More trainer extensions, bug fixes and consistency across trainer extensions

docs/code/MlNetCookBook.md

@@ -1331,7 +1331,7 @@ var learningPipeline = reader.MakeNewEstimator()
 IEstimator<ITransformer> dynamicPipe = learningPipeline.AsDynamic;
 
 // Create a binary classification trainer.
-var binaryTrainer = mlContext.BinaryClassification.Trainers.AveragedPerceptron();
+var binaryTrainer = mlContext.BinaryClassification.Trainers.AveragedPerceptron("Label", "Features");
 
 // Append the OVA learner to the pipeline.
 dynamicPipe = dynamicPipe.Append(new Ova(mlContext, binaryTrainer));

docs/samples/Microsoft.ML.Samples/Dynamic/MatrixFactorization.cs

@@ -71,8 +71,10 @@ public static void MatrixFactorizationInMemoryData()
             // Create a matrix factorization trainer which may consume "Value" as the training label, "MatrixColumnIndex" as the
             // matrix's column index, and "MatrixRowIndex" as the matrix's row index. Here nameof(...) is used to extract field
             // names' in MatrixElement class.
-            var pipeline = new MatrixFactorizationTrainer(mlContext, nameof(MatrixElement.Value),
-                nameof(MatrixElement.MatrixColumnIndex), nameof(MatrixElement.MatrixRowIndex),
+            var pipeline = new MatrixFactorizationTrainer(mlContext, 
+                nameof(MatrixElement.MatrixColumnIndex),
+                nameof(MatrixElement.MatrixRowIndex),
+                nameof(MatrixElement.Value),
                 advancedSettings: s =>
                 {
                     s.NumIterations = 10;

docs/samples/Microsoft.ML.Samples/Dynamic/SDCA.cs

@@ -48,7 +48,7 @@ public static void SDCA_BinaryClassification()
             // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
             // the "Features" column produced by FeaturizeText as the features column. 
             var pipeline = mlContext.Transforms.Text.FeaturizeText("SentimentText", "Features")
-                    .Append(mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscent(label: "Sentiment", features: "Features", l2Const: 0.001f));
+                    .Append(mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscent(labelColumn: "Sentiment", featureColumn: "Features", l2Const: 0.001f));
 
             // Step 3: Run Cross-Validation on this pipeline.
             var cvResults = mlContext.BinaryClassification.CrossValidate(data, pipeline, labelColumn: "Sentiment");
@@ -60,8 +60,8 @@ public static void SDCA_BinaryClassification()
             // we could do so by tweaking the 'advancedSetting'.
             var advancedPipeline = mlContext.Transforms.Text.FeaturizeText("SentimentText", "Features")
                                   .Append(mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscent
-                                  (label: "Sentiment",
-                                   features: "Features",
+                                  (labelColumn: "Sentiment",
+                                   featureColumn: "Features",
                                    advancedSettings: s=>
                                        {
                                            s.ConvergenceTolerance = 0.01f;   // The learning rate for adjusting bias from being regularized

docs/samples/Microsoft.ML.Samples/Static/FastTreeBinaryClassification.cs

@@ -89,7 +89,7 @@ public static void FastTreeBinaryClassification()
                             row.Features,
                             numTrees: 100, // try: (int) 20-2000
                             numLeaves: 20, // try: (int) 2-128
-                            minDatapointsInLeafs: 10, // try: (int) 1-100
+                            minDatapointsInLeaves: 10, // try: (int) 1-100
                             learningRate: 0.2))) // try: (float) 0.025-0.4
                 .Append(row => (
                     Label: row.Label,

docs/samples/Microsoft.ML.Samples/Static/FastTreeRegression.cs

@@ -47,7 +47,7 @@ public static void FastTreeRegression()
                                             r.features,
                                             numTrees: 100, // try: (int) 20-2000
                                             numLeaves: 20, // try: (int) 2-128
-                                            minDatapointsInLeafs: 10, // try: (int) 1-100
+                                            minDatapointsInLeaves: 10, // try: (int) 1-100
                                             learningRate: 0.2, // try: (float) 0.025-0.4    
                                         onFit: p => pred = p)
                                 )

src/Microsoft.ML.Ensemble/Trainer/Multiclass/MulticlassDataPartitionEnsembleTrainer.cs

@@ -59,7 +59,7 @@ public Arguments()
                 BasePredictors = new[]
                 {
                     ComponentFactoryUtils.CreateFromFunction(
-                        env => new MulticlassLogisticRegression(env, FeatureColumn, LabelColumn))
+                        env => new MulticlassLogisticRegression(env, LabelColumn, FeatureColumn))
                 };
             }
         }

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -28,10 +28,10 @@ protected BoostingFastTreeTrainerBase(IHostEnvironment env,
             string groupIdColumn,
             int numLeaves,
             int numTrees,
-            int minDocumentsInLeafs,
+            int minDatapointsInLeaves,
             double learningRate,
             Action<TArgs> advancedSettings)
-            : base(env, label, featureColumn, weightColumn, groupIdColumn, numLeaves, numTrees, minDocumentsInLeafs, advancedSettings)
+            : base(env, label, featureColumn, weightColumn, groupIdColumn, numLeaves, numTrees, minDatapointsInLeaves, advancedSettings)
         {
 
             if (Args.LearningRates != learningRate)

src/Microsoft.ML.FastTree/FastTree.cs

@@ -102,7 +102,7 @@ private protected FastTreeTrainerBase(IHostEnvironment env,
             string groupIdColumn,
             int numLeaves,
             int numTrees,
-            int minDocumentsInLeafs,
+            int minDatapointsInLeaves,
             Action<TArgs> advancedSettings)
             : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), TrainerUtils.MakeR4VecFeature(featureColumn), label, TrainerUtils.MakeR4ScalarWeightColumn(weightColumn), TrainerUtils.MakeU4ScalarColumn(groupIdColumn))
         {
@@ -112,7 +112,7 @@ private protected FastTreeTrainerBase(IHostEnvironment env,
             // override with the directly provided values.
             Args.NumLeaves = numLeaves;
             Args.NumTrees = numTrees;
-            Args.MinDocumentsInLeafs = minDocumentsInLeafs;
+            Args.MinDocumentsInLeafs = minDatapointsInLeaves;
 
             //apply the advanced args, if the user supplied any
             advancedSettings?.Invoke(Args);
@@ -121,10 +121,10 @@ private protected FastTreeTrainerBase(IHostEnvironment env,
             Args.FeatureColumn = featureColumn;
 
             if (weightColumn != null)
-                Args.WeightColumn = Optional<string>.Explicit(weightColumn); ;
+                Args.WeightColumn = Optional<string>.Explicit(weightColumn);
 
             if (groupIdColumn != null)
-                Args.GroupIdColumn = Optional<string>.Explicit(groupIdColumn); ;
+                Args.GroupIdColumn = Optional<string>.Explicit(groupIdColumn);
 
             // The discretization step renders this trainer non-parametric, and therefore it does not need normalization.
             // Also since it builds its own internal discretized columnar structures, it cannot benefit from caching.

src/Microsoft.ML.FastTree/FastTreeArguments.cs

@@ -143,7 +143,7 @@ internal static class Defaults
     {
         internal const int NumTrees = 100;
         internal const int NumLeaves = 20;
-        internal const int MinDocumentsInLeafs = 10;
+        internal const int MinDocumentsInLeaves = 10;
         internal const double LearningRates = 0.2;
     }
 
@@ -245,7 +245,7 @@ public abstract class TreeArgs : LearnerInputBaseWithGroupId
         [Argument(ArgumentType.LastOccurenceWins, HelpText = "The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data", ShortName = "mil", SortOrder = 3)]
         [TGUI(Description = "Minimum number of training instances required to form a leaf", SuggestedSweeps = "1,10,50")]
         [TlcModule.SweepableDiscreteParamAttribute("MinDocumentsInLeafs", new object[] { 1, 10, 50 })]
-        public int MinDocumentsInLeafs = Defaults.MinDocumentsInLeafs;
+        public int MinDocumentsInLeafs = Defaults.MinDocumentsInLeaves;
 
         // REVIEW: Different shortname than FastRank module. Same as the TLC FRWrapper.
         [Argument(ArgumentType.LastOccurenceWins, HelpText = "Total number of decision trees to create in the ensemble", ShortName = "iter", SortOrder = 1)]

src/Microsoft.ML.FastTree/FastTreeClassification.cs

@@ -123,20 +123,20 @@ public sealed partial class FastTreeBinaryClassificationTrainer :
         /// <param name="featureColumn">The name of the feature column.</param>
         /// <param name="weightColumn">The name for the column containing the initial weight.</param>
         /// <param name="learningRate">The learning rate.</param>
-        /// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
+        /// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
         /// <param name="numLeaves">The max number of leaves in each regression tree.</param>
         /// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
         /// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
         public FastTreeBinaryClassificationTrainer(IHostEnvironment env,
-            string labelColumn,
-            string featureColumn,
+            string labelColumn = DefaultColumnNames.Label,
+            string featureColumn = DefaultColumnNames.Features,
             string weightColumn = null,
             int numLeaves = Defaults.NumLeaves,
             int numTrees = Defaults.NumTrees,
-            int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
+            int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves,
             double learningRate = Defaults.LearningRates,
             Action<Arguments> advancedSettings = null)
-            : base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDocumentsInLeafs, learningRate, advancedSettings)
+            : base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDatapointsInLeaves, learningRate, advancedSettings)
         {
             // Set the sigmoid parameter to the 2 * learning rate, for traditional FastTreeClassification loss
             _sigmoidParameter = 2.0 * Args.LearningRates;

src/Microsoft.ML.FastTree/FastTreeRanking.cs

@@ -69,20 +69,20 @@ public sealed partial class FastTreeRankingTrainer
         /// <param name="weightColumn">The name for the column containing the initial weight.</param>
         /// <param name="numLeaves">The max number of leaves in each regression tree.</param>
         /// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
-        /// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
+        /// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
         /// <param name="learningRate">The learning rate.</param>
         /// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
         public FastTreeRankingTrainer(IHostEnvironment env,
-            string labelColumn,
-            string featureColumn,
-            string groupIdColumn,
+            string labelColumn = DefaultColumnNames.Label,
+            string featureColumn = DefaultColumnNames.Features,
+            string groupIdColumn = DefaultColumnNames.GroupId,
             string weightColumn = null,
             int numLeaves = Defaults.NumLeaves,
             int numTrees = Defaults.NumTrees,
-            int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
+            int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves,
             double learningRate = Defaults.LearningRates,
             Action<Arguments> advancedSettings = null)
-            : base(env, TrainerUtils.MakeR4ScalarLabel(labelColumn), featureColumn, weightColumn, groupIdColumn, numLeaves, numTrees, minDocumentsInLeafs, learningRate, advancedSettings)
+            : base(env, TrainerUtils.MakeR4ScalarLabel(labelColumn), featureColumn, weightColumn, groupIdColumn, numLeaves, numTrees, minDatapointsInLeaves, learningRate, advancedSettings)
         {
             Host.CheckNonEmpty(groupIdColumn, nameof(groupIdColumn));
         }

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -59,20 +59,20 @@ public sealed partial class FastTreeRegressionTrainer
         /// <param name="featureColumn">The name of the feature column.</param>
         /// <param name="weightColumn">The name for the column containing the initial weight.</param>
         /// <param name="learningRate">The learning rate.</param>
-        /// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
+        /// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
         /// <param name="numLeaves">The max number of leaves in each regression tree.</param>
         /// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
         /// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
         public FastTreeRegressionTrainer(IHostEnvironment env,
-            string labelColumn,
-            string featureColumn,
+            string labelColumn = DefaultColumnNames.Label,
+            string featureColumn = DefaultColumnNames.Features,
             string weightColumn = null,
             int numLeaves = Defaults.NumLeaves,
             int numTrees = Defaults.NumTrees,
-            int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
+            int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves,
             double learningRate = Defaults.LearningRates,
             Action<Arguments> advancedSettings = null)
-            : base(env, TrainerUtils.MakeR4ScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDocumentsInLeafs, learningRate, advancedSettings)
+            : base(env, TrainerUtils.MakeR4ScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDatapointsInLeaves, learningRate, advancedSettings)
         {
         }
 

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -56,20 +56,20 @@ public sealed partial class FastTreeTweedieTrainer
         /// <param name="featureColumn">The name of the feature column.</param>
         /// <param name="weightColumn">The name for the column containing the initial weight.</param>
         /// <param name="learningRate">The learning rate.</param>
-        /// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
+        /// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
         /// <param name="numLeaves">The max number of leaves in each regression tree.</param>
         /// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
         /// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
         public FastTreeTweedieTrainer(IHostEnvironment env,
-            string labelColumn,
-            string featureColumn,
+            string labelColumn = DefaultColumnNames.Label,
+            string featureColumn = DefaultColumnNames.Features,
             string weightColumn = null,
             int numLeaves = Defaults.NumLeaves,
             int numTrees = Defaults.NumTrees,
-            int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
+            int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves,
             double learningRate = Defaults.LearningRates,
             Action<Arguments> advancedSettings = null)
-            : base(env, TrainerUtils.MakeR4ScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDocumentsInLeafs, learningRate, advancedSettings)
+            : base(env, TrainerUtils.MakeR4ScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDatapointsInLeaves, learningRate, advancedSettings)
         {
             Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
             Host.CheckNonEmpty(featureColumn, nameof(featureColumn));

src/Microsoft.ML.FastTree/GamClassification.cs

@@ -63,16 +63,16 @@ internal BinaryClassificationGamTrainer(IHostEnvironment env, Arguments args)
         /// <param name="featureColumn">The name of the feature column.</param>
         /// <param name="weightColumn">The name for the column containing the initial weight.</param>
         /// <param name="learningRate">The learning rate.</param>
-        /// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
+        /// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
         /// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
         public BinaryClassificationGamTrainer(IHostEnvironment env,
-            string labelColumn,
-            string featureColumn,
+            string labelColumn = DefaultColumnNames.Label,
+            string featureColumn = DefaultColumnNames.Features,
             string weightColumn = null,
-            int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
+            int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves,
             double learningRate = Defaults.LearningRates,
             Action<Arguments> advancedSettings = null)
-            : base(env, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, minDocumentsInLeafs, learningRate, advancedSettings)
+            : base(env, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, minDatapointsInLeaves, learningRate, advancedSettings)
         {
             _sigmoidParameter = 1;
         }

src/Microsoft.ML.FastTree/GamRegression.cs

@@ -51,17 +51,17 @@ internal RegressionGamTrainer(IHostEnvironment env, Arguments args)
         /// <param name="labelColumn">The name of the label column.</param>
         /// <param name="featureColumn">The name of the feature column.</param>
         /// <param name="weightColumn">The name for the column containing the initial weight.</param>
-        /// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
+        /// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
         /// <param name="learningRate">The learning rate.</param>
         /// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
         public RegressionGamTrainer(IHostEnvironment env,
-            string labelColumn,
-            string featureColumn,
+            string labelColumn = DefaultColumnNames.Label,
+            string featureColumn = DefaultColumnNames.Features,
             string weightColumn = null,
-            int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
+            int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves,
             double learningRate = Defaults.LearningRates,
             Action<Arguments> advancedSettings = null)
-            : base(env, LoadNameValue, TrainerUtils.MakeR4ScalarLabel(labelColumn), featureColumn, weightColumn, minDocumentsInLeafs, learningRate, advancedSettings)
+            : base(env, LoadNameValue, TrainerUtils.MakeR4ScalarLabel(labelColumn), featureColumn, weightColumn, minDatapointsInLeaves, learningRate, advancedSettings)
         {
         }