</typeparam>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulFilterTransform`3.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,System.Func{`0,`1,`2,System.Boolean},System.Action{`2},Microsoft.ML.Data.SchemaDefinition,Microsoft.ML.Data.SchemaDefinition)">
|
||
<summary>
|
||
Create a filter transform
|
||
</summary>
|
||
<param name="env">The host environment</param>
|
||
<param name="source">The dataview upon which we construct the transform</param>
|
||
<param name="filterFunc">The function by which we transform source to destination columns and decide whether
|
||
to keep the row.</param>
|
||
<param name="initStateAction">The function that is called once per cursor to initialize state. Can be null.</param>
|
||
<param name="inputSchemaDefinition">The schema definition overrides for <typeparamref name="TSrc"/></param>
|
||
<param name="outputSchemaDefinition">The schema definition overrides for <typeparamref name="TDst"/></param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulFilterTransform`3.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.Transforms.StatefulFilterTransform{`0,`1,`2},Microsoft.ML.IDataView)">
|
||
<summary>
|
||
The 'reapply' constructor.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulFilterTransform`3.Cursor.IsColumnActive(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns whether the given column is active in this row.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.StatefulFilterTransform`3.Cursor.GetGetter``1(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns a value getter delegate to fetch the value of column with the given columnIndex, from the row.
|
||
This throws if the column is not active in this row, or if the type
|
||
<typeparamref name="TValue"/> differs from this column's type.
|
||
</summary>
|
||
<typeparam name="TValue"> is the column's content type.</typeparam>
|
||
<param name="column"> is the output column whose getter should be returned.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.UngroupTransform">
|
||
<summary>
|
||
Un-groups vector columns into sequences of rows, inverse of Group transform.
|
||
</summary><remarks>
|
||
<para>This can be thought of as an inverse of the <see cref="T:Microsoft.ML.Transforms.CombinerByContiguousGroupId" />.
|
||
For all specified vector columns ("pivot" columns), performs the "ungroup" (or "unroll") operation as outlined below.
|
||
</para>
|
||
<para>If the only pivot column is called P, and has size K, then for every row of the input we will produce
|
||
K rows, that are identical in all columns except P. The column P will become a scalar column, and this
|
||
column will hold all the original values of input's P, one value per row, in order. The order of columns
|
||
will remain the same.
|
||
</para>
|
||
<para>Variable-length pivot columns are supported (including zero, which will eliminate the row from the result).</para>
|
||
<para>Multiple pivot columns are also supported:</para>
|
||
<list type="bullet">
|
||
<item><description>A number of output rows is controlled by the 'mode' parameter.
|
||
<list type="bullet">
|
||
<item><term>outer</term><description> it is equal to the maximum length of pivot columns</description></item>
|
||
<item><term>inner</term><description> it is equal to the minimum length of pivot columns</description></item>
|
||
<item><term>first</term><description> it is equal to the length of the first pivot column</description></item>
|
||
</list>
|
||
</description>
|
||
</item>
|
||
<item><description>
|
||
If a particular pivot column has size that is different than the number of output rows, the extra slots will
|
||
be ignored, and the missing slots will be 'padded' with default values.
|
||
</description></item>
|
||
</list>
|
||
<para>All metadata are preserved for the retained columns. For 'unrolled' columns, all known metadata
|
||
except slot names are preserved.
|
||
</para>
|
||
</remarks>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Transforms.UngroupTransform.UngroupMode">
|
||
<summary>
|
||
Controls the number of output rows produced by the <see cref="T:Microsoft.ML.Transforms.UngroupTransform"/> transform
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.UngroupTransform.UngroupMode.Inner">
|
||
<summary>
|
||
The number of output rows is equal to the minimum length of pivot columns
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.UngroupTransform.UngroupMode.Outer">
|
||
<summary>
|
||
The number of output rows is equal to the maximum length of pivot columns
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.UngroupTransform.UngroupMode.First">
|
||
<summary>
|
||
The number of output rows is equal to the length of the first pivot column.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.UngroupTransform.#ctor(Microsoft.ML.Runtime.IHostEnvironment,Microsoft.ML.IDataView,Microsoft.ML.Transforms.UngroupTransform.UngroupMode,System.String[])">
|
||
<summary>
|
||
Initializes a new instance of <see cref="T:Microsoft.ML.Transforms.UngroupTransform"/>.
|
||
</summary>
|
||
<param name="env">Host Environment.</param>
|
||
<param name="input">Input <see cref="T:Microsoft.ML.IDataView"/>. This is the output from previous transform or loader.</param>
|
||
<param name="mode">Specifies how to unroll multiple pivot columns of different size.</param>
|
||
<param name="columns">Columns to unroll, or 'pivot'</param>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._infos">
|
||
<summary>
|
||
Information of columns to be ungrouped in <see cref="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._inputSchema"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._pivotIndex">
|
||
<summary>
|
||
<see cref="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._pivotIndex"/>[i] is -1 means that the i-th column in both of <see cref="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._inputSchema"/> and <see cref="P:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.OutputSchema"/>
|
||
are not produced by ungrouping; we just copy the i-th input column to the i-th output column.
|
||
If <see cref="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._pivotIndex"/>[i] is not -1, the i-th output column should be produced by ungrouping the i-th input column.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.InputColumnCount">
|
||
<summary>
|
||
Columns contained in <see cref="T:Microsoft.ML.IDataView"/> passed in <see cref="T:Microsoft.ML.Transforms.UngroupTransform"/>.
|
||
Note that input data's schema is stored as <see cref="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._inputSchema"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.Mode">
|
||
<summary>
|
||
This attribute specifies how <see cref="T:Microsoft.ML.Transforms.UngroupTransform"/> expanding input columns stored in <see cref="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._infos"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.OutputSchema">
|
||
<summary>
|
||
Output data's <see cref="T:Microsoft.ML.DataViewSchema"/> produced by this <see cref="T:Microsoft.ML.Transforms.UngroupTransform"/>
|
||
when input data's schema is <see cref="F:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding._inputSchema"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.GetActiveInput(System.Func{System.Int32,System.Boolean})">
|
||
<summary>
|
||
Return an array of active input columns given the target predicate.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.IsPivot(System.Int32)">
|
||
<summary>
|
||
Determine if an output column is produced by a pivot column from input.
|
||
</summary>
|
||
<param name="col">Column index in <see cref="P:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.OutputSchema"/></param>
|
||
<returns>True if the specified column is produced by expanding a pivot column and false otherwise.</returns>
|
||
</member>
|
||
<member name="F:Microsoft.ML.Transforms.UngroupTransform.Cursor._active">
|
||
<summary>
|
||
Total number of input columns is <see cref="P:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.InputColumnCount"/> of <see cref="F:Microsoft.ML.Transforms.UngroupTransform.Cursor._ungroupBinding"/>.
|
||
Note that the number of input columns equals to the number of output columns; that is, <see cref="P:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.InputColumnCount"/>
|
||
is identical to the number of columns in <see cref="P:Microsoft.ML.Transforms.UngroupTransform.UngroupBinding.OutputSchema"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.UngroupTransform.Cursor.MakeSizeGetter``1(System.Int32)">
|
||
<summary>
|
||
Create a getter which returns the length of a vector (aka a column's value) in the input data.
|
||
</summary>
|
||
<typeparam name="T">The type of the considered input vector</typeparam>
|
||
<param name="col">Column index, which should point to a vector-typed column in the input data.</param>
|
||
<returns>Getter of the length to the considered input vector.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.UngroupTransform.Cursor.IsColumnActive(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns whether the given column is active in this row.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Transforms.UngroupTransform.Cursor.GetGetter``1(Microsoft.ML.DataViewSchema.Column)">
|
||
<summary>
|
||
Returns the getter of an output column.
|
||
</summary>
|
||
<typeparam name="TValue"> is the output column's content type, for example, <see cref="T:Microsoft.ML.Data.VBuffer`1"/>.</typeparam>
|
||
<param name="column"> is the output column whose getter should be returned.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.ConversionsCatalog">
|
||
<summary>
|
||
Collection of extension methods for <see cref="T:Microsoft.ML.TransformsCatalog"/> to create instances of
|
||
key to binary vector mapping transformer components
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.ConversionsCatalog.MapKeyToBinaryVector(Microsoft.ML.TransformsCatalog.ConversionTransforms,Microsoft.ML.InputOutputColumnPair[])">
|
||
<summary>
|
||
Convert the key types back to binary vector.
|
||
</summary>
|
||
<param name="catalog">The categorical transform's catalog.</param>
|
||
<param name="columns">Specifies the output and input columns on which the transformation should be applied.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.ConversionsCatalog.MapKeyToBinaryVector(Microsoft.ML.TransformsCatalog.ConversionTransforms,System.String,System.String)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.KeyToBinaryVectorMappingEstimator"/>, which converts key types to their corresponding binary representation of the original value.
|
||
</summary>
|
||
<param name="catalog">The categorical transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type is a known-size vector of <see cref="T:System.Single"/> representing the input value.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
The data type is a key or a known-size vector of keys.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="T:Microsoft.ML.CustomMappingCatalog">
|
||
<summary>
|
||
Class containing an extension method for <see cref="T:Microsoft.ML.TransformsCatalog"/> to create instances of
|
||
user-defined one-to-one row mapping transformer components.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CustomMappingCatalog.CustomMapping``2(Microsoft.ML.TransformsCatalog,System.Action{``0,``1},System.String,Microsoft.ML.Data.SchemaDefinition,Microsoft.ML.Data.SchemaDefinition)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.CustomMappingEstimator`2"/>, which applies a custom mapping of input columns to output columns.
|
||
</summary>
|
||
<typeparam name="TSrc">The class defining which columns to take from the incoming data.</typeparam>
|
||
<typeparam name="TDst">The class defining which new columns are added to the data.</typeparam>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="mapAction">The mapping action. This must be thread-safe and free from side effects.
|
||
If the resulting transformer needs to be save-able, the class defining <paramref name="mapAction"/> should implement
|
||
<see cref="T:Microsoft.ML.Transforms.CustomMappingFactory`2"/> and needs to be decorated with
|
||
<see cref="T:Microsoft.ML.Transforms.CustomMappingFactoryAttributeAttribute"/> with the provided <paramref name="contractName"/>.
|
||
In versions v1.5-preview2 and earlier, the assembly containing the class should be registered in the environment where it is loaded back
|
||
using <see cref="M:Microsoft.ML.Runtime.ComponentCatalog.RegisterAssembly(System.Reflection.Assembly,System.Boolean)"/>.</param>
|
||
<param name="contractName">The contract name, used by ML.NET for loading the model.
|
||
If <see langword="null"/> is specified, resulting transformer would not be save-able.</param>
|
||
<param name="inputSchemaDefinition">Additional parameters for schema mapping between <typeparamref name="TSrc"/> and input data.
|
||
Useful when dealing with annotations.</param>
|
||
<param name="outputSchemaDefinition">Additional parameters for schema mapping between <typeparamref name="TDst"/> and output data.
|
||
Useful when dealing with annotations.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
[!code-csharp[CustomMapping](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSaveAndLoad.cs)]
|
||
[!code-csharp[CustomMapping](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingWithInMemoryCustomType.cs)]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CustomMappingCatalog.StatefulCustomMapping``3(Microsoft.ML.TransformsCatalog,System.Action{``0,``1,``2},System.Action{``2},System.String)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.StatefulCustomMappingEstimator`3"/>, which applies a custom mapping of input columns to output columns,
|
||
while allowing a per-cursor state.
|
||
</summary>
|
||
<typeparam name="TSrc">The class defining which columns to take from the incoming data.</typeparam>
|
||
<typeparam name="TState">The type that describes per-cursor state.</typeparam>
|
||
<typeparam name="TDst">The class defining which new columns are added to the data.</typeparam>
|
||
<param name="catalog">The transform catalog.</param>
|
||
<param name="mapAction">The mapping action. In addition to the input and output objects, the action is given a state object that it can look at and/or modify.
|
||
If the resulting transformer needs to be save-able, the class defining <paramref name="mapAction"/> should implement
|
||
<see cref="T:Microsoft.ML.Transforms.StatefulCustomMappingFactory`3"/> and needs to be decorated with
|
||
<see cref="T:Microsoft.ML.Transforms.CustomMappingFactoryAttributeAttribute"/> with the provided <paramref name="contractName"/>.
|
||
The assembly containing the class should be registered in the environment where it is loaded back
|
||
using <see cref="M:Microsoft.ML.Runtime.ComponentCatalog.RegisterAssembly(System.Reflection.Assembly,System.Boolean)"/>.</param>
|
||
<param name="stateInitAction">The action to initialize the state object, that is called once before the cursor is initialized.</param>
|
||
<param name="contractName">The contract name, used by ML.NET for loading the model.
|
||
If <see langword="null"/> is specified, resulting transformer would not be save-able.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CustomMappingCatalog.FilterByCustomPredicate``1(Microsoft.ML.DataOperationsCatalog,Microsoft.ML.IDataView,System.Func{``0,System.Boolean})">
|
||
<summary>
|
||
Drop rows where a specified predicate returns true.
|
||
</summary>
|
||
<typeparam name="TSrc">The class defining which columns to take from the incoming data.</typeparam>
|
||
<param name="catalog">The data operations catalog.</param>
|
||
<param name="input">The input data.</param>
|
||
<param name="filterPredicate">A predicate, that takes an input of type <typeparamref name="TSrc"/> and returns true if the row should be filtered (dropped) and false otherwise.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.CustomMappingCatalog.FilterByStatefulCustomPredicate``2(Microsoft.ML.DataOperationsCatalog,Microsoft.ML.IDataView,System.Func{``0,``1,System.Boolean},System.Action{``1})">
|
||
<summary>
|
||
Drop rows where a specified predicate returns true. This filter allows to maintain a per-cursor state.
|
||
</summary>
|
||
<typeparam name="TSrc">The class defining which columns to take from the incoming data.</typeparam>
|
||
<typeparam name="TState">The type that describes per-cursor state.</typeparam>
|
||
<param name="catalog">The data operations catalog.</param>
|
||
<param name="input">The input data.</param>
|
||
<param name="filterPredicate">A predicate, that takes an input of type <typeparamref name="TSrc"/> and a state object of type
|
||
<typeparamref name="TState"/>, and returns true if the row should be filtered (dropped) and false otherwise.</param>
|
||
<param name="stateInitAction">The action to initialize the state object, that is called once before the cursor is initialized.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.ExpressionCatalog.Expression(Microsoft.ML.TransformsCatalog,System.String,System.String,System.String[])">
|
||
<summary>
|
||
Creates an <see cref="T:Microsoft.ML.Transforms.ExpressionEstimator"/>.
|
||
</summary>
|
||
<param name="catalog">The <see cref="T:Microsoft.ML.TransformsCatalog"/>.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnNames"/>.
|
||
This column's data type will be the same as that of the input column.</param>
|
||
<param name="expression">The expression to apply to <paramref name="inputColumnNames"/> to create the column <paramref name="outputColumnName"/>.</param>
|
||
<param name="inputColumnNames">The names of the input columns.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="T:Microsoft.ML.ExtensionsCatalog">
|
||
<summary>
|
||
Collection of extension methods for <see cref="T:Microsoft.ML.TransformsCatalog"/> to create instances of
|
||
missing value transformer components.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.ExtensionsCatalog.IndicateMissingValues(Microsoft.ML.TransformsCatalog,System.String,System.String)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.MissingValueIndicatorEstimator"/>, which scans the data from the column specified in <paramref name="inputColumnName"/>
|
||
and fills new column specified in <paramref name="outputColumnName"/> with vector of bools where i-th bool has value of <see langword="true"/>
|
||
if i-th element in column data has missing value and <see langword="false"/> otherwise.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a vector of <see cref="T:System.Boolean"/>.</param>
|
||
<param name="inputColumnName">Name of the column to copy the data from.
|
||
This estimator operates over scalar or vector of <see cref="T:System.Single"/> or <see cref="T:System.Double"/>.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.ExtensionsCatalog.IndicateMissingValues(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.MissingValueIndicatorEstimator"/>, which copies the data from the column specified in <see cref="P:Microsoft.ML.InputOutputColumnPair.InputColumnName" />
|
||
to a new column: <see cref="P:Microsoft.ML.InputOutputColumnPair.OutputColumnName" />.
|
||
</summary>
|
||
<remarks>This transform can operate over several columns.</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns">The pairs of input and output columns. This estimator operates over data which is either scalar or vector of <see cref="T:System.Single"/> or <see cref="T:System.Double"/>.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.ExtensionsCatalog.ReplaceMissingValues(Microsoft.ML.TransformsCatalog,System.String,System.String,Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.MissingValueReplacingEstimator"/>, which copies the data from the column specified in <paramref name="inputColumnName"/>
|
||
to a new column: <paramref name="outputColumnName"/> and replaces missing values in it according to <paramref name="replacementMode"/>.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be the same as that of the input column.</param>
|
||
<param name="inputColumnName">Name of the column to copy the data from.
|
||
This estimator operates over scalar or vector of <see cref="T:System.Single"/> or <see cref="T:System.Double"/>.</param>
|
||
<param name="replacementMode">The type of replacement to use as specified in <see cref="T:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode"/></param>
|
||
<param name="imputeBySlot">If true, per-slot imputation of replacement is performed.
|
||
Otherwise, replacement value is imputed for the entire vector column. This setting is ignored for scalars and variable vectors,
|
||
where imputation is always for the entire column.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.ExtensionsCatalog.ReplaceMissingValues(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.ColumnCopyingEstimator"/>, which copies the data from the column specified in <see cref="P:Microsoft.ML.InputOutputColumnPair.InputColumnName" />
|
||
to a new column: <see cref="P:Microsoft.ML.InputOutputColumnPair.OutputColumnName" /> and replaces missing values in it according to <paramref name="replacementMode"/>.
|
||
</summary>
|
||
<remarks>This transform can operate over several columns.</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns">The pairs of input and output columns. This estimator operates over scalar or vector of floats or doubles.</param>
|
||
<param name="replacementMode">The type of replacement to use as specified in <see cref="T:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode"/></param>
|
||
<param name="imputeBySlot">If <see langword="true"/>, per-slot imputation of replacement is performed.
|
||
Otherwise, replacement value is imputed for the entire vector column. This setting is ignored for scalars and variable vectors,
|
||
where imputation is always for the entire column.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]></format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.ExtensionsCatalog.ReplaceMissingValues(Microsoft.ML.TransformsCatalog,Microsoft.ML.Transforms.MissingValueReplacingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Creates a new output column, identical to the input column for everything but the missing values.
|
||
The missing values of the input column, in this new column are replaced with <see cref="F:Microsoft.ML.Transforms.MissingValueReplacingEstimator.ReplacementMode.DefaultValue"/>.
|
||
</summary>
|
||
<param name="catalog">The transform extensions' catalog.</param>
|
||
<param name="columns">The name of the columns to use, and per-column transformation configuraiton.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.FeatureSelectionCatalog">
|
||
<summary>
|
||
Collection of extension methods for <see cref="T:Microsoft.ML.TransformsCatalog"/> to create instances of feature
|
||
selection transformer components.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnMutualInformation(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,System.String,System.String,System.String,System.Int32,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator"/>, which selects the top k slots across all specified columns ordered by their mutual information with the label column.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
|
||
<param name="labelColumnName">The name of the label column.</param>
|
||
<param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
|
||
<param name="numberOfBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnMutualInformation(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,Microsoft.ML.InputOutputColumnPair[],System.String,System.Int32,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.MutualInformationFeatureSelectingEstimator"/>, which selects the top k slots across all specified columns ordered by their mutual information with the label column.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns">Specifies the names of the input columns for the transformation, and their respective output column names.</param>
|
||
<param name="labelColumnName">The name of the label column.</param>
|
||
<param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
|
||
<param name="numberOfBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnCount(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,Microsoft.ML.Transforms.CountFeatureSelectingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.CountFeatureSelectingEstimator"/>, which selects the slots for which the count of non-default values is greater than or equal to a threshold.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns">Describes the parameters of the feature selection process for each column pair.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnCount(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,System.String,System.String,System.Int64)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.CountFeatureSelectingEstimator"/>, which selects the slots for which the count of non-default values is greater than or equal to a threshold.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be the same as the input column's data type.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over vector or scalar of numeric, text or keys data types.</param>
|
||
<param name="count">If the count of non-default values for a slot is greater than or equal to this threshold in the training data, the slot is preserved.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.FeatureSelectionCatalog.SelectFeaturesBasedOnCount(Microsoft.ML.TransformsCatalog.FeatureSelectionTransforms,Microsoft.ML.InputOutputColumnPair[],System.Int64)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.CountFeatureSelectingEstimator"/>, which selects the slots for which the count of non-default values is greater than or equal to a threshold.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns">Specifies the names of the columns on which to apply the transformation.
|
||
This estimator operates over vector or scalar of numeric, text or keys data types.
|
||
The output columns' data types will be the same as the input columns' data types.</param>
|
||
<param name="count">If the count of non-default values for a slot is greater than or equal to this threshold in the training data, the slot is preserved.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="T:Microsoft.ML.KernelExpansionCatalog">
|
||
<summary>
|
||
Collection of extension methods for <see cref="T:Microsoft.ML.TransformsCatalog"/> to create instances of kernel method
|
||
feature engineering transformer components.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.KernelExpansionCatalog.ApproximatedKernelMap(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Int32,System.Boolean,Microsoft.ML.Transforms.KernelBase,System.Nullable{System.Int32})">
|
||
<summary>
|
||
Create an <see cref="T:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator"/> that maps input vectors to a low dimensional
|
||
feature space where inner products approximate a shift-invariant kernel function.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type on this column will be a known-sized vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>,
|
||
the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates on known-sized vector of <see cref="T:System.Single"/> data type.</param>
|
||
<param name="rank">The dimension of the feature space to map the input to.</param>
|
||
<param name="useCosAndSinBases">If <see langword="true"/>, use both of cos and sin basis functions to create
|
||
two features for every random Fourier frequency. Otherwise, only cos bases would be used. Note that if set
|
||
to <see langword="true"/>, the dimension of the output feature space will be 2*<paramref name="rank"/>.</param>
|
||
<param name="generator">The argument that indicates which kernel to use. The two available implementations
|
||
are <see cref="T:Microsoft.ML.Transforms.GaussianKernel"/> and <see cref="T:Microsoft.ML.Transforms.LaplacianKernel"/>.</param>
|
||
<param name="seed">The seed of the random number generator for generating the new features (if unspecified, the global random is used).</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.KernelExpansionCatalog.ApproximatedKernelMap(Microsoft.ML.TransformsCatalog,Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Create an <see cref="T:Microsoft.ML.Transforms.ApproximatedKernelMappingEstimator"/> that maps input vectors to a low dimensional
|
||
feature space where inner products approximate a shift-invariant kernel function.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns">The input columns to use for the transformation.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.MetricStatistics">
|
||
<summary>
|
||
The MetricsStatistics class computes summary statistics over multiple observations of a metric.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MetricStatistics.Mean">
|
||
<summary>
|
||
Get the mean value for the metric.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MetricStatistics.StandardDeviation">
|
||
<summary>
|
||
Get the standard deviation for the metric.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MetricStatistics.StandardError">
|
||
<summary>
|
||
Get the standard error of the mean for the metric.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MetricStatistics.Count">
|
||
<summary>
|
||
Get the count for the number of samples used. Useful for interpreting
|
||
the standard deviation and the standard error and building confidence intervals.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.MetricStatistics.Add(System.Double)">
|
||
<summary>
|
||
Add another metric to the set of observations.
|
||
</summary>
|
||
<param name="metric">The metric being accumulated</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.IMetricsStatistics`1">
|
||
<summary>
|
||
This interface handles the accumulation of summary statistics over multiple observations of
|
||
evaluation metrics.
|
||
</summary>
|
||
<typeparam name="T">The metric results type, such as <see cref="T:Microsoft.ML.Data.RegressionMetrics"/>.</typeparam>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.RegressionMetricsStatistics">
|
||
<summary>
|
||
The <see cref="T:Microsoft.ML.Data.RegressionMetricsStatistics"/> class holds summary
|
||
statistics over multiple observations of <see cref="T:Microsoft.ML.Data.RegressionMetrics"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.RegressionMetricsStatistics.MeanAbsoluteError">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.RegressionMetrics.MeanAbsoluteError"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.RegressionMetricsStatistics.MeanSquaredError">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.RegressionMetrics.MeanSquaredError"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.RegressionMetricsStatistics.RootMeanSquaredError">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.RegressionMetrics.RootMeanSquaredError"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.RegressionMetricsStatistics.LossFunction">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.RegressionMetrics.LossFunction"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.RegressionMetricsStatistics.RSquared">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.RegressionMetrics.RSquared"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.RegressionMetricsStatistics.Microsoft#ML#Data#IMetricsStatistics{Microsoft#ML#Data#RegressionMetrics}#Add(Microsoft.ML.Data.RegressionMetrics)">
|
||
<summary>
|
||
Add a set of evaluation metrics to the set of observations.
|
||
</summary>
|
||
<param name="metrics">The observed regression evaluation metric</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.BinaryClassificationMetricsStatistics">
|
||
<summary>
|
||
The <see cref="T:Microsoft.ML.Data.BinaryClassificationMetricsStatistics"/> class holds summary
|
||
statistics over multiple observations of <see cref="T:Microsoft.ML.Data.BinaryClassificationMetrics"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.AreaUnderRocCurve">
|
||
<summary>
|
||
Summary Statistics for <see cref="P:Microsoft.ML.Data.BinaryClassificationMetrics.AreaUnderRocCurve"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.Accuracy">
|
||
<summary>
|
||
Summary Statistics for <see cref="P:Microsoft.ML.Data.BinaryClassificationMetrics.Accuracy"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.PositivePrecision">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.BinaryClassificationMetrics.PositivePrecision"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.PositiveRecall">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.BinaryClassificationMetrics.PositiveRecall"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.NegativePrecision">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.BinaryClassificationMetrics.NegativePrecision"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.NegativeRecall">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.BinaryClassificationMetrics.NegativeRecall"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.F1Score">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.BinaryClassificationMetrics.F1Score"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.AreaUnderPrecisionRecallCurve">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.BinaryClassificationMetrics.AreaUnderPrecisionRecallCurve"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.BinaryClassificationMetricsStatistics.Microsoft#ML#Data#IMetricsStatistics{Microsoft#ML#Data#BinaryClassificationMetrics}#Add(Microsoft.ML.Data.BinaryClassificationMetrics)">
|
||
<summary>
|
||
Add a set of evaluation metrics to the set of observations.
|
||
</summary>
|
||
<param name="metrics">The observed binary classification evaluation metric</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics">
|
||
<summary>
|
||
The <see cref="T:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics"/> class holds summary
|
||
statistics over multiple observations of <see cref="T:Microsoft.ML.Data.MulticlassClassificationMetrics"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics.MacroAccuracy">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.MulticlassClassificationMetrics.MacroAccuracy"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics.MicroAccuracy">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.MulticlassClassificationMetrics.MicroAccuracy"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics.LogLoss">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.MulticlassClassificationMetrics.LogLoss"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics.LogLossReduction">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.MulticlassClassificationMetrics.LogLossReduction"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics.TopKAccuracy">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.MulticlassClassificationMetrics.TopKAccuracy"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics.PerClassLogLoss">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.MulticlassClassificationMetrics.PerClassLogLoss"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.MulticlassClassificationMetricsStatistics.Microsoft#ML#Data#IMetricsStatistics{Microsoft#ML#Data#MulticlassClassificationMetrics}#Add(Microsoft.ML.Data.MulticlassClassificationMetrics)">
|
||
<summary>
|
||
Add a set of evaluation metrics to the set of observations.
|
||
</summary>
|
||
<param name="metrics">The observed binary classification evaluation metric</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.RankingMetricsStatistics">
|
||
<summary>
|
||
The <see cref="T:Microsoft.ML.Data.RankingMetricsStatistics"/> class holds summary
|
||
statistics over multiple observations of <see cref="T:Microsoft.ML.Data.RankingMetrics"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.RankingMetricsStatistics.DiscountedCumulativeGains">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.RankingMetrics.DiscountedCumulativeGains"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="P:Microsoft.ML.Data.RankingMetricsStatistics.NormalizedDiscountedCumulativeGains">
|
||
<summary>
|
||
Summary statistics for <see cref="P:Microsoft.ML.Data.RankingMetrics.NormalizedDiscountedCumulativeGains"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.RankingMetricsStatistics.Microsoft#ML#Data#IMetricsStatistics{Microsoft#ML#Data#RankingMetrics}#Add(Microsoft.ML.Data.RankingMetrics)">
|
||
<summary>
|
||
Add a set of evaluation metrics to the set of observations.
|
||
</summary>
|
||
<param name="metrics">The observed regression evaluation metric</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.SvmLightLoader">
|
||
<summary>
|
||
This attempts to reads data in a format close to the SVM-light format, the goal being
|
||
that the majority of SVM-light formatted data should be interpretable by this loader.
|
||
</summary>
|
||
<remarks>
|
||
<format type="text/markdown"><![CDATA[
|
||
The loader may also be different than SVM-light's parsing behavior, in the following
|
||
general ways:
|
||
|
||
1. As an <xref:Microsoft.ML.IDataView>, vectors are required to have a logical length,
|
||
and for practical reasons it's helpful if the output of this loader has a fixed
|
||
length vector type, since few estimators and no basic trainer estimators accept features
|
||
of a variable length vector types. SVM-light had no such concept.
|
||
2. The <xref:Microsoft.ML.IDataView> idiom has different behavior w.r.t. parse errors.
|
||
3. The SVM-light has some restrictions in its format that are unnatural to attempt
|
||
to restrict in the concept of this loader.
|
||
4. Some common "extensions" of this format that have happened over the years are
|
||
accommodated where sensible, often supported by specifying some options.
|
||
|
||
The SVM-light format can be summarized here. An SVM-light file can lead with any number
|
||
of lines starting with '#'. These are discarded.
|
||
{label} {key}:{value} {key}:{value} ... {key}:{value}[#{comment}]
|
||
|
||
Lines are not whitespace trimmed, though whitespace within the line, prior to the #
|
||
comment character (if any) are ignored. SVM-light itself uses the standard C "isspace"
|
||
function, while we respect only space and tab as whitespace. So, the spaces in the
|
||
line above could be, say, tabs, and there could even be multiple of them in sequence.
|
||
Unlike the text loader's format, for instance, there is no concept of a "blank" field
|
||
having any status.
|
||
|
||
The feature vector is specified through a series of key/value pairs. SVM-light
|
||
requires that the keys be positive, increasing integers, except for three special keys:
|
||
cost (we interpret as Weight), qid (we interpret as GroupId) and sid (we ignore these,
|
||
but might present them as a column in the future if any of our learners implement anything
|
||
resembling slack id). The value for 'cost' is float, 'qid' is a long, and 'sid' is a long
|
||
that must be positive. If these keys are specified multiple times, the last one wins.
|
||
|
||
SVM-light, if the tail of the value is not interpretable as a number, will ignore the tail.
|
||
E.g., "5:3.14hello" will be interpreted the same as "5:3.14". This loader does not support
|
||
this syntax.
|
||
|
||
We do not retain the restriction on keys needing to be increasing values in our loader,
|
||
due to the way we compose our feature vectors, but it will be most efficient if this policy
|
||
is still followed. If it is followed a sort will not be required.
|
||
|
||
This loader has the special option to read raw text for the keys and convert to feature
|
||
indices, retaining the text key values as feature names for the resulting feature vector.
|
||
The intent of this is to allow string keys, a common variant of the format, but one
|
||
emphatically not allowed by the original format.
|
||
]]></format>
|
||
</remarks>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.SvmLightLoader.Input">
|
||
<summary>
|
||
This class is used as input for the <see cref="T:Microsoft.ML.Transforms.CustomMappingTransformer`2"/> mapping the input as a line of text.
|
||
It is used by two custom mappers: one that maps the text to a float value indicating whether the line of text is a comment
|
||
and the other maps the text to an object of type <see cref="T:Microsoft.ML.Data.SvmLightLoader.IntermediateInput"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.SvmLightLoader.InputMapper">
|
||
<summary>
|
||
This class contains the mapper that maps an <see cref="T:Microsoft.ML.Data.SvmLightLoader.Input"/> to an <see cref="T:Microsoft.ML.Data.SvmLightLoader.IntermediateInput"/>.
|
||
The mapper parses the label and weight into floats, the group ID into ulong, the comment into a <see cref="T:System.ReadOnlyMemory`1"/> of <see cref="T:System.Char"/>,
|
||
the feature values into a vector of floats and the feature indices/names into a vector of <see cref="T:System.ReadOnlyMemory`1"/> of <see cref="T:System.Char"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.SvmLightLoader.Indices">
|
||
<summary>
|
||
This class is used for mapping the vector of <see cref="T:System.ReadOnlyMemory`1"/> of <see cref="T:System.Char"/> field in an <see cref="T:Microsoft.ML.Data.SvmLightLoader.IntermediateInput"/> object
|
||
to a numeric vector of indices. This class is used in case the indices in the input file are numeric. For the case where the input file contains
|
||
feature names, instead of a <see cref="T:Microsoft.ML.Transforms.CustomMappingTransformer`2"/>, we use a <see cref="T:Microsoft.ML.Transforms.ValueToKeyMappingTransformer"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.SvmLightLoader.IntermediateOut">
|
||
<summary>
|
||
This class is used by the <see cref="T:Microsoft.ML.Transforms.CustomMappingTransformer`2"/>
|
||
that maps a vector of indices and a vector of values into a single <see cref="T:Microsoft.ML.Data.VBuffer`1"/> of values.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.SvmLightLoader.OutputMapper">
|
||
<summary>
|
||
This class contains the mapper that maps an an <see cref="T:Microsoft.ML.Data.SvmLightLoader.IntermediateOut"/>
|
||
to an <see cref="T:Microsoft.ML.Data.SvmLightLoader.Output"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.SvmLightLoader.TextDataView">
|
||
<summary>
|
||
This class creates an <see cref="T:Microsoft.ML.IDataView"/> from an <see cref="T:Microsoft.ML.Data.IMultiStreamSource"/>, that has a single text column
|
||
called "Text".
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.SvmLightLoaderSaverCatalog.CreateSvmLightLoader(Microsoft.ML.DataOperationsCatalog,System.Nullable{System.Int64},System.Int32,System.Boolean,Microsoft.ML.Data.IMultiStreamSource)">
|
||
<summary>
|
||
Creates a loader that loads SVM-light format files. <see cref="T:Microsoft.ML.Data.SvmLightLoader"/>.
|
||
</summary>
|
||
<param name="catalog">The <see cref="T:Microsoft.ML.DataOperationsCatalog"/> catalog.</param>
|
||
<param name="inputSize">The number of features in the Features column. If 0 is specified, the
|
||
loader will determine it by looking at the file sample given in <paramref name="dataSample"/>.</param>
|
||
<param name="numberOfRows">The number of rows from the sample to be used for determining the number of features.</param>
|
||
<param name="zeroBased">If the file contains zero-based indices, this parameter should be set to true. If they are one-based
|
||
it should be set to false.</param>
|
||
<param name="dataSample">A data sample to be used for determining the number of features in the Features column.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.SvmLightLoaderSaverCatalog.CreateSvmLightLoaderWithFeatureNames(Microsoft.ML.DataOperationsCatalog,System.Nullable{System.Int64},Microsoft.ML.Data.IMultiStreamSource)">
|
||
<summary>
|
||
Creates a loader that loads SVM-light like files, where features are specified by their names.
|
||
</summary>
|
||
<param name="catalog">The <see cref="T:Microsoft.ML.DataOperationsCatalog"/> catalog.</param>
|
||
<param name="numberOfRows">The number of rows from the sample to be used for determining the set of feature names.</param>
|
||
<param name="dataSample">A data sample to be used for determining the set of features names.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.SvmLightLoaderSaverCatalog.LoadFromSvmLightFile(Microsoft.ML.DataOperationsCatalog,System.String,System.Nullable{System.Int64},System.Int32,System.Boolean)">
|
||
<summary>
|
||
Load a <see cref="T:Microsoft.ML.IDataView"/> from a text file using <see cref="T:Microsoft.ML.Data.SvmLightLoader"/>.
|
||
</summary>
|
||
<param name="catalog">The <see cref="T:Microsoft.ML.DataOperationsCatalog"/> catalog.</param>
|
||
<param name="path">The path to the file.</param>
|
||
<param name="inputSize">The number of features in the Features column. If 0 is specified, the
|
||
loader will determine it by looking at the file given in <paramref name="path"/>.</param>
|
||
<param name="zeroBased">If the file contains zero-based indices, this parameter should be set to true. If they are one-based
|
||
it should be set to false.</param>
|
||
<param name="numberOfRows">The number of rows from the sample to be used for determining the number of features.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.SvmLightLoaderSaverCatalog.LoadFromSvmLightFileWithFeatureNames(Microsoft.ML.DataOperationsCatalog,System.String,System.Nullable{System.Int64})">
|
||
<summary>
|
||
Load a <see cref="T:Microsoft.ML.IDataView"/> from a text file containing features specified by feature names,
|
||
using <see cref="T:Microsoft.ML.Data.SvmLightLoader"/>.
|
||
</summary>
|
||
<param name="catalog">The <see cref="T:Microsoft.ML.DataOperationsCatalog"/> catalog.</param>
|
||
<param name="path">The path to the file.</param>
|
||
<param name="numberOfRows">The number of rows from the sample to be used for determining the set of feature names.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.Data.SvmLightLoaderSaverCatalog.SaveInSvmLightFormat(Microsoft.ML.DataOperationsCatalog,Microsoft.ML.IDataView,System.IO.Stream,System.Boolean,System.Boolean,System.String,System.String,System.String,System.String)">
|
||
<summary>
|
||
Save the <see cref="T:Microsoft.ML.IDataView"/> in SVM-light format. Four columns can be saved: a label and a features column,
|
||
and optionally a group ID column and an example weight column.
|
||
</summary>
|
||
<param name="catalog">The <see cref="T:Microsoft.ML.DataOperationsCatalog"/> catalog.</param>
|
||
<param name="data">The data view to save.</param>
|
||
<param name="stream">The stream to write to.</param>
|
||
<param name="zeroBasedIndexing">Whether to index the features starting at 0 or at 1.</param>
|
||
<param name="binaryLabel">If set to true, saves 1 for positive labels, -1 for non-positive labels and 0 for NaN.
|
||
Otherwise, saves the value of the label in the data view.</param>
|
||
<param name="labelColumnName">The name of the column to be saved as the label column.</param>
|
||
<param name="featureColumnName">The name of the column to be saved as the features column.</param>
|
||
<param name="rowGroupColumnName">The name of the column to be saved as the group ID column. If null, a group ID column
|
||
will not be saved.</param>
|
||
<param name="exampleWeightColumnName">The name of the column to be saved as the weight column. If null, a weight column
|
||
will not be saved.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.SvmLightSaver">
|
||
<summary>
|
||
The SVM-light saver is a saver class that is capable of saving the label,
|
||
features, group ID and weight columns of a dataset in SVM-light format. It is a bit
|
||
idiosyncratic in that unlike <see cref="T:Microsoft.ML.Data.IO.TextSaver"/> and <see cref="T:Microsoft.ML.Data.IO.BinarySaver"/>, there is no
|
||
attempt to save all columns, just those specific columns, with other columns being dropped on
|
||
the floor.
|
||
</summary>
|
||
</member>
|
||
<member name="T:Microsoft.ML.Data.NgramIdFinder">
|
||
<summary>
|
||
This delegate represents a function that gets an n-gram as input, and outputs the id of
|
||
the n-gram and whether or not to continue processing n-grams.
|
||
</summary>
|
||
<param name="ngram">The array containing the n-gram</param>
|
||
<param name="lim">The n-gram is stored in ngram[0],...ngram[lim-1].</param>
|
||
<param name="icol">The index of the column the transform is applied to.</param>
|
||
<param name="more">True if processing should continue, false if it should stop.
|
||
It is true on input, so only needs to be set to false.</param>
|
||
<returns>The n-gram slot if it was found, -1 otherwise.</returns>
|
||
</member>
|
||
<member name="T:Microsoft.ML.NormalizationCatalog">
|
||
<summary>
|
||
Collection of extension methods for <see cref="T:Microsoft.ML.TransformsCatalog"/> to create instances of numerical
|
||
normalization components.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.Normalize(Microsoft.ML.TransformsCatalog,Microsoft.ML.Transforms.NormalizingEstimator.NormalizationMode,Microsoft.ML.InputOutputColumnPair[])">
|
||
<summary>
|
||
Normalize (rescale) several columns according to the specified <paramref name="mode"/>.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="mode">The <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator.NormalizationMode"/> used to map the old values to the new ones. </param>
|
||
<param name="columns">The pairs of input and output columns.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeMinMax(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Int64,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes based on the observed minimum and maximum values of the data.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type on this column is the same as the input column.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
The data type on this column should be <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeMinMax(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.Int64,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes based on the observed minimum and maximum values of the data.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The pairs of input and output columns.
|
||
The input columns must be of data type <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.
|
||
The data type for the output column will be the same as the associated input column.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeMeanVariance(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Int64,System.Boolean,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes based on the computed mean and variance of the data.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type on this column is the same as the input column.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
The data type on this column should be <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<param name="useCdf">Whether to use CDF as the output.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeMeanVariance(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.Int64,System.Boolean,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes based on the computed mean and variance of the data.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The pairs of input and output columns.
|
||
The input columns must be of data type <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.
|
||
The data type for the output column will be the same as the associated input column.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<param name="useCdf">Whether to use CDF as the output.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeLogMeanVariance(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Int64,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes based on the computed mean and variance of the logarithm of the data.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type on this column is the same as the input column.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
The data type on this column should be <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="useCdf">Whether to use CDF as the output.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeLogMeanVariance(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.Int64,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes based on the computed mean and variance of the logarithm of the data.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The pairs of input and output columns.
|
||
The input columns must be of data type <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.
|
||
The data type for the output column will be the same as the associated input column.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="useCdf">Whether to use CDF as the output.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeLogMeanVariance(Microsoft.ML.TransformsCatalog,System.String,System.Boolean,System.String,System.Int64,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes based on the computed mean and variance of the logarithm of the data.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type on this column is the same as the input column.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
The data type on this column should be <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="useCdf">Whether to use CDF as the output.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeLogMeanVariance(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.Boolean,System.Int64,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes based on the computed mean and variance of the logarithm of the data.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The pairs of input and output columns.
|
||
The input columns must be of data type <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.
|
||
The data type for the output column will be the same as the associated input column.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="useCdf">Whether to use CDF as the output.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeBinning(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Int64,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes by assigning the data into bins with equal density.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type on this column is the same as the input column.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
The data type on this column should be <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<param name="maximumBinCount">Maximum number of bins (power of 2 recommended).</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeBinning(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.Int64,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes by assigning the data into bins with equal density.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The pairs of input and output columns.
|
||
The input columns must be of data type <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.
|
||
The data type for the output column will be the same as the associated input column.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<param name="maximumBinCount">Maximum number of bins (power of 2 recommended).</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeSupervisedBinning(Microsoft.ML.TransformsCatalog,System.String,System.String,System.String,System.Int64,System.Boolean,System.Int32,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes by assigning the data into bins based on correlation with the <paramref name="labelColumnName"/> column.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type on this column is the same as the input column.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
The data type on this column should be <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.</param>
|
||
<param name="labelColumnName">Name of the label column for supervised binning.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<param name="maximumBinCount">Maximum number of bins (power of 2 recommended).</param>
|
||
<param name="mininimumExamplesPerBin">Minimum number of examples per bin.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeSupervisedBinning(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.String,System.Int64,System.Boolean,System.Int32,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes by assigning the data into bins based on correlation with the <paramref name="labelColumnName"/> column.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The pairs of input and output columns.
|
||
The input columns must be of data type <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.
|
||
The data type for the output column will be the same as the associated input column.</param>
|
||
<param name="labelColumnName">Name of the label column for supervised binning.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
|
||
<param name="maximumBinCount">Maximum number of bins (power of 2 recommended).</param>
|
||
<param name="mininimumExamplesPerBin">Minimum number of examples per bin.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeRobustScaling(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Int64,System.Boolean,System.UInt32,System.UInt32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes using statistics that are robust to outliers by centering the data around 0 (removing the median) and scales
|
||
the data according to the quantile range (defaults to the interquartile range).
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
The data type on this column is the same as the input column.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
The data type on this column should be <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="centerData">Whether to center the data around 0 by removing the median. Defaults to true.</param>
|
||
<param name="quantileMin">Quantile min used to scale the data. Defaults to 25.</param>
|
||
<param name="quantileMax">Quantile max used to scale the data. Defaults to 75.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeRobustScaling(Microsoft.ML.TransformsCatalog,Microsoft.ML.InputOutputColumnPair[],System.Int64,System.Boolean,System.UInt32,System.UInt32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.NormalizingEstimator"/>, which normalizes using statistics that are robust to outliers by centering the data around 0 (removing the median) and scales
|
||
the data according to the quantile range (defaults to the interquartile range).
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The pairs of input and output columns.
|
||
The input columns must be of data type <see cref="T:System.Single"/>, <see cref="T:System.Double"/> or a known-sized vector of those types.
|
||
The data type for the output column will be the same as the associated input column.</param>
|
||
<param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
|
||
<param name="centerData">Whether to center the data around 0 be removing the median. Defaults to true.</param>
|
||
<param name="quantileMin">Quantile min used to scale the data. Defaults to 25.</param>
|
||
<param name="quantileMax">Quantile max used to scale the data. Defaults to 75.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.Normalize(Microsoft.ML.TransformsCatalog,Microsoft.ML.Transforms.NormalizingEstimator.ColumnOptionsBase[])">
|
||
<summary>
|
||
Normalize (rescale) columns according to specified custom parameters.
|
||
</summary>
|
||
<param name="catalog">The transform catalog</param>
|
||
<param name="columns">The normalization settings for all the columns</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeLpNorm(Microsoft.ML.TransformsCatalog,System.String,System.String,Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimator"/>, which normalizes (scales) vectors in the input column to the unit norm.
|
||
The type of norm that is used is defined by <paramref name="norm"/>. Setting <paramref name="ensureZeroMean"/> to <see langword="true"/>,
|
||
will apply a pre-processing step to make the specified column's mean be a zero vector.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be the same as the input column's data type.</param>
|
||
<param name="inputColumnName">Name of the column to normalize. If set to <see langword="null"/>, the value of the
|
||
<paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over known-sized vectors of <see cref="T:System.Single"/>.</param>
|
||
<param name="norm">Type of norm to use to normalize each sample. The indicated norm of the resulting vector will be normalized to one.</param>
|
||
<param name="ensureZeroMean">If <see langword="true"/>, subtract mean from each value before normalizing and use the raw input otherwise.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeLpNorm(Microsoft.ML.TransformsCatalog,Microsoft.ML.Transforms.LpNormNormalizingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Takes column filled with a vector of floats and normalize its norm to one. Note that the allowed norm functions are defined in <see cref="T:Microsoft.ML.Transforms.LpNormNormalizingEstimatorBase.NormFunction"/>.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns"> Describes the parameters of the lp-normalization process for each column pair.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeGlobalContrast(Microsoft.ML.TransformsCatalog,System.String,System.String,System.Boolean,System.Boolean,System.Single)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator"/>, which normalizes columns individually applying global contrast normalization.
|
||
Setting <paramref name="ensureZeroMean"/> to <see langword="true"/>, will apply a pre-processing step to make the specified column's mean be the zero vector.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be the same as the input column's data type.</param>
|
||
<param name="inputColumnName">Name of the column to normalize. If set to <see langword="null"/>, the value of the
|
||
<paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over known-sized vectors of <see cref="T:System.Single"/>.</param>
|
||
<param name="ensureZeroMean">If <see langword="true"/>, subtract mean from each value before normalizing and use the raw input otherwise.</param>
|
||
<param name="ensureUnitStandardDeviation">If <see langword="true"/>, the resulting vector's standard deviation would be one.
|
||
Otherwise, the resulting vector's L2-norm would be one.</param>
|
||
<param name="scale">Scale features by this value.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.NormalizationCatalog.NormalizeGlobalContrast(Microsoft.ML.TransformsCatalog,Microsoft.ML.Transforms.GlobalContrastNormalizingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Takes columns filled with a vector of floats and computes global contrast normalization of it.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns"> Describes the parameters of the gcn-normaliztion process for each column pair.</param>
|
||
</member>
|
||
<member name="T:Microsoft.ML.PermutationFeatureImportanceExtensions">
|
||
<summary>
|
||
Collection of extension methods used by <see cref="T:Microsoft.ML.RegressionCatalog"/>,
|
||
<see cref="T:Microsoft.ML.BinaryClassificationCatalog"/>, <see cref="T:Microsoft.ML.MulticlassClassificationCatalog"/>,
|
||
and <see cref="T:Microsoft.ML.RankingCatalog"/> to create instances of permutation feature importance components.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.PermutationFeatureImportanceExtensions.PermutationFeatureImportance``1(Microsoft.ML.RegressionCatalog,Microsoft.ML.ISingleFeaturePredictionTransformer{``0},Microsoft.ML.IDataView,System.String,System.Boolean,System.Nullable{System.Int32},System.Int32)">
|
||
<summary>
|
||
Permutation Feature Importance (PFI) for Regression.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
Permutation feature importance (PFI) is a technique to determine the global importance of features in a trained
|
||
machine learning model. PFI is a simple yet powerful technique motivated by Breiman in his Random Forest paper, section 10
|
||
(Breiman. <a href='https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf'>"Random Forests."</a> Machine Learning, 2001.)
|
||
The advantage of the PFI method is that it is model agnostic -- it works with any model that can be
|
||
evaluated -- and it can use any dataset, not just the training set, to compute feature importance metrics.
|
||
</para>
|
||
<para>
|
||
PFI works by taking a labeled dataset, choosing a feature, and permuting the values
|
||
for that feature across all the examples, so that each example now has a random value for the feature and
|
||
the original values for all other features. The evaluation metric (e.g. R-squared) is then calculated
|
||
for this modified dataset, and the change in the evaluation metric from the original dataset is computed.
|
||
The larger the change in the evaluation metric, the more important the feature is to the model.
|
||
PFI works by performing this permutation analysis across all the features of a model, one after another.
|
||
</para>
|
||
<para>
|
||
In this implementation, PFI computes the change in all possible regression evaluation metrics for each feature, and an
|
||
<see cref="T:System.Collections.Immutable.ImmutableArray"/> of <see cref="T:Microsoft.ML.Data.RegressionMetrics"/> objects is returned. See the sample below for an
|
||
example of working with these results to analyze the feature importance of a model.
|
||
</para>
|
||
</remarks>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
<param name="catalog">The regression catalog.</param>
|
||
<param name="predictionTransformer">The model on which to evaluate feature importance.</param>
|
||
<param name="data">The evaluation data set.</param>
|
||
<param name="labelColumnName">Label column name. The column data must be <see cref="T:System.Single"/>.</param>
|
||
<param name="useFeatureWeightFilter">Use features weight to pre-filter features.</param>
|
||
<param name="numberOfExamplesToUse">Limit the number of examples to evaluate on. <cref langword="null"/> means up to ~2 bln examples from <paramref param="data"/> will be used.</param>
|
||
<param name="permutationCount">The number of permutations to perform.</param>
|
||
<returns>Array of per-feature 'contributions' to the score.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.PermutationFeatureImportanceExtensions.PermutationFeatureImportance(Microsoft.ML.RegressionCatalog,Microsoft.ML.ITransformer,Microsoft.ML.IDataView,System.String,System.Boolean,System.Nullable{System.Int32},System.Int32)">
|
||
<summary>
|
||
Permutation Feature Importance (PFI) for Regression.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
Permutation feature importance (PFI) is a technique to determine the global importance of features in a trained
|
||
machine learning model. PFI is a simple yet powerful technique motivated by Breiman in his Random Forest paper, section 10
|
||
(Breiman. <a href='https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf'>"Random Forests."</a> Machine Learning, 2001.)
|
||
The advantage of the PFI method is that it is model agnostic -- it works with any model that can be
|
||
evaluated -- and it can use any dataset, not just the training set, to compute feature importance metrics.
|
||
</para>
|
||
<para>
|
||
PFI works by taking a labeled dataset, choosing a feature, and permuting the values
|
||
for that feature across all the examples, so that each example now has a random value for the feature and
|
||
the original values for all other features. The evaluation metric (e.g. R-squared) is then calculated
|
||
for this modified dataset, and the change in the evaluation metric from the original dataset is computed.
|
||
The larger the change in the evaluation metric, the more important the feature is to the model.
|
||
PFI works by performing this permutation analysis across all the features of a model, one after another.
|
||
</para>
|
||
<para>
|
||
In this implementation, PFI computes the change in all possible regression evaluation metrics for each feature, and an
|
||
<see cref="T:System.Collections.Immutable.ImmutableArray"/> of <see cref="T:Microsoft.ML.Data.RegressionMetrics"/> objects is returned. See the sample below for an
|
||
example of working with these results to analyze the feature importance of a model.
|
||
</para>
|
||
</remarks>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
<param name="catalog">The regression catalog.</param>
|
||
<param name="model">The model on which to evaluate feature importance.</param>
|
||
<param name="data">The evaluation data set.</param>
|
||
<param name="labelColumnName">Label column name. The column data must be <see cref="T:System.Single"/>.</param>
|
||
<param name="useFeatureWeightFilter">Use features weight to pre-filter features.</param>
|
||
<param name="numberOfExamplesToUse">Limit the number of examples to evaluate on. <cref langword="null"/> means up to ~2 bln examples from <paramref param="data"/> will be used.</param>
|
||
<param name="permutationCount">The number of permutations to perform.</param>
|
||
<returns>Dictionary mapping each feature to its per-feature 'contributions' to the score.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.PermutationFeatureImportanceExtensions.PermutationFeatureImportance``1(Microsoft.ML.BinaryClassificationCatalog,Microsoft.ML.ISingleFeaturePredictionTransformer{``0},Microsoft.ML.IDataView,System.String,System.Boolean,System.Nullable{System.Int32},System.Int32)">
|
||
<summary>
|
||
Permutation Feature Importance (PFI) for Binary Classification.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
Permutation feature importance (PFI) is a technique to determine the global importance of features in a trained
|
||
machine learning model. PFI is a simple yet powerful technique motivated by Breiman in his Random Forest paper, section 10
|
||
(Breiman. <a href='https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf'>"Random Forests."</a> Machine Learning, 2001.)
|
||
The advantage of the PFI method is that it is model agnostic -- it works with any model that can be
|
||
evaluated -- and it can use any dataset, not just the training set, to compute feature importance metrics.
|
||
</para>
|
||
<para>
|
||
PFI works by taking a labeled dataset, choosing a feature, and permuting the values
|
||
for that feature across all the examples, so that each example now has a random value for the feature and
|
||
the original values for all other features. The evaluation metric (e.g. AUC) is then calculated
|
||
for this modified dataset, and the change in the evaluation metric from the original dataset is computed.
|
||
The larger the change in the evaluation metric, the more important the feature is to the model.
|
||
PFI works by performing this permutation analysis across all the features of a model, one after another.
|
||
</para>
|
||
<para>
|
||
In this implementation, PFI computes the change in all possible binary classification evaluation metrics for each feature, and an
|
||
<see cref="T:System.Collections.Immutable.ImmutableArray"/> of <see cref="T:Microsoft.ML.Data.BinaryClassificationMetrics"/> objects is returned. See the sample below for an
|
||
example of working with these results to analyze the feature importance of a model.
|
||
</para>
|
||
</remarks>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
<param name="catalog">The binary classification catalog.</param>
|
||
<param name="predictionTransformer">The model on which to evaluate feature importance.</param>
|
||
<param name="data">The evaluation data set.</param>
|
||
<param name="labelColumnName">Label column name. The column data must be <see cref="T:System.Boolean"/>.</param>
|
||
<param name="useFeatureWeightFilter">Use features weight to pre-filter features.</param>
|
||
<param name="numberOfExamplesToUse">Limit the number of examples to evaluate on. <cref langword="null"/> means up to ~2 bln examples from <paramref param="data"/> will be used.</param>
|
||
<param name="permutationCount">The number of permutations to perform.</param>
|
||
<returns>Array of per-feature 'contributions' to the score.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.PermutationFeatureImportanceExtensions.PermutationFeatureImportanceNonCalibrated(Microsoft.ML.BinaryClassificationCatalog,Microsoft.ML.ITransformer,Microsoft.ML.IDataView,System.String,System.Boolean,System.Nullable{System.Int32},System.Int32)">
|
||
<summary>
|
||
Permutation Feature Importance (PFI) for Binary Classification.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
Permutation feature importance (PFI) is a technique to determine the global importance of features in a trained
|
||
machine learning model. PFI is a simple yet powerful technique motivated by Breiman in his Random Forest paper, section 10
|
||
(Breiman. <a href='https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf'>"Random Forests."</a> Machine Learning, 2001.)
|
||
The advantage of the PFI method is that it is model agnostic -- it works with any model that can be
|
||
evaluated -- and it can use any dataset, not just the training set, to compute feature importance metrics.
|
||
</para>
|
||
<para>
|
||
PFI works by taking a labeled dataset, choosing a feature, and permuting the values
|
||
for that feature across all the examples, so that each example now has a random value for the feature and
|
||
the original values for all other features. The evaluation metric (e.g. AUC) is then calculated
|
||
for this modified dataset, and the change in the evaluation metric from the original dataset is computed.
|
||
The larger the change in the evaluation metric, the more important the feature is to the model.
|
||
PFI works by performing this permutation analysis across all the features of a model, one after another.
|
||
</para>
|
||
<para>
|
||
In this implementation, PFI computes the change in all possible binary classification evaluation metrics for each feature, and an
|
||
<see cref="T:System.Collections.Immutable.ImmutableArray"/> of <see cref="T:Microsoft.ML.Data.BinaryClassificationMetrics"/> objects is returned. See the sample below for an
|
||
example of working with these results to analyze the feature importance of a model.
|
||
</para>
|
||
</remarks>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
<param name="catalog">The binary classification catalog.</param>
|
||
<param name="model">The model on which to evaluate feature importance.</param>
|
||
<param name="data">The evaluation data set.</param>
|
||
<param name="labelColumnName">Label column name. The column data must be <see cref="T:System.Boolean"/>.</param>
|
||
<param name="useFeatureWeightFilter">Use features weight to pre-filter features.</param>
|
||
<param name="numberOfExamplesToUse">Limit the number of examples to evaluate on. <cref langword="null"/> means up to ~2 bln examples from <paramref param="data"/> will be used.</param>
|
||
<param name="permutationCount">The number of permutations to perform.</param>
|
||
<returns>Dictionary mapping each feature to its per-feature 'contributions' to the score.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.PermutationFeatureImportanceExtensions.PermutationFeatureImportance``1(Microsoft.ML.MulticlassClassificationCatalog,Microsoft.ML.ISingleFeaturePredictionTransformer{``0},Microsoft.ML.IDataView,System.String,System.Boolean,System.Nullable{System.Int32},System.Int32)">
|
||
<summary>
|
||
Permutation Feature Importance (PFI) for MulticlassClassification.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
Permutation feature importance (PFI) is a technique to determine the global importance of features in a trained
|
||
machine learning model. PFI is a simple yet powerful technique motivated by Breiman in his Random Forest paper, section 10
|
||
(Breiman. <a href='https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf'>"Random Forests."</a> Machine Learning, 2001.)
|
||
The advantage of the PFI method is that it is model agnostic -- it works with any model that can be
|
||
evaluated -- and it can use any dataset, not just the training set, to compute feature importance metrics.
|
||
</para>
|
||
<para>
|
||
PFI works by taking a labeled dataset, choosing a feature, and permuting the values
|
||
for that feature across all the examples, so that each example now has a random value for the feature and
|
||
the original values for all other features. The evaluation metric (e.g. micro-accuracy) is then calculated
|
||
for this modified dataset, and the change in the evaluation metric from the original dataset is computed.
|
||
The larger the change in the evaluation metric, the more important the feature is to the model.
|
||
PFI works by performing this permutation analysis across all the features of a model, one after another.
|
||
</para>
|
||
<para>
|
||
In this implementation, PFI computes the change in all possible multiclass classification evaluation metrics for each feature, and an
|
||
<see cref="T:System.Collections.Immutable.ImmutableArray"/> of <see cref="T:Microsoft.ML.Data.MulticlassClassificationMetrics"/> objects is returned. See the sample below for an
|
||
example of working with these results to analyze the feature importance of a model.
|
||
</para>
|
||
</remarks>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
<param name="catalog">The multiclass classification catalog.</param>
|
||
<param name="predictionTransformer">The model on which to evaluate feature importance.</param>
|
||
<param name="data">The evaluation data set.</param>
|
||
<param name="labelColumnName">Label column name. The column data must be <see cref="T:Microsoft.ML.Data.KeyDataViewType"/>.</param>
|
||
<param name="useFeatureWeightFilter">Use features weight to pre-filter features.</param>
|
||
<param name="numberOfExamplesToUse">Limit the number of examples to evaluate on. <cref langword="null"/> means up to ~2 bln examples from <paramref param="data"/> will be used.</param>
|
||
<param name="permutationCount">The number of permutations to perform.</param>
|
||
<returns>Array of per-feature 'contributions' to the score.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.PermutationFeatureImportanceExtensions.PermutationFeatureImportance(Microsoft.ML.MulticlassClassificationCatalog,Microsoft.ML.ITransformer,Microsoft.ML.IDataView,System.String,System.Boolean,System.Nullable{System.Int32},System.Int32)">
|
||
<summary>
|
||
Permutation Feature Importance (PFI) for MulticlassClassification.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
Permutation feature importance (PFI) is a technique to determine the global importance of features in a trained
|
||
machine learning model. PFI is a simple yet powerful technique motivated by Breiman in his Random Forest paper, section 10
|
||
(Breiman. <a href='https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf'>"Random Forests."</a> Machine Learning, 2001.)
|
||
The advantage of the PFI method is that it is model agnostic -- it works with any model that can be
|
||
evaluated -- and it can use any dataset, not just the training set, to compute feature importance metrics.
|
||
</para>
|
||
<para>
|
||
PFI works by taking a labeled dataset, choosing a feature, and permuting the values
|
||
for that feature across all the examples, so that each example now has a random value for the feature and
|
||
the original values for all other features. The evaluation metric (e.g. micro-accuracy) is then calculated
|
||
for this modified dataset, and the change in the evaluation metric from the original dataset is computed.
|
||
The larger the change in the evaluation metric, the more important the feature is to the model.
|
||
PFI works by performing this permutation analysis across all the features of a model, one after another.
|
||
</para>
|
||
<para>
|
||
In this implementation, PFI computes the change in all possible multiclass classification evaluation metrics for each feature, and an
|
||
<see cref="T:System.Collections.Immutable.ImmutableArray"/> of <see cref="T:Microsoft.ML.Data.MulticlassClassificationMetrics"/> objects is returned. See the sample below for an
|
||
example of working with these results to analyze the feature importance of a model.
|
||
</para>
|
||
</remarks>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
<param name="catalog">The multiclass classification catalog.</param>
|
||
<param name="model">The model on which to evaluate feature importance.</param>
|
||
<param name="data">The evaluation data set.</param>
|
||
<param name="labelColumnName">Label column name. The column data must be <see cref="T:Microsoft.ML.Data.KeyDataViewType"/>.</param>
|
||
<param name="useFeatureWeightFilter">Use features weight to pre-filter features.</param>
|
||
<param name="numberOfExamplesToUse">Limit the number of examples to evaluate on. <cref langword="null"/> means up to ~2 bln examples from <paramref param="data"/> will be used.</param>
|
||
<param name="permutationCount">The number of permutations to perform.</param>
|
||
<returns>Dictionary mapping each feature to its per-feature 'contributions' to the score.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.PermutationFeatureImportanceExtensions.PermutationFeatureImportance``1(Microsoft.ML.RankingCatalog,Microsoft.ML.ISingleFeaturePredictionTransformer{``0},Microsoft.ML.IDataView,System.String,System.String,System.Boolean,System.Nullable{System.Int32},System.Int32)">
|
||
<summary>
|
||
Permutation Feature Importance (PFI) for Ranking.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
Permutation feature importance (PFI) is a technique to determine the global importance of features in a trained
|
||
machine learning model. PFI is a simple yet powerful technique motivated by Breiman in his Random Forest paper, section 10
|
||
(Breiman. <a href='https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf'>"Random Forests."</a> Machine Learning, 2001.)
|
||
The advantage of the PFI method is that it is model agnostic -- it works with any model that can be
|
||
evaluated -- and it can use any dataset, not just the training set, to compute feature importance metrics.
|
||
</para>
|
||
<para>
|
||
PFI works by taking a labeled dataset, choosing a feature, and permuting the values
|
||
for that feature across all the examples, so that each example now has a random value for the feature and
|
||
the original values for all other features. The evaluation metric (e.g. NDCG) is then calculated
|
||
for this modified dataset, and the change in the evaluation metric from the original dataset is computed.
|
||
The larger the change in the evaluation metric, the more important the feature is to the model.
|
||
PFI works by performing this permutation analysis across all the features of a model, one after another.
|
||
</para>
|
||
<para>
|
||
In this implementation, PFI computes the change in all possible ranking evaluation metrics for each feature, and an
|
||
<see cref="T:System.Collections.Immutable.ImmutableArray"/> of <see cref="T:Microsoft.ML.Data.RankingMetrics"/> objects is returned. See the sample below for an
|
||
example of working with these results to analyze the feature importance of a model.
|
||
</para>
|
||
</remarks>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
<param name="catalog">The ranking catalog.</param>
|
||
<param name="predictionTransformer">The model on which to evaluate feature importance.</param>
|
||
<param name="data">The evaluation data set.</param>
|
||
<param name="labelColumnName">Label column name. The column data must be <see cref="T:System.Single"/> or <see cref="T:Microsoft.ML.Data.KeyDataViewType"/>.</param>
|
||
<param name="rowGroupColumnName">GroupId column name</param>
|
||
<param name="useFeatureWeightFilter">Use features weight to pre-filter features.</param>
|
||
<param name="numberOfExamplesToUse">Limit the number of examples to evaluate on. <cref langword="null"/> means up to ~2 bln examples from <paramref param="data"/> will be used.</param>
|
||
<param name="permutationCount">The number of permutations to perform.</param>
|
||
<returns>Array of per-feature 'contributions' to the score.</returns>
|
||
</member>
|
||
<member name="M:Microsoft.ML.PermutationFeatureImportanceExtensions.PermutationFeatureImportance(Microsoft.ML.RankingCatalog,Microsoft.ML.ITransformer,Microsoft.ML.IDataView,System.String,System.String,System.Boolean,System.Nullable{System.Int32},System.Int32)">
|
||
<summary>
|
||
Permutation Feature Importance (PFI) for Ranking.
|
||
</summary>
|
||
<remarks>
|
||
<para>
|
||
Permutation feature importance (PFI) is a technique to determine the global importance of features in a trained
|
||
machine learning model. PFI is a simple yet powerful technique motivated by Breiman in his Random Forest paper, section 10
|
||
(Breiman. <a href='https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf'>"Random Forests."</a> Machine Learning, 2001.)
|
||
The advantage of the PFI method is that it is model agnostic -- it works with any model that can be
|
||
evaluated -- and it can use any dataset, not just the training set, to compute feature importance metrics.
|
||
</para>
|
||
<para>
|
||
PFI works by taking a labeled dataset, choosing a feature, and permuting the values
|
||
for that feature across all the examples, so that each example now has a random value for the feature and
|
||
the original values for all other features. The evaluation metric (e.g. NDCG) is then calculated
|
||
for this modified dataset, and the change in the evaluation metric from the original dataset is computed.
|
||
The larger the change in the evaluation metric, the more important the feature is to the model.
|
||
PFI works by performing this permutation analysis across all the features of a model, one after another.
|
||
</para>
|
||
<para>
|
||
In this implementation, PFI computes the change in all possible ranking evaluation metrics for each feature, and an
|
||
<see cref="T:System.Collections.Immutable.ImmutableArray"/> of <see cref="T:Microsoft.ML.Data.RankingMetrics"/> objects is returned. See the sample below for an
|
||
example of working with these results to analyze the feature importance of a model.
|
||
</para>
|
||
</remarks>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
<param name="catalog">The ranking catalog.</param>
|
||
<param name="model">The model on which to evaluate feature importance.</param>
|
||
<param name="data">The evaluation data set.</param>
|
||
<param name="labelColumnName">Label column name. The column data must be <see cref="T:System.Single"/> or <see cref="T:Microsoft.ML.Data.KeyDataViewType"/>.</param>
|
||
<param name="rowGroupColumnName">GroupId column name</param>
|
||
<param name="useFeatureWeightFilter">Use features weight to pre-filter features.</param>
|
||
<param name="numberOfExamplesToUse">Limit the number of examples to evaluate on. <cref langword="null"/> means up to ~2 bln examples from <paramref param="data"/> will be used.</param>
|
||
<param name="permutationCount">The number of permutations to perform.</param>
|
||
<returns>Dictionary mapping each feature to its per-feature 'contributions' to the score.</returns>
|
||
</member>
|
||
<member name="T:Microsoft.ML.TextCatalog">
|
||
<summary>
|
||
Collection of extension methods for the <see cref="T:Microsoft.ML.TransformsCatalog"/>.
|
||
</summary>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.FeaturizeText(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator"/>, which transforms a text column into a featurized vector of <see cref="T:System.Single"/> that represents normalized counts of n-grams and char-grams.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a vector of <see cref="T:System.Single"/>. </param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over text data.
|
||
</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.FeaturizeText(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,Microsoft.ML.Transforms.Text.TextFeaturizingEstimator.Options,System.String[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.TextFeaturizingEstimator"/>, which transforms a text column into featurized vector of <see cref="T:System.Single"/> that represents normalized counts of n-grams and char-grams.
|
||
</summary>
|
||
<remarks>This transform can operate over several columns.</remarks>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnNames"/>.
|
||
This column's data type will be a vector of <see cref="T:System.Single"/>.
|
||
</param>
|
||
<param name="options">Advanced options to the algorithm.</param>
|
||
<param name="inputColumnNames">Name of the columns to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over text data, and it can transform several columns at once, yielding one vector of <see cref="T:System.Single"/>
|
||
as the resulting features for all columns.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.TokenizeIntoCharactersAsKeys(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.TokenizingByCharactersEstimator"/>, which tokenizes by splitting text into sequences of characters
|
||
using a sliding window.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a variable-sized vector of keys.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the
|
||
<paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over text data type.</param>
|
||
<param name="useMarkerCharacters">To be able to distinguish the tokens, for example for debugging purposes,
|
||
you can choose to prepend a marker character, <see langword="0x02"/>, to the beginning,
|
||
and append another marker character, <see langword="0x03"/>, to the end of the output vector of characters.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.TokenizeIntoCharactersAsKeys(Microsoft.ML.TransformsCatalog.TextTransforms,System.Boolean,Microsoft.ML.InputOutputColumnPair[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.TokenizingByCharactersEstimator"/>, which tokenizes incoming text in input columns and output the tokens as output columns.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="useMarkerCharacters">Whether to prepend a marker character, <see langword="0x02"/>, to the beginning,
|
||
and append another marker character, <see langword="0x03"/>, to the end of the output vector of characters.</param>
|
||
<param name="columns">Pairs of columns to run the tokenization on.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.NormalizeText(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,Microsoft.ML.Transforms.Text.TextNormalizingEstimator.CaseMode,System.Boolean,System.Boolean,System.Boolean)">
|
||
<summary>
|
||
Creates a <see cref="T:Microsoft.ML.Transforms.Text.TextNormalizingEstimator"/>, which normalizes incoming text in <paramref name="inputColumnName"/> by optionally
|
||
changing case, removing diacritical marks, punctuation marks, numbers, and outputs new text as <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type is a scalar or a vector of text depending on the input column data type.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>,
|
||
the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates on text or vector of text data types.</param>
|
||
<param name="caseMode">Casing text using the rules of the invariant culture.</param>
|
||
<param name="keepDiacritics">Whether to keep diacritical marks or remove them.</param>
|
||
<param name="keepPunctuations">Whether to keep punctuation marks or remove them.</param>
|
||
<param name="keepNumbers">Whether to keep numbers or remove them.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ApplyWordEmbedding(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind)">
|
||
<summary>
|
||
Create an <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator"/>, which is a text featurizer that converts a vector
|
||
of text into a numerical vector using pre-trained embeddings models.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>,
|
||
the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over known-size vector of text data type.</param>
|
||
<param name="modelKind">The embeddings <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind"/> to use. </param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ApplyWordEmbedding(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.String)">
|
||
<summary>
|
||
Create an <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator"/>, which is a text featurizer that converts vectors
|
||
of text into numerical vectors using pre-trained embeddings models.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="customModelFile">The path of the pre-trained embeddings model to use.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>,
|
||
the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over known-size vector of text data type.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ApplyWordEmbedding(Microsoft.ML.TransformsCatalog.TextTransforms,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind,Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Create an <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator"/>, which is a text featurizer that converts vectors
|
||
of text into numerical vectors using pre-trained embeddings models.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="modelKind">The embeddings <see cref="T:Microsoft.ML.Transforms.Text.WordEmbeddingEstimator.PretrainedModelKind"/> to use. </param>
|
||
<param name="columns">The array columns, and per-column configurations to extract embeddings from.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.TokenizeIntoWords(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Char[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.WordTokenizingEstimator"/>, which tokenizes input text using <paramref name="separators"/> as separators.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a variable-size vector of text.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates on scalar of text and vector of text data type.</param>
|
||
<param name="separators">The separators to use (uses space character by default).</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.TokenizeIntoWords(Microsoft.ML.TransformsCatalog.TextTransforms,Microsoft.ML.Transforms.Text.WordTokenizingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Tokenizes incoming text in input columns, using per-column configurations, and outputs the tokens.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="columns">Pairs of columns to run the tokenization on.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceNgrams(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria)">
|
||
<summary>
|
||
Creates a <see cref="T:Microsoft.ML.Transforms.Text.NgramExtractingEstimator"/> which produces a vector of counts of n-grams (sequences of consecutive words)
|
||
encountered in the input text.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be a vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over vectors of keys data type.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Number of tokens to skip between each n-gram. By default no token is skipped.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="weighting">Statistical measure used to evaluate how important a word or n-gram is to a document in a corpus.
|
||
When <paramref name="maximumNgramsCount"/> is smaller than the total number of encountered n-grams this measure is used
|
||
to determine which n-grams to keep.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceNgrams(Microsoft.ML.TransformsCatalog.TextTransforms,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Produces a bag of counts of n-grams (sequences of consecutive words) in <paramref name="columns.inputs.inputs"/>
|
||
and outputs bag of word vector for each output in <paramref name="columns.output.output"/>
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="columns">Pairs of columns to run the n-gram process on.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.RemoveDefaultStopWords(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,Microsoft.ML.Transforms.Text.StopWordsRemovingEstimator.Language)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator"/>, which copies the data from the column specified in <paramref name="inputColumnName"/>
|
||
to a new column: <paramref name="outputColumnName"/> and removes predifined set of text specific for <paramref name="language"/> from it.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be variable-size vector of text.</param>
|
||
<param name="inputColumnName">Name of the column to copy the data from.
|
||
This estimator operates over vector of text.</param>
|
||
<param name="language">Langauge of the input text column <paramref name="inputColumnName"/>.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.RemoveStopWords(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.String[])">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.CustomStopWordsRemovingEstimator"/>, which copies the data from the column specified in <paramref name="inputColumnName"/>
|
||
to a new column: <paramref name="outputColumnName"/> and removes text specified in <paramref name="stopwords"/> from it.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be variable-size vector of text.</param>
|
||
<param name="inputColumnName">Name of the column to copy the data from.
|
||
This estimator operates over a vector of text.</param>
|
||
<param name="stopwords">Array of words to remove.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.WordBagEstimator"/>, which maps the column specified in <paramref name="inputColumnName"/>
|
||
to a vector of n-gram counts in a new column named <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<remarks>
|
||
<see cref="T:Microsoft.ML.Transforms.Text.WordBagEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.NgramExtractingEstimator"/> in that the former
|
||
tokenizes text internally and the latter takes tokenized text as input.
|
||
</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be known-size vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of the column to take the data from.
|
||
This estimator operates over vector of text.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="weighting">Statistical measure used to evaluate how important a word is to a document in a corpus.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.Char,System.Char,System.String,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.WordBagEstimator"/>, which maps the column specified in <paramref name="inputColumnName"/>
|
||
to a vector of n-gram counts in a new column named <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<remarks>
|
||
<see cref="T:Microsoft.ML.Transforms.Text.WordBagEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.NgramExtractingEstimator"/> in that the former
|
||
tokenizes text internally and the latter takes tokenized text as input.
|
||
</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be known-size vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of the column to take the data from.
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="termSeparator">Separator used to separate terms/frequency pairs.</param>
|
||
<param name="freqSeparator">Separator used to separate terms from their frequency.</param>
|
||
This estimator operates over vector of text.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String[],System.Int32,System.Int32,System.Boolean,System.Int32,Microsoft.ML.Transforms.Text.NgramExtractingEstimator.WeightingCriteria)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.WordBagEstimator"/>, which maps the multiple columns specified in <paramref name="inputColumnNames"/>
|
||
to a vector of n-gram counts in a new column named <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<remarks>
|
||
<see cref="T:Microsoft.ML.Transforms.Text.WordBagEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.NgramExtractingEstimator"/> in that the former
|
||
tokenizes text internally and the latter takes tokenized text as input.
|
||
</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnNames"/>.
|
||
This column's data type will be known-size vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnNames">Names of the multiple columns to take the data from.
|
||
This estimator operates over vector of text.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="maximumNgramsCount">Maximum number of n-grams to store in the dictionary.</param>
|
||
<param name="weighting">Statistical measure used to evaluate how important a word is to a document in a corpus.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceHashedWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/>, which maps the column specified in <paramref name="inputColumnName"/>
|
||
to a vector of counts of hashed n-grams in a new column named <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<remarks>
|
||
<see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/> in that the former
|
||
tokenizes text internally and the latter takes tokenized text as input.
|
||
</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be known-size vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of the column to take the data from.
|
||
This estimator operates over vector of text.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we construct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the annotations for the new column. Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceHashedWordBags(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String[],System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/>, which maps the multiple columns specified in <paramref name="inputColumnNames"/>
|
||
to a vector of counts of hashed n-grams in a new column named <paramref name="outputColumnName"/>.
|
||
</summary>
|
||
<remarks>
|
||
<see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/> in that the former
|
||
tokenizes text internally and the latter takes tokenized text as input.
|
||
</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnNames"/>.
|
||
This column's data type will be known-size vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnNames">Names of the multiple columns to take the data from.
|
||
This estimator operates over vector of text.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we construct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the annotations for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceHashedNgrams(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>, which copies the data from the column specified in <paramref name="inputColumnName"/>
|
||
to a new column: <paramref name="outputColumnName"/> and produces a vector of counts of hashed n-grams.
|
||
</summary>
|
||
<remarks>
|
||
<see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> in a way that <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>
|
||
takes tokenized text as input while <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> tokenizes text internally.
|
||
</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This column's data type will be vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of the column to copy the data from.
|
||
This estimator operates over vector of key type.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we construct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the annotations for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
<param name="rehashUnigrams">Whether to rehash unigrams.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceHashedNgrams(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String[],System.Int32,System.Int32,System.Int32,System.Boolean,System.UInt32,System.Boolean,System.Int32,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>, which takes the data from the multiple columns specified in <paramref name="inputColumnNames"/>
|
||
to a new column: <paramref name="outputColumnName"/> and produces a vector of counts of hashed n-grams.
|
||
</summary>
|
||
<remarks>
|
||
<see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> in a way that <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>
|
||
takes tokenized text as input while <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> tokenizes text internally.
|
||
</remarks>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnNames"/>.
|
||
This column's data type will be vector of known size of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnNames">Name of the multiple columns to take the data from.
|
||
This estimator operates over vector of key type.</param>
|
||
<param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
|
||
<param name="ngramLength">Ngram length.</param>
|
||
<param name="skipLength">Maximum number of tokens to skip when constructing an n-gram.</param>
|
||
<param name="useAllLengths">Whether to include all n-gram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
|
||
<param name="seed">Hashing seed.</param>
|
||
<param name="useOrderedHashing">Whether the position of each source column should be included in the hash (when there are multiple source columns).</param>
|
||
<param name="maximumNumberOfInverts">During hashing we construct mappings between original values and the produced hash values.
|
||
Text representation of original values are stored in the slot names of the annotations for the new column.Hashing, as such, can map many initial values to one.
|
||
<paramref name="maximumNumberOfInverts"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
|
||
<value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
|
||
<param name="rehashUnigrams">Whether to rehash unigrams.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.ProduceHashedNgrams(Microsoft.ML.TransformsCatalog.TextTransforms,Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Produces a bag of counts of hashed n-grams for each <paramref name="columns"/>. For each column,
|
||
<see cref="P:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.InputColumnNames"/> are the input columns of the output column named as <see cref="F:Microsoft.ML.Transforms.Text.NgramHashingEstimator.ColumnOptions.Name"/>.
|
||
|
||
<see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/> is different from <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> in a way that <see cref="T:Microsoft.ML.Transforms.Text.NgramHashingEstimator"/>
|
||
takes tokenized text as input while <see cref="T:Microsoft.ML.Transforms.Text.WordHashBagEstimator"/> tokenizes text internally.
|
||
</summary>
|
||
<param name="catalog">The text-related transform's catalog.</param>
|
||
<param name="columns">Pairs of columns to compute n-grams. Note that gram indices are generated by hashing.</param>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.LatentDirichletAllocation(Microsoft.ML.TransformsCatalog.TextTransforms,System.String,System.String,System.Int32,System.Single,System.Single,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Int32,System.Boolean)">
|
||
<summary>
|
||
Create a <see cref="T:Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator"/>, which uses <a href="https://arxiv.org/abs/1412.1576">LightLDA</a> to transform text (represented as a vector of floats)
|
||
into a vector of <see cref="T:System.Single"/> indicating the similarity of the text with each topic identified.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.
|
||
This estimator outputs a vector of <see cref="T:System.Single"/>.</param>
|
||
<param name="inputColumnName">Name of the column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.
|
||
This estimator operates over a vector of <see cref="T:System.Single"/>.
|
||
</param>
|
||
<param name="numberOfTopics">The number of topics.</param>
|
||
<param name="alphaSum">Dirichlet prior on document-topic vectors.</param>
|
||
<param name="beta">Dirichlet prior on vocab-topic vectors.</param>
|
||
<param name="samplingStepCount">Number of Metropolis Hasting step.</param>
|
||
<param name="maximumNumberOfIterations">Number of iterations.</param>
|
||
<param name="likelihoodInterval">Compute log likelihood over local dataset on this iteration interval.</param>
|
||
<param name="numberOfThreads">The number of training threads. Default value depends on number of logical processors.</param>
|
||
<param name="maximumTokenCountPerDocument">The threshold of maximum count of tokens per doc.</param>
|
||
<param name="numberOfSummaryTermsPerTopic">The number of words to summarize the topic.</param>
|
||
<param name="numberOfBurninIterations">The number of burn-in iterations.</param>
|
||
<param name="resetRandomGenerator">Reset the random number generator for each document.</param>
|
||
<example>
|
||
<format type="text/markdown">
|
||
<]
|
||
]]>
|
||
</format>
|
||
</example>
|
||
</member>
|
||
<member name="M:Microsoft.ML.TextCatalog.LatentDirichletAllocation(Microsoft.ML.TransformsCatalog.TextTransforms,Microsoft.ML.Transforms.Text.LatentDirichletAllocationEstimator.ColumnOptions[])">
|
||
<summary>
|
||
Uses <a href="https://arxiv.org/abs/1412.1576">LightLDA</a> to transform a document (represented as a vector of floats)
|
||
into a vector of floats over a set of topics.
|
||
</summary>
|
||
<param name="catalog">The transform's catalog.</param>
|
||
<param name="columns">Describes the parameters of LDA for each column pair.</param>
|
||
</member>
|
||
</members>
|
||
</doc>
|