ML - исправления очередного аудита

Configuration/GlobalAssemblyInfo.cs

@@ -15,7 +15,7 @@ internal static class RevisionClass
 	public const string Major = "3";
 	public const string Minor = "11";
 	public const string Build = "1";
-	public const string Revision = "3790";
+	public const string Revision = "3793";
 
         public const string MainVersion = Major + "." + Minor;
 	public const string FullVersion = Major + "." + Minor + "." + Build + "." + Revision;

Configuration/Version.defs

@@ -1,4 +1,4 @@
-%COREVERSION%=1
-%REVISION%=3790
 %MINOR%=11
+%REVISION%=3793
+%COREVERSION%=1
 %MAJOR%=3

Release/pabcversion.txt

@@ -1 +1 @@
-3.11.1.3790
+3.11.1.3793

ReleaseGenerators/PascalABCNET_version.nsh

@@ -1 +1 @@
-!define VERSION '3.11.1.3790'
+!define VERSION '3.11.1.3793'

bin/Lib/DataFrameABC.pas

@@ -10,7 +10,7 @@ interface
 
 uses DataFrameABCCore;
 
-const DataFrameVersion = '1.0';
+const DataFrameVersion = '1.1';
 
 // Реэкспортируем публичные типы для удобства
 type
@@ -93,6 +93,9 @@ type
     
     function GetColumnIndex(name: string): integer;
     function GetColumn(name: string): Column;
+    
+    function CloneWithCopiedColumns: DataFrame;
+    static procedure EnsureValidArray(var valid: array of boolean; rowCount, filledCount: integer);
   public
     /// Создает пустой DataFrame
     constructor Create;
@@ -2475,7 +2478,7 @@ begin
       cnt += 1;
     end;
 
-  if cnt = 0 then
+  if cnt <= 1 then
     exit(0.0);
 
   var mean := sum / cnt;
@@ -2491,7 +2494,7 @@ begin
       acc += d * d;
     end;
 
-  Result := acc / cnt;
+  Result := acc / (cnt - 1);
 end;
 
 function DataFrame.Variance(colName: string): real
@@ -3182,14 +3185,10 @@ begin
   Result := columns[idx];
 end;
 
-function DataFrame.WithColumnInt(name: string; f: DataFrameCursor -> integer): DataFrame;
+function DataFrame.CloneWithCopiedColumns: DataFrame;
 begin
-  if fSchema.HasColumn(name) then
+  Result := new DataFrame;
-    ArgumentError(ER_COLUMN_ALREADY_EXISTS, name);
-  
-  var res := new DataFrame;
 
-  // 1. копируем столбцы (без categorical!)
   for var i := 0 to columns.Count - 1 do
   begin
     var col := columns[i];
@@ -3198,30 +3197,47 @@ begin
       ctInt:
       begin
         var c := IntColumn(col);
-        res.AddIntColumn(c.Info.Name, c.Data, c.IsValid);
+        Result.AddIntColumn(c.Info.Name, c.Data, c.IsValid);
       end;
 
       ctStr:
       begin
         var c := StrColumn(col);
-        res.AddStrColumn(c.Info.Name, c.Data, c.IsValid);
+        Result.AddStrColumn(c.Info.Name, c.Data, c.IsValid);
       end;
 
       ctFloat:
       begin
         var c := FloatColumn(col);
-        res.AddFloatColumn(c.Info.Name, c.Data, c.IsValid);
+        Result.AddFloatColumn(c.Info.Name, c.Data, c.IsValid);
       end;
 
       ctBool:
       begin
         var c := BoolColumn(col);
-        res.AddBoolColumn(c.Info.Name, c.Data, c.IsValid);
+        Result.AddBoolColumn(c.Info.Name, c.Data, c.IsValid);
       end;
     end;
   end;
+end;
+
+static procedure DataFrame.EnsureValidArray(var valid: array of boolean; rowCount, filledCount: integer);
+begin
+  if valid = nil then
+  begin
+    valid := new boolean[rowCount];
+    for var j := 0 to filledCount - 1 do
+      valid[j] := true;
+  end;
+end;
+
+function DataFrame.WithColumnInt(name: string; f: DataFrameCursor -> integer): DataFrame;
+begin
+  if fSchema.HasColumn(name) then
+    ArgumentError(ER_COLUMN_ALREADY_EXISTS, name);
+
+  var res := CloneWithCopiedColumns;
 
-  // 2. вычисляем новый столбец
   var data := new integer[RowCount];
   var valid: array of boolean := nil;
 
@@ -3236,14 +3252,7 @@ begin
       on e: Exception do
       begin
         data[i] := 0;
-
+        EnsureValidArray(valid, RowCount, i);
-        if valid = nil then
-        begin
-          valid := new boolean[RowCount];
-          for var j := 0 to i - 1 do
-            valid[j] := true;
-        end;
-
         valid[i] := false;
         i += 1;
         continue;
@@ -3256,13 +3265,10 @@ begin
     i += 1;
   end;
 
-  // 3. добавляем новый столбец
   res.AddIntColumn(name, data, valid);
-
   res.SetSchema(ExtendSchema(name, ctInt, false));
 
   Result := res;
-
   AssertSchemaConsistent;
 end;
 
@@ -3270,41 +3276,9 @@ function DataFrame.WithColumnFloat(name: string; f: DataFrameCursor -> real): Da
 begin
   if fSchema.HasColumn(name) then
     ArgumentError(ER_COLUMN_ALREADY_EXISTS, name);
-  
-  var res := new DataFrame;
 
-  // 1. копируем существующие колонки
+  var res := CloneWithCopiedColumns;
-  for var i := 0 to columns.Count - 1 do
-  begin
-    var col := columns[i];
-    case col.Info.ColType of
-      ctInt:
-      begin
-        var c := IntColumn(col);
-        res.AddIntColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
 
-      ctStr:
-      begin
-        var c := StrColumn(col);
-        res.AddStrColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-
-      ctFloat:
-      begin
-        var c := FloatColumn(col);
-        res.AddFloatColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-
-      ctBool:
-      begin
-        var c := BoolColumn(col);
-        res.AddBoolColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-    end;
-  end;
-
-  // 2. вычисляем новый столбец
   var data := new real[RowCount];
   var valid: array of boolean := nil;
 
@@ -3316,16 +3290,10 @@ begin
     try
       data[i] := f(cur);
     except
+      on e: Exception do
       begin
         data[i] := 0.0;
-
+        EnsureValidArray(valid, RowCount, i);
-        if valid = nil then
-        begin
-          valid := new boolean[RowCount];
-          for var j := 0 to i - 1 do
-            valid[j] := true;
-        end;
-
         valid[i] := false;
         i += 1;
         continue;
@@ -3338,13 +3306,10 @@ begin
     i += 1;
   end;
 
-  // 3. добавляем новый столбец
   res.AddFloatColumn(name, data, valid);
-
   res.SetSchema(ExtendSchema(name, ctFloat, false));
 
   Result := res;
-
   AssertSchemaConsistent;
 end;
 
@@ -3352,41 +3317,9 @@ function DataFrame.WithColumnStr(name: string; f: DataFrameCursor -> string): Da
 begin
   if fSchema.HasColumn(name) then
     ArgumentError(ER_COLUMN_ALREADY_EXISTS, name);
-  
-  var res := new DataFrame;
 
-  // 1. копируем существующие колонки
+  var res := CloneWithCopiedColumns;
-  for var i := 0 to columns.Count - 1 do
-  begin
-    var col := columns[i];
-    case col.Info.ColType of
-      ctInt:
-      begin
-        var c := IntColumn(col);
-        res.AddIntColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
 
-      ctStr:
-      begin
-        var c := StrColumn(col);
-        res.AddStrColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-
-      ctFloat:
-      begin
-        var c := FloatColumn(col);
-        res.AddFloatColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-
-      ctBool:
-      begin
-        var c := BoolColumn(col);
-        res.AddBoolColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-    end;
-  end;
-
-  // 2. вычисляем новый столбец
   var data := new string[RowCount];
   var valid: array of boolean := nil;
 
@@ -3398,16 +3331,10 @@ begin
     try
       data[i] := f(cur);
     except
+      on e: Exception do
       begin
-        data[i] := '';
+        data[i] := nil;
-
+        EnsureValidArray(valid, RowCount, i);
-        if valid = nil then
-        begin
-          valid := new boolean[RowCount];
-          for var j := 0 to i - 1 do
-            valid[j] := true;
-        end;
-
         valid[i] := false;
         i += 1;
         continue;
@@ -3420,13 +3347,10 @@ begin
     i += 1;
   end;
 
-  // 3. добавляем новый столбец
   res.AddStrColumn(name, data, valid);
-
   res.SetSchema(ExtendSchema(name, ctStr, false));
 
   Result := res;
-
   AssertSchemaConsistent;
 end;
 
@@ -3434,41 +3358,9 @@ function DataFrame.WithColumnBool(name: string; f: DataFrameCursor -> boolean):
 begin
   if fSchema.HasColumn(name) then
     ArgumentError(ER_COLUMN_ALREADY_EXISTS, name);
-  
-  var res := new DataFrame;
 
-  // 1. копируем существующие колонки
+  var res := CloneWithCopiedColumns;
-  for var i := 0 to columns.Count - 1 do
-  begin
-    var col := columns[i];
-    case col.Info.ColType of
-      ctInt:
-      begin
-        var c := IntColumn(col);
-        res.AddIntColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
 
-      ctStr:
-      begin
-        var c := StrColumn(col);
-        res.AddStrColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-
-      ctFloat:
-      begin
-        var c := FloatColumn(col);
-        res.AddFloatColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-
-      ctBool:
-      begin
-        var c := BoolColumn(col);
-        res.AddBoolColumn(c.Info.Name, c.Data, c.IsValid);
-      end;
-    end;
-  end;
-
-  // 2. вычисляем новый столбец
   var data := new boolean[RowCount];
   var valid: array of boolean := nil;
 
@@ -3480,16 +3372,10 @@ begin
     try
       data[i] := f(cur);
     except
+      on e: Exception do
       begin
         data[i] := false;
-
+        EnsureValidArray(valid, RowCount, i);
-        if valid = nil then
-        begin
-          valid := new boolean[RowCount];
-          for var j := 0 to i - 1 do
-            valid[j] := true;
-        end;
-
         valid[i] := false;
         i += 1;
         continue;
@@ -3502,13 +3388,10 @@ begin
     i += 1;
   end;
 
-  // 3. добавляем новый столбец
   res.AddBoolColumn(name, data, valid);
-
   res.SetSchema(ExtendSchema(name, ctBool, false));
 
   Result := res;
-
   AssertSchemaConsistent;
 end;
 
@@ -3549,27 +3432,56 @@ begin
 
   var cur := GetCursor;
   var row := 0;
+
   while cur.MoveNext do
   begin
+    // --- NA: обрабатываем явно, без исключений
+    if not cur.IsValid(colIndex) then
+    begin
+      data[row] := 0.0;
+
+      if valid = nil then
+      begin
+        valid := new boolean[rowCount];
+        for var j := 0 to row - 1 do
+          valid[j] := true;
+      end;
+
+      valid[row] := false;
+      row += 1;
+      continue;
+    end;
+
+    // --- вычисление
     try
       data[row] := f(cur);
-      if valid <> nil then valid[row] := true;
     except
       on e: Exception do
       begin
         data[row] := 0.0;
+
         if valid = nil then
         begin
           valid := new boolean[rowCount];
-          for var j := 0 to row - 1 do valid[j] := true;
+          for var j := 0 to row - 1 do
+            valid[j] := true;
         end;
+
         valid[row] := false;
+        row += 1;
+        continue;
       end;
     end;
+
+    if valid <> nil then
+      valid[row] := true;
+
     row += 1;
   end;
 
+  // --- сборка результата
   var res := new DataFrame;
+
   for var i := 0 to columns.Count - 1 do
     if i <> colIndex then
       res.AddColumnView(columns[i])
@@ -5452,11 +5364,8 @@ begin
     Error(ER_ZERO_STD_STANDARDIZE);
 
   Result := df.ReplaceColumnFloat(colName, cur ->
-  begin
+    (cur.Float(idx) - mean) / std
-    if not cur.IsValid(idx) then
+  );
-      Error(ER_INVALID_VALUE_IN_COLUMN, colName);
-    Result := (cur.Float(idx) - mean) / std;
-  end);
 end;
 
 static function Statistics.StandardizeAll(df: DataFrame): DataFrame;
@@ -5653,37 +5562,6 @@ end;
 //          CSVLoader
 //-----------------------------
 
-{procedure ScanFields(line: string; delimiter: char;
-  starts, lens: array of integer; var actualCount: integer);
-begin
-  var j := 1;
-  var col := 0;
-  var n := line.Length;
-
-  starts[0] := 1;
-
-  while j <= n do
-  begin
-    if line[j] = delimiter then
-    begin
-      if col < starts.Length then
-        lens[col] := j - starts[col];
-      col += 1;
-      if col < starts.Length then
-        starts[col] := j + 1;
-    end;
-    j += 1;
-  end;
-
-  if col < starts.Length then
-    lens[col] := n - starts[col] + 1;
-
-  for var k := col + 1 to starts.Length - 1 do
-    lens[k] := 0;
-
-  actualCount := col + 1;
-end;}
-
 procedure ScanFieldsQuoted(
   line: string; delimiter: char;
   starts, lens: array of integer;
@@ -6466,13 +6344,34 @@ begin
     System.IO.FileShare.ReadWrite
   );
   try
+    // --- BOM check
     var bom := new byte[3];
     var n := fs.Read(bom, 0, 3);
-    
+
+    // UTF-8 BOM
     if (n >= 3) and (bom[0] = $EF) and (bom[1] = $BB) and (bom[2] = $BF) then
-      Result := Encoding.UTF8
+      exit(Encoding.UTF8);
-    else
+
-      Result := Encoding.UTF8;
+    // --- reset position
+    fs.Position := 0;
+
+    // --- read small chunk
+    var bufferSize := 4096;
+    var buffer := new byte[bufferSize];
+    var readBytes := fs.Read(buffer, 0, bufferSize);
+
+    // --- strict UTF-8 check
+    try
+      var utf8 := new System.Text.UTF8Encoding(false, true); // strict
+      utf8.GetString(buffer, 0, readBytes);
+      exit(Encoding.UTF8);
+    except
+      // not UTF-8
+    end;
+
+    // --- fallback
+    Result := Encoding.Default;
+
   finally
     fs.Close;
   end;

bin/Lib/DataFrameABCCore.pas

@@ -789,7 +789,14 @@ end;}
 
 function JoinKey.Equals(oth: object): boolean;
 begin
-  var other: JoinKey := JoinKey(oth);
+  if oth = nil then
+    exit(false);
+
+  if not (oth is JoinKey) then
+    exit(false);
+
+  var other := JoinKey(oth);
+
   if Ints.Length <> other.Ints.Length then exit(false);
   if Floats.Length <> other.Floats.Length then exit(false);
   if Strs.Length <> other.Strs.Length then exit(false);

bin/Lib/LinearAlgebraML.pas

@@ -327,6 +327,9 @@ const
   ER_SINGULAR_MATRIX =
     'Матрица вырождена или плохо обусловлена!!Matrix is singular or ill-conditioned';
   
+type
+  MLNotSPDException = class(MLException);
+    
 //-----------------------------
 //           Vector
 //-----------------------------
@@ -1254,7 +1257,6 @@ begin
 end;
 
 
-
 // Helper
 function Cholesky(A: Matrix): Matrix;
 begin
@@ -1274,7 +1276,7 @@ begin
       if i = j then
       begin
         if s <= 0.0 then
-          Error(ER_MATRIX_NOT_SPD);
+          raise new MLNotSPDException('Матрица не является положительно определённой (SPD)');
         L[i, i] := Sqrt(s);
       end
       else
@@ -1423,6 +1425,7 @@ begin
     DimensionError(ER_VECTOR_SIZE_MISMATCH, b.Length, A.RowCount);
   
   var L := Cholesky(A);
+
   var y := SolveLowerTriangular(L, b);
   Result := SolveUpperTriangular(L.Transpose, y);
 end;
@@ -1432,7 +1435,8 @@ begin
   try
     Result := SolveSPD(A, b);
   except
-    Result := Solve(A, b);
+    on e: MLNotSPDException do
+      Result := Solve(A, b);
   end;
 end;
 

bin/Lib/MLABC.pas

@@ -92,7 +92,7 @@ type
   
   IModel = MLCoreABC.IModel;
   ISupervisedModel = MLCoreABC.ISupervisedModel;
-  IUnSupervisedModel = MLCoreABC.IUnSupervisedModel;
+  IUnsupervisedModel = MLCoreABC.IUnsupervisedModel;
   UPipeline = MLModelsABC.UPipeline;
   UDataPipeline = MLPipelineABC.UDataPipeline;
   TaskKind = MLPipelineABC.TaskKind;

bin/Lib/MLDatasets.pas

@@ -1303,26 +1303,31 @@ end;
 
 static function Datasets.StudentExam: Dataset;
 begin
+  NotImplementedError(ER_NOT_IMPLEMENTED, 'Datasets.StudentExam');
   Result := nil;
 end;
 
 static function Datasets.BankClients: Dataset;
 begin
+  NotImplementedError(ER_NOT_IMPLEMENTED, 'Datasets.BankClients');
   Result := nil;
 end;
 
 static function Datasets.TaxiTrips: Dataset;
 begin
+  NotImplementedError(ER_NOT_IMPLEMENTED, 'Datasets.TaxiTrips');
   Result := nil;
 end;
 
 static function Datasets.MoscowTransport: Dataset;
 begin
+  NotImplementedError(ER_NOT_IMPLEMENTED, 'Datasets.MoscowTransport');
   Result := nil;
 end;
 
 static function Datasets.OnlineShopping: Dataset;
 begin
+  NotImplementedError(ER_NOT_IMPLEMENTED, 'Datasets.OnlineShopping');
   Result := nil;
 end;
 

bin/Lib/MLExceptions.pas

@@ -23,7 +23,9 @@ const
     'Пустой набор данных для {0}!!Empty dataset for {0}';
   ER_COLUMN_NOT_FOUND =
     'В DataFrame отсутствует столбец "{0}"!!DataFrame does not contain column "{0}"';  
-    
+  ER_NOT_IMPLEMENTED = 
+    'Метод {0} не реализован!!Method {0} is not implemented';
+  
 type
   /// Базовое исключение ML-библиотеки
   MLException = class(Exception);
@@ -33,6 +35,8 @@ type
 
   /// Несоответствие размерностей
   MLDimensionException = class(MLException);
+  
+  MLNotImplementedException = class(MLException);
 
 procedure Error(msg: string; params args: array of object);
 procedure ArgumentError(msg: string; params args: array of object);
@@ -40,6 +44,7 @@ procedure NotFittedError(msg: string; params args: array of object);
 procedure DimensionError(msg: string; params args: array of object);
 procedure ArgumentNullError(msg: string; params args: array of object);
 procedure ArgumentOutOfRangeError(msg: string; params args: array of object);
+procedure NotImplementedError(msg: string; params args: array of object);
 
 implementation
 
@@ -83,4 +88,10 @@ begin
   raise new System.ArgumentOutOfRangeException(FormatSafe(msg, args));
 end;
 
+procedure NotImplementedError(msg: string; params args: array of object);
+begin
+  raise new MLNotImplementedException(FormatSafe(msg, args));
+end;
+  
+
 end.

bin/Lib/MLModelsABC.pas

@@ -1013,7 +1013,7 @@ type
       : ISupervisedModel;
 
     procedure BuildClassMapping(y: Vector);
-    function EncodeLabels(y: Vector): array of integer;
+    function ApplyLabelEncoding(y: Vector): array of integer;
 
     procedure SoftmaxRow(var logits: array of real; var probs: array of real);
     procedure SoftmaxMatrix(logits: Matrix; probs: Matrix);
@@ -1339,7 +1339,6 @@ type
   private
     fEps: real;
     fMinSamples: integer;
-    fSeed: integer;
   
     fFitted: boolean;
     fFeatureCount: integer;
@@ -1356,8 +1355,7 @@ type
     /// seed — параметр для совместимости API.
     constructor Create(
       eps: real;
-      minSamples: integer := 5;
+      minSamples: integer := 5
-      seed: integer := -1
     );
   
     /// Обучает модель на матрице признаков.
@@ -3506,18 +3504,6 @@ begin
   if X.RowCount <> y.Length then
     DimensionError(ER_DIM_MISMATCH, X.RowCount, y.Length);
 
-  if fMinSamplesSplit < 2 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESSPLIT_INVALID, fMinSamplesSplit);
-
-  if fMinSamplesLeaf < 1 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESLEAF_INVALID, fMinSamplesLeaf);
-
-  if fMaxDepth < -1 then
-    ArgumentOutOfRangeError(ER_MAX_DEPTH_INVALID, fMaxDepth);
-
-  if fMaxDepth > 10000 then
-    ArgumentError(ER_MAX_DEPTH_TOO_LARGE, fMaxDepth);
-  
   
   fFeatureImportances := new Vector(X.ColCount);
 
@@ -3758,21 +3744,9 @@ begin
   if X.RowCount <> y.Length then
     DimensionError(ER_DIM_MISMATCH, X.RowCount, y.Length);
 
-  if fMinSamplesSplit < 2 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESSPLIT_INVALID, fMinSamplesSplit);
-
-  if fMinSamplesLeaf < 1 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESLEAF_INVALID, fMinSamplesLeaf);
-
   if fLeafL2 < 0 then
     ArgumentOutOfRangeError(ER_L2_NEGATIVE, fLeafL2);
 
-  if fMaxDepth < -1 then
-    ArgumentOutOfRangeError(ER_MAX_DEPTH_INVALID, fMaxDepth);
-
-  if fMaxDepth > 10000 then
-    ArgumentError(ER_MAX_DEPTH_TOO_LARGE, fMaxDepth);
-  
   fFeatureImportances := new Vector(X.ColCount);
 
   var indices: array of integer;
@@ -3986,24 +3960,6 @@ begin
   if X.RowCount <> y.Length then
     DimensionError(ER_DIM_MISMATCH, X.RowCount, y.Length);
 
-  if fNTrees <= 0 then
-    ArgumentOutOfRangeError(ER_NTREES_INVALID, fNTrees);
-
-  if fMinSamplesSplit < 2 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESSPLIT_INVALID, fMinSamplesSplit);
-
-  if fMinSamplesLeaf < 1 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESLEAF_INVALID, fMinSamplesLeaf);
-
-  if fMinSamplesLeaf >= fMinSamplesSplit then
-    ArgumentError(ER_MIN_LEAF_GE_SPLIT, fMinSamplesLeaf, fMinSamplesSplit);
-
-  if fMaxDepth < -1 then
-    ArgumentOutOfRangeError(ER_MAX_DEPTH_INVALID, fMaxDepth);
-
-  if fMaxDepth > MAX_ALLOWED_TREE_DEPTH then
-    ArgumentError(ER_MAX_DEPTH_TOO_LARGE, fMaxDepth);
-
   var n := X.RowCount;
   var p := X.ColCount;
 
@@ -4231,24 +4187,6 @@ begin
   if X.RowCount <> y.Length then
     DimensionError(ER_DIM_MISMATCH, X.RowCount, y.Length);
 
-  if fNTrees <= 0 then
-    ArgumentOutOfRangeError(ER_NTREES_INVALID, fNTrees);
-
-  if fMinSamplesSplit < 2 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESSPLIT_INVALID, fMinSamplesSplit);
-
-  if fMinSamplesLeaf < 1 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESLEAF_INVALID, fMinSamplesLeaf);
-
-  if fMinSamplesLeaf >= fMinSamplesSplit then
-    ArgumentError(ER_MIN_LEAF_GE_SPLIT, fMinSamplesLeaf, fMinSamplesSplit);
-
-  if fMaxDepth < -1 then
-    ArgumentOutOfRangeError(ER_MAX_DEPTH_INVALID, fMaxDepth);
-
-  if fMaxDepth > MAX_ALLOWED_TREE_DEPTH then
-    ArgumentError(ER_MAX_DEPTH_TOO_LARGE, fMaxDepth);
-
   var n := X.RowCount;
   var p := X.ColCount;
 
@@ -4594,6 +4532,51 @@ begin
   Result := fClassLabels;
 end;
 
+//-----------------------------
+//      Helper GBC GBR
+//-----------------------------
+
+function BuildSubsampleIndices(nTrain: integer; subsample: real; rng: System.Random): array of integer;
+begin
+  if nTrain <= 0 then
+    ArgumentOutOfRangeError(ER_EMPTY_DATASET);
+
+  if (subsample <= 0.0) or (subsample > 1.0) then
+    ArgumentOutOfRangeError(ER_SUBSAMPLE_INVALID, subsample);
+
+  var k := Floor(nTrain * subsample);
+  if k < 1 then
+    k := 1;
+  if k > nTrain then
+    k := nTrain;
+
+  // если берём всё — можно быстро вернуть [0..nTrain-1]
+  if k = nTrain then
+  begin
+    Result := new integer[nTrain];
+    for var i := 0 to nTrain - 1 do
+      Result[i] := i;
+    exit;
+  end;
+
+  var all := new integer[nTrain];
+  for var i := 0 to nTrain - 1 do
+    all[i] := i;
+
+  // partial Fisher–Yates (без повторений)
+  for var i := 0 to k - 1 do
+  begin
+    var j := i + rng.Next(nTrain - i);
+    var tmp := all[i];
+    all[i] := all[j];
+    all[j] := tmp;
+  end;
+
+  Result := new integer[k];
+  for var i := 0 to k - 1 do
+    Result[i] := all[i];
+end;
+
 //-----------------------------
 //  GradientBoostingRegressor 
 //-----------------------------
@@ -4629,6 +4612,9 @@ begin
   
   if minSamplesLeaf < 1 then
     ArgumentOutOfRangeError(ER_MIN_SAMPLES_LEAF_INVALID, minSamplesLeaf);
+  
+  if maxDepth > MAX_ALLOWED_TREE_DEPTH then
+    ArgumentOutOfRangeError(ER_MAX_DEPTH_TOO_LARGE, maxDepth);
 
   fNEstimators := nEstimators;
   fLearningRate := learningRate;
@@ -4905,28 +4891,6 @@ begin
       DimensionError(ER_FEATURE_COUNT_MISMATCH);
   end;
 
-  // --- hyperparameter checks ---
-  if fNEstimators <= 0 then
-    ArgumentOutOfRangeError(ER_NESTIMATORS_INVALID, fNEstimators);
-
-  if fLearningRate <= 0 then
-    ArgumentOutOfRangeError(ER_LEARNING_RATE_INVALID, fLearningRate);
-
-  if (fSubsample <= 0.0) or (fSubsample > 1.0) then
-    ArgumentOutOfRangeError(ER_SUBSAMPLE_INVALID, fSubsample);
-
-  if fMinSamplesSplit < 2 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESSPLIT_INVALID, fMinSamplesSplit);
-
-  if fMinSamplesLeaf < 1 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESLEAF_INVALID, fMinSamplesLeaf);
-
-  if fMaxDepth < 0 then
-    ArgumentOutOfRangeError(ER_MAX_DEPTH_INVALID, fMaxDepth);
-
-  if fMaxDepth > MAX_ALLOWED_TREE_DEPTH then
-    ArgumentError(ER_MAX_DEPTH_TOO_LARGE, fMaxDepth);
-
   // --- init state ---
   fOOBLossHistory.Clear;
   fEstimators.Clear;
@@ -4994,40 +4958,20 @@ begin
     // --- subsample ---
     var rows: array of integer := nil;
     var used: array of boolean := nil;
-
+    
     if useSubsample then
     begin
-      var k := Floor(nTrain * fSubsample);
+      rows := BuildSubsampleIndices(nTrain, fSubsample, fRng);
-      if k < 1 then k := 1;
-      if k > nTrain then k := nTrain;
-
-      var all := new integer[nTrain];
-      for var i := 0 to nTrain - 1 do
-        all[i] := i;
-
-      // partial Fisher–Yates
-      for var i := 0 to k - 1 do
-      begin
-        var j := i + fRng.Next(nTrain - i);
-        var tmp := all[i];
-        all[i] := all[j];
-        all[j] := tmp;
-      end;
-
-      rows := new integer[k];
-      for var i := 0 to k - 1 do
-        rows[i] := all[i];
-
       tree.SetRowIndices(rows);
-
+    
       if useOOB then
       begin
         used := new boolean[nTrain];
-        for var i := 0 to k - 1 do
+        for var i := 0 to rows.Length - 1 do
           used[rows[i]] := true;
       end;
     end;
-
+    
     tree.Fit(XTrain, r);
     fEstimators.Add(tree);
 
@@ -5399,6 +5343,7 @@ begin
   Result := copy;
 end;
 
+
 //-----------------------------
 // GradientBoostingClassifier 
 //-----------------------------
@@ -5450,28 +5395,6 @@ begin
       DimensionError(ER_FEATURE_COUNT_MISMATCH);
   end;
 
-  // --- hyperparameter checks ---
-  if fNEstimators <= 0 then
-    ArgumentOutOfRangeError(ER_NESTIMATORS_INVALID, fNEstimators);
-
-  if fLearningRate <= 0 then
-    ArgumentOutOfRangeError(ER_LEARNING_RATE_INVALID, fLearningRate);
-
-  if (fSubsample <= 0.0) or (fSubsample > 1.0) then
-    ArgumentOutOfRangeError(ER_SUBSAMPLE_INVALID, fSubsample);
-
-  if fMinSamplesSplit < 2 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESSPLIT_INVALID, fMinSamplesSplit);
-
-  if fMinSamplesLeaf < 1 then
-    ArgumentOutOfRangeError(ER_MINSAMPLESLEAF_INVALID, fMinSamplesLeaf);
-
-  if fMaxDepth < 0 then
-    ArgumentOutOfRangeError(ER_MAX_DEPTH_INVALID, fMaxDepth);
-
-  if fMaxDepth > MAX_ALLOWED_TREE_DEPTH then
-    ArgumentError(ER_MAX_DEPTH_TOO_LARGE, fMaxDepth);
-
   // --- reset state
   fOOBLossHistory.Clear;
   fEstimators.Clear;
@@ -5485,7 +5408,7 @@ begin
 
   // --- mapping
   BuildClassMapping(yTrain);
-  var yEncoded := EncodeLabels(yTrain);
+  var yEncoded := ApplyLabelEncoding(yTrain);
 
   var nTrain := XTrain.RowCount;
   var classCount := fClassCount;
@@ -5540,7 +5463,7 @@ begin
   if useValidation then
   begin
     logitsVal := new Matrix(XVal.RowCount, classCount);
-    yValEncoded := EncodeLabels(yVal);
+    yValEncoded := ApplyLabelEncoding(yVal);
   
     // --- инициализация log-prior
     for var i := 0 to XVal.RowCount - 1 do
@@ -5578,6 +5501,11 @@ begin
     // inBag
     var inBag: array of boolean := nil;
     
+    if useSubsample then
+    begin
+      subIndices := BuildSubsampleIndices(nTrain, fSubsample, fRng);
+    end;
+    
     if useOOB then
     begin
       SetLength(inBag, nTrain);
@@ -5741,7 +5669,7 @@ begin
     fClassIndex[fClasses[cls]] := cls;
 end;
 
-function GradientBoostingClassifier.EncodeLabels(y: Vector): array of integer;
+function GradientBoostingClassifier.ApplyLabelEncoding(y: Vector): array of integer;
 begin
   var n := y.Length;
   Result := new integer[n];
@@ -7297,8 +7225,7 @@ end;
 
 constructor DBSCAN.Create(
   eps: real;
-  minSamples: integer;
+  minSamples: integer
-  seed: integer
 );
 begin
   if eps <= 0 then
@@ -7309,7 +7236,6 @@ begin
 
   fEps := eps;
   fMinSamples := minSamples;
-  fSeed := seed;
 
   fFitted := False;
 end;
@@ -7454,7 +7380,7 @@ end;
 
 function DBSCAN.Clone: IModel;
 begin
-  var m := new DBSCAN(fEps, fMinSamples, fSeed);
+  var m := new DBSCAN(fEps, fMinSamples);
 
   m.fFitted := fFitted;
   m.fFeatureCount := fFeatureCount;

bin/Lib/PlotML.pas

@@ -101,8 +101,6 @@ type
     procedure Hist(x: Vector; bins: integer := 0;
       color: ColorWPF := DefaultColor; alpha: real := 0.7; legend: string := nil);
       
-    //procedure Surface(labels: array of integer; nx, ny: integer; xmin, xmax, ymin, ymax: real; pal: PlotML.Palette := nil);
-    
     procedure Surface(x1, x2: array of real; nx, ny: integer; f: Matrix -> array of integer; pal: PlotML.Palette := nil);      
       
     procedure Heatmap(m: Matrix);
@@ -1319,16 +1317,6 @@ begin
   end;
 end;
 
-{procedure Cell.Surface(labels: array of integer; nx, ny: integer; xmin, xmax, ymin, ymax: real; pal: PlotML.Palette);
-begin
-  Plot.RunUI(() ->
-  begin
-    EnsureChart;
-    var usePal := if pal <> nil then pal else palette;
-    Plot.DrawSurface(chart, labels, nx, ny, xmin, xmax, ymin, ymax, usePal);
-  end);
-end;}
-
 procedure Cell.Surface(x1, x2: array of real; nx, ny: integer; f: Matrix -> array of integer; pal: PlotML.Palette);
 begin
   Plot.RunUI(() ->

bin/Lib/ValidationML.pas

@@ -69,7 +69,8 @@ type
     X: Matrix; y: Vector;
     k: integer;
     metric: (Vector, Vector) -> real;
-    maximize: boolean := True
+    maximize: boolean := True;
+    seed: integer := -1
   ): (real, real, T); where T: class,ISupervisedModel;
   end;
 
@@ -447,7 +448,8 @@ class function GridSearch.Search<T>(
   y: Vector;
   k: integer;
   metric: (Vector, Vector) -> real;
-  maximize: boolean
+  maximize: boolean;
+  seed: integer
 ): (real, real, T); where T: class,ISupervisedModel;
 begin
   if modelFactory = nil then
@@ -480,7 +482,7 @@ begin
     var model := modelFactory(param);
     if model = nil then
       ArgumentError(ER_MODEL_NULL);
-    var avgScore := Validation.CrossValidate(model, X, y, k, metric);
+    var avgScore := Validation.CrossValidate(model, X, y, k, metric, seed);
 
     if double.IsNaN(avgScore) or double.IsInfinity(avgScore) then
       ArgumentError(ER_INVALID_VALUE, 'avgScore');