Removed unnecessary StdHandlers module and cleaned up the source code.

EasyMLCore/Data/FeatureFilter/FeatureFilterBase.cs

@@ -75,7 +75,7 @@ protected FeatureFilterBase(FeatureFilterBase source)
         {
             ValueType = source.ValueType;
             Use = source.Use;
-            SamplesStat = new BasicStat(source.SamplesStat);
+            SamplesStat = source.SamplesStat.DeepClone();
             return;
         }
 

EasyMLCore/Data/TaskErrStat/CategoricalErrStat.cs

@@ -68,9 +68,9 @@ public CategoricalErrStat(IComputableTaskSpecific computableUnit, SampleDataset
         public CategoricalErrStat(CategoricalErrStat source)
             : base(source)
         {
-            ClassificationLogLossStat = new BasicStat(source.ClassificationLogLossStat);
-            WrongClassificationStat = new BasicStat(source.WrongClassificationStat);
-            LowProbabilityClassificationStat = new BasicStat(source.LowProbabilityClassificationStat);
+            ClassificationLogLossStat = source.ClassificationLogLossStat.DeepClone();
+            WrongClassificationStat = source.WrongClassificationStat.DeepClone();
+            LowProbabilityClassificationStat = source.LowProbabilityClassificationStat.DeepClone();
             return;
         }
 

EasyMLCore/Data/TaskErrStat/MultipleDecisionErrStat.cs

@@ -91,10 +91,10 @@ public MultipleDecisionErrStat(MultipleDecisionErrStat source)
                 FeatureBinDecisionStats[i] = new SingleDecisionErrStat(source.FeatureBinDecisionStats[i]);
             }
             TotalBinFalseFlagStat = new BasicStat[2];
-            TotalBinFalseFlagStat[0] = new BasicStat(source.TotalBinFalseFlagStat[0]);
-            TotalBinFalseFlagStat[1] = new BasicStat(source.TotalBinFalseFlagStat[1]);
-            TotalBinWrongDecisionStat = new BasicStat(source.TotalBinWrongDecisionStat);
-            TotalBinLogLossStat = new BasicStat(source.TotalBinLogLossStat);
+            TotalBinFalseFlagStat[0] = source.TotalBinFalseFlagStat[0].DeepClone();
+            TotalBinFalseFlagStat[1] = source.TotalBinFalseFlagStat[1].DeepClone();
+            TotalBinWrongDecisionStat = source.TotalBinWrongDecisionStat.DeepClone();
+            TotalBinLogLossStat = source.TotalBinLogLossStat.DeepClone();
             return;
         }
 

EasyMLCore/Data/TaskErrStat/MultiplePrecisionErrStat.cs

@@ -69,7 +69,7 @@ public MultiplePrecisionErrStat(MultiplePrecisionErrStat source)
             {
                 FeaturePrecisionStats[i] = new SinglePrecisionErrStat(source.FeaturePrecisionStats[i]);
             }
-            TotalPrecisionStat = new BasicStat(source.TotalPrecisionStat);
+            TotalPrecisionStat = source.TotalPrecisionStat.DeepClone();
             return;
         }
 

EasyMLCore/Data/TaskErrStat/SingleDecisionErrStat.cs

@@ -86,12 +86,12 @@ public SingleDecisionErrStat(IComputableTaskSpecific computableUnit, SampleDatas
         public SingleDecisionErrStat(SingleDecisionErrStat source)
             : base(source)
         {
-            IdealStat = new BasicStat(source.IdealStat);
+            IdealStat = source.IdealStat.DeepClone();
             FalseFlagStat = new BasicStat[2];
-            FalseFlagStat[0] = new BasicStat(source.FalseFlagStat[0]);
-            FalseFlagStat[1] = new BasicStat(source.FalseFlagStat[1]);
-            WrongDecisionStat = new BasicStat(source.WrongDecisionStat);
-            LogLossStat = new BasicStat(source.LogLossStat);
+            FalseFlagStat[0] = source.FalseFlagStat[0].DeepClone();
+            FalseFlagStat[1] = source.FalseFlagStat[1].DeepClone();
+            WrongDecisionStat = source.WrongDecisionStat.DeepClone();
+            LogLossStat = source.LogLossStat.DeepClone();
             return;
         }
 

EasyMLCore/Data/TaskErrStat/SinglePrecisionErrStat.cs

@@ -57,7 +57,7 @@ public SinglePrecisionErrStat(IComputableTaskSpecific computableUnit, SampleData
         public SinglePrecisionErrStat(SinglePrecisionErrStat source)
             : base(source)
         {
-            FeaturePrecisionStat = new BasicStat(source.FeaturePrecisionStat);
+            FeaturePrecisionStat = source.FeaturePrecisionStat.DeepClone();
             return;
         }
 

EasyMLCore/MLP/Model/MLPModelConfidenceMetrics.cs

@@ -77,7 +77,7 @@ BasicStat featureConfidencesStat
             CategoricalAccuracy = categoricalAccuracy;
             BinaryAccuracy = binaryAccuracy;
             FeatureConfidences = (double[])featureConfidences.Clone();
-            FeatureConfidencesStat = new BasicStat(featureConfidencesStat);
+            FeatureConfidencesStat = featureConfidencesStat.DeepClone();
             return;
         }
 

EasyMLCore/MLP/Model/Network/MLPEngine.cs

@@ -90,8 +90,8 @@ public MLPEngine(MLPEngine source)
                 LayerCollection.Add(layer.DeepClone());
             }
             _flatWeights = (double[])source._flatWeights.Clone();
-            HLWeightsStat = new BasicStat(source.HLWeightsStat);
-            OLWeightsStat = new BasicStat(source.OLWeightsStat);
+            HLWeightsStat = source.HLWeightsStat.DeepClone();
+            OLWeightsStat = source.OLWeightsStat.DeepClone();
             return;
         }
 

EasyMLCore/MLP/Model/RVFL/RVFLPreprocessor.cs

@@ -121,8 +121,8 @@ public RVFLPreprocessor(RVFLPreprocessor source)
             {
                 _inputFilters[i] = source._inputFilters[i].DeepClone();
             }
-            WeightsStat = new BasicStat(source.WeightsStat);
-            BiasesStat = new BasicStat(source.BiasesStat);
+            WeightsStat = source.WeightsStat.DeepClone();
+            BiasesStat = source.BiasesStat.DeepClone();
             Initialized = source.Initialized;
             return;
         }
@@ -185,15 +185,14 @@ RVFLModelConfig modelCfg
         /// <summary>
         /// Randomizes internal weights.
         /// </summary>
-        /// <param name="stdTrainingInputs">Standardized training input data.</param>
         /// <param name="rand">The random generator to be used.</param>
-        private void RandomizeWeights(double[][] stdTrainingInputs, Random rand)
+        private void RandomizeWeights(Random rand)
         {
             WeightsStat.Reset();
             BiasesStat.Reset();
             foreach (Layer layer in LayerCollection)
             {
-                layer.RandomizeWeights(stdTrainingInputs, _flatWeights, rand);
+                layer.RandomizeWeights(_flatWeights, rand);
                 WeightsStat.Merge(layer.WeightsStat);
                 BiasesStat.Merge(layer.BiasesStat);
             }
@@ -295,7 +294,7 @@ public SampleDataset Init(SampleDataset trainingData,
                     }
                 });
                 //New weights
-                RandomizeWeights(stdInputs, rand);
+                RandomizeWeights(rand);
                 //Activation statistics
                 BasicStat[][][] activationStats = new BasicStat[LayerCollection.Count][][];
                 BasicStat[][] weightStats = new BasicStat[LayerCollection.Count][];
@@ -312,8 +311,8 @@ public SampleDataset Init(SampleDataset trainingData,
                         {
                             activationStats[i][j][k] = new BasicStat();
                         }
-                        weightStats[i][j] = new BasicStat(LayerCollection[i].Pools[j].WeightsStat);
-                        biasStats[i][j] = new BasicStat(LayerCollection[i].Pools[j].BiasesStat);
+                        weightStats[i][j] = LayerCollection[i].Pools[j].WeightsStat.DeepClone();
+                        biasStats[i][j] = LayerCollection[i].Pools[j].BiasesStat.DeepClone();
                     }
                 }
                 //Output
@@ -421,8 +420,8 @@ internal Layer(Layer source)
                 NumOfLayerNeurons = source.NumOfLayerNeurons;
                 NumOfLayerWeights = source.NumOfLayerWeights;
                 NumOfPredictors = source.NumOfPredictors;
-                WeightsStat = new BasicStat(source.WeightsStat);
-                BiasesStat = new BasicStat(source.BiasesStat);
+                WeightsStat = source.WeightsStat.DeepClone();
+                BiasesStat = source.BiasesStat.DeepClone();
                 return;
             }
 
@@ -474,16 +473,15 @@ internal Layer DeepClone()
             /// <summary>
             /// Randomly initializes layer weights.
             /// </summary>
-            /// <param name="stdTrainingInputs">Standardized training input data.</param>
             /// <param name="flatWeights">RVFL's weights in a flat structure.</param>
             /// <param name="rand">Random generator to be used.</param>
-            internal void RandomizeWeights(double[][] stdTrainingInputs, double[] flatWeights, Random rand)
+            internal void RandomizeWeights(double[] flatWeights, Random rand)
             {
                 WeightsStat.Reset();
                 BiasesStat.Reset();
                 foreach (Pool pool in Pools)
                 {
-                    pool.RandomizeWeights(stdTrainingInputs, flatWeights, rand);
+                    pool.RandomizeWeights(flatWeights, rand);
                     WeightsStat.Merge(pool.WeightsStat);
                     BiasesStat.Merge(pool.BiasesStat);
                 }
@@ -571,8 +569,8 @@ public class Pool
                 public BasicStat BiasesStat { get; }
 
                 //Attributes
-                private double _scaleFactorW;
-                private double _scaleFactorB;
+                private readonly double _scaleFactorW;
+                private readonly double _scaleFactorB;
 
                 //Constructor
                 /// <summary>
@@ -591,8 +589,8 @@ internal Pool(Pool source)
                     BiasesStartFlatIdx = source.BiasesStartFlatIdx;
                     NeuronsStartFlatIdx = source.NeuronsStartFlatIdx;
                     NumOfAllWeights = source.NumOfAllWeights;
-                    WeightsStat = new BasicStat(source.WeightsStat);
-                    BiasesStat = new BasicStat(source.BiasesStat);
+                    WeightsStat = source.WeightsStat.DeepClone();
+                    BiasesStat = source.BiasesStat.DeepClone();
                     _scaleFactorW = source._scaleFactorW;
                     _scaleFactorB = source._scaleFactorB;
                     return;
@@ -644,10 +642,9 @@ internal Pool DeepClone()
                 /// <summary>
                 /// Randomly initializes pool weights.
                 /// </summary>
-                /// <param name="stdTrainingInputs">Standardized training input data.</param>
                 /// <param name="flatWeights">RVFL's weights in a flat structure.</param>
                 /// <param name="rand">Random generator to be used.</param>
-                internal void RandomizeWeights(double[][] stdTrainingInputs, double[] flatWeights, Random rand)
+                internal void RandomizeWeights(double[] flatWeights, Random rand)
                 {
                     double[] wBuff = new double[NumOfInputNodes * NumOfNeurons];
                     double[] bBuff = new double[NumOfNeurons];