Go through all places once

Author: wschin

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

@@ -29,7 +29,7 @@ public static void Example()
             // We will train a FastTreeRegression model with 1 tree on these two columns to predict Age.
             string outputColumnName = "Features";
             var pipeline = ml.Transforms.Concatenate(outputColumnName, new[] { "Parity", "Induced" })
-                .Append(ml.Regression.Trainers.FastTree(labelColumnName: "Age", featureColumnName: outputColumnName, numTrees: 1, numLeaves: 2, minDatapointsInLeaves: 1));
+                .Append(ml.Regression.Trainers.FastTree(labelColumnName: "Age", featureColumnName: outputColumnName, numberOfTrees: 1, numberOfLeaves: 2, minimumExampleCountPerLeaf: 1));
 
             var model = pipeline.Fit(trainData);
 

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

@@ -28,7 +28,7 @@ public static void Example()
                 .ToArray();
             var pipeline = mlContext.Transforms.Concatenate("Features", featureNames)
                     .Append(mlContext.Regression.Trainers.GeneralizedAdditiveModels(
-                        labelColumnName: labelName, featureColumnName: "Features", maxBins: 16));
+                        labelColumnName: labelName, featureColumnName: "Features", maxBinCountPerFeature: 16));
             var fitPipeline = pipeline.Fit(data);
 
             // Extract the model from the pipeline
@@ -37,7 +37,7 @@ public static void Example()
             // Now investigate the properties of the Generalized Additive Model: The intercept and shape functions.
 
             // The intercept for the GAM models represent the average prediction for the training data
-            var intercept = gamModel.Intercept;
+            var intercept = gamModel.Bias;
             // Expected output: Average predicted cost: 22.53
             Console.WriteLine($"Average predicted cost: {intercept:0.00}");
 
@@ -93,7 +93,7 @@ public static void Example()
             // Distillation." <a href='https://arxiv.org/abs/1710.06169'>arXiv:1710.06169</a>."
             Console.WriteLine();
             Console.WriteLine("Student-Teacher Ratio");
-            for (int i = 0; i < teacherRatioBinUpperBounds.Length; i++)
+            for (int i = 0; i < teacherRatioBinUpperBounds.Count; i++)
             {
                 Console.WriteLine($"x < {teacherRatioBinUpperBounds[i]:0.00} => {teacherRatioBinEffects[i]:0.000}");
             }

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -164,7 +164,7 @@ private protected override int GetBestIteration(IChannel ch)
         private protected double BsrMaxTreeOutput()
         {
             if (FastTreeTrainerOptions.BestStepRankingRegressionTrees)
-                return FastTreeTrainerOptions.MaxTreeOutput;
+                return FastTreeTrainerOptions.MaximumTreeOutput;
             else
                 return -1;
         }

src/Microsoft.ML.FastTree/FastTreeArguments.cs

@@ -146,7 +146,7 @@ internal static class Defaults
     {
         public const int NumberOfTrees = 100;
         public const int NumberOfLeaves = 20;
-        public const int MinExampleCountInLeaves = 10;
+        public const int MinimumExampleCountPerLeaf = 10;
         public const double LearningRate = 0.2;
     }
 
@@ -320,7 +320,7 @@ public abstract class TreeOptions : 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,MinDocumentsInLeafs", 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 MinExampleCountPerLeaf = Defaults.MinExampleCountInLeaves;
+        public int MinExampleCountPerLeaf = Defaults.MinimumExampleCountPerLeaf;
 
         /// <summary>
         /// Total number of decision trees to create in the ensemble.
@@ -463,13 +463,13 @@ public abstract class BoostedTreeOptions : TreeOptions
         /// Number of post-bracket line search steps.
         /// </summary>
         [Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of post-bracket line search steps", ShortName = "lssteps,NumPostBracketSteps")]
-        public int MaxNumberOfLinearSearchSteps;
+        public int MaximumNumberOfLineSearchSteps;
 
         /// <summary>
         /// Minimum line search step size.
         /// </summary>
-        [Argument(ArgumentType.LastOccurenceWins, HelpText = "Minimum line search step size", ShortName = "minstep")]
-        public Double MinStepSize;
+        [Argument(ArgumentType.LastOccurenceWins, HelpText = "Minimum line search step size", ShortName = "minstep,MinStepSize")]
+        public Double MinimumStepSize;
 
         public enum OptimizationAlgorithmType { GradientDescent, AcceleratedGradientDescent, ConjugateGradientDescent };
 
@@ -510,7 +510,7 @@ public enum OptimizationAlgorithmType { GradientDescent, AcceleratedGradientDesc
         /// </summary>
         [Argument(ArgumentType.AtMostOnce, HelpText = "The tolerance threshold for pruning", ShortName = "prth")]
         [TGUI(Description = "Pruning threshold")]
-        public Double PruningThreshold = 0.004;
+        public double PruningThreshold = 0.004;
 
         /// <summary>
         /// The moving window size for pruning.
@@ -525,7 +525,7 @@ public enum OptimizationAlgorithmType { GradientDescent, AcceleratedGradientDesc
         [Argument(ArgumentType.LastOccurenceWins, HelpText = "The learning rate", ShortName = "lr,LearningRates", SortOrder = 4)]
         [TGUI(Label = "Learning Rate", SuggestedSweeps = "0.025-0.4;log")]
         [TlcModule.SweepableFloatParamAttribute("LearningRates", 0.025f, 0.4f, isLogScale: true)]
-        public Double LearningRate = Defaults.LearningRate;
+        public double LearningRate = Defaults.LearningRate;
 
         /// <summary>
         /// Shrinkage.
@@ -559,7 +559,7 @@ public enum OptimizationAlgorithmType { GradientDescent, AcceleratedGradientDesc
         /// Upper bound on absolute value of single tree output.
         /// </summary>
         [Argument(ArgumentType.AtMostOnce, HelpText = "Upper bound on absolute value of single tree output", ShortName = "mo")]
-        public Double MaxTreeOutput = 100;
+        public Double MaximumTreeOutput = 100;
 
         /// <summary>
         /// Training starts from random ordering (determined by /r1).
@@ -630,14 +630,14 @@ internal override void Check(IExceptionContext ectx)
         {
             base.Check(ectx);
 
-            ectx.CheckUserArg(0 <= MaxTreeOutput, nameof(MaxTreeOutput), "Must be non-negative.");
+            ectx.CheckUserArg(0 <= MaximumTreeOutput, nameof(MaximumTreeOutput), "Must be non-negative.");
             ectx.CheckUserArg(0 <= PruningThreshold, nameof(PruningThreshold), "Must be non-negative.");
             ectx.CheckUserArg(0 < PruningWindowSize, nameof(PruningWindowSize), "Must be positive.");
             ectx.CheckUserArg(0 < Shrinkage, nameof(Shrinkage), "Must be positive.");
             ectx.CheckUserArg(0 <= DropoutRate && DropoutRate <= 1, nameof(DropoutRate), "Must be between 0 and 1.");
             ectx.CheckUserArg(0 < GetDerivativesSampleRate, nameof(GetDerivativesSampleRate), "Must be positive.");
-            ectx.CheckUserArg(0 <= MaxNumberOfLinearSearchSteps, nameof(MaxNumberOfLinearSearchSteps), "Must be non-negative.");
-            ectx.CheckUserArg(0 <= MinStepSize, nameof(MinStepSize), "Must be non-negative.");
+            ectx.CheckUserArg(0 <= MaximumNumberOfLineSearchSteps, nameof(MaximumNumberOfLineSearchSteps), "Must be non-negative.");
+            ectx.CheckUserArg(0 <= MinimumStepSize, nameof(MinimumStepSize), "Must be non-negative.");
         }
     }
 }

src/Microsoft.ML.FastTree/FastTreeClassification.cs

@@ -10,7 +10,6 @@
 using Microsoft.ML.Calibrators;
 using Microsoft.ML.Data;
 using Microsoft.ML.EntryPoints;
-using Microsoft.ML.Internal.Internallearn;
 using Microsoft.ML.Model;
 using Microsoft.ML.Trainers.FastTree;
 
@@ -132,7 +131,7 @@ internal FastTreeBinaryClassificationTrainer(IHostEnvironment env,
             string weightColumn = null,
             int numLeaves = Defaults.NumberOfLeaves,
             int numTrees = Defaults.NumberOfTrees,
-            int minDatapointsInLeaves = Defaults.MinExampleCountInLeaves,
+            int minDatapointsInLeaves = Defaults.MinimumExampleCountPerLeaf,
             double learningRate = Defaults.LearningRate)
             : base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDatapointsInLeaves, learningRate)
         {
@@ -195,7 +194,7 @@ private protected override ObjectiveFunctionBase ConstructObjFunc(IChannel ch)
                 FastTreeTrainerOptions.Shrinkage,
                 _sigmoidParameter,
                 FastTreeTrainerOptions.UnbalancedSets,
-                FastTreeTrainerOptions.MaxTreeOutput,
+                FastTreeTrainerOptions.MaximumTreeOutput,
                 FastTreeTrainerOptions.GetDerivativesSampleRate,
                 FastTreeTrainerOptions.BestStepRankingRegressionTrees,
                 FastTreeTrainerOptions.RandomSeed,
@@ -209,7 +208,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
             {
                 var lossCalculator = new BinaryClassificationTest(optimizationAlgorithm.TrainingScores, _trainSetLabels, _sigmoidParameter);
                 // REVIEW: we should makeloss indices an enum in BinaryClassificationTest
-                optimizationAlgorithm.AdjustTreeOutputsOverride = new LineSearch(lossCalculator, FastTreeTrainerOptions.UnbalancedSets ? 3 /*Unbalanced  sets  loss*/ : 1 /*normal loss*/, FastTreeTrainerOptions.MaxNumberOfLinearSearchSteps, FastTreeTrainerOptions.MinStepSize);
+                optimizationAlgorithm.AdjustTreeOutputsOverride = new LineSearch(lossCalculator, FastTreeTrainerOptions.UnbalancedSets ? 3 /*Unbalanced  sets  loss*/ : 1 /*normal loss*/, FastTreeTrainerOptions.MaximumNumberOfLineSearchSteps, FastTreeTrainerOptions.MinimumStepSize);
             }
             return optimizationAlgorithm;
         }

src/Microsoft.ML.FastTree/FastTreeRanking.cs

@@ -12,7 +12,6 @@
 using Microsoft.ML;
 using Microsoft.ML.Data;
 using Microsoft.ML.EntryPoints;
-using Microsoft.ML.Internal.Internallearn;
 using Microsoft.ML.Internal.Utilities;
 using Microsoft.ML.Model;
 using Microsoft.ML.Trainers.FastTree;
@@ -76,7 +75,7 @@ internal FastTreeRankingTrainer(IHostEnvironment env,
             string weightColumn = null,
             int numLeaves = Defaults.NumberOfLeaves,
             int numTrees = Defaults.NumberOfTrees,
-            int minDatapointsInLeaves = Defaults.MinExampleCountInLeaves,
+            int minDatapointsInLeaves = Defaults.MinimumExampleCountPerLeaf,
             double learningRate = Defaults.LearningRate)
             : base(env, TrainerUtils.MakeR4ScalarColumn(labelColumn), featureColumn, weightColumn, groupIdColumn, numLeaves, numTrees, minDatapointsInLeaves, learningRate)
         {
@@ -193,7 +192,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
             if (FastTreeTrainerOptions.UseLineSearch)
             {
                 _specialTrainSetTest = new FastNdcgTest(optimizationAlgorithm.TrainingScores, TrainSet.Ratings, FastTreeTrainerOptions.SortingAlgorithm, FastTreeTrainerOptions.EarlyStoppingMetrics);
-                optimizationAlgorithm.AdjustTreeOutputsOverride = new LineSearch(_specialTrainSetTest, 0, FastTreeTrainerOptions.MaxNumberOfLinearSearchSteps, FastTreeTrainerOptions.MinStepSize);
+                optimizationAlgorithm.AdjustTreeOutputsOverride = new LineSearch(_specialTrainSetTest, 0, FastTreeTrainerOptions.MaximumNumberOfLineSearchSteps, FastTreeTrainerOptions.MinimumStepSize);
             }
             return optimizationAlgorithm;
         }
@@ -554,7 +553,7 @@ public LambdaRankObjectiveFunction(Dataset trainset, short[] labels, Options opt
                 : base(trainset,
                     options.LearningRate,
                     options.Shrinkage,
-                    options.MaxTreeOutput,
+                    options.MaximumTreeOutput,
                     options.GetDerivativesSampleRate,
                     options.BestStepRankingRegressionTrees,
                     options.RandomSeed)

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -8,7 +8,6 @@
 using Microsoft.ML;
 using Microsoft.ML.Data;
 using Microsoft.ML.EntryPoints;
-using Microsoft.ML.Internal.Internallearn;
 using Microsoft.ML.Model;
 using Microsoft.ML.Trainers.FastTree;
 
@@ -65,7 +64,7 @@ internal FastTreeRegressionTrainer(IHostEnvironment env,
             string weightColumn = null,
             int numLeaves = Defaults.NumberOfLeaves,
             int numTrees = Defaults.NumberOfTrees,
-            int minDatapointsInLeaves = Defaults.MinExampleCountInLeaves,
+            int minDatapointsInLeaves = Defaults.MinimumExampleCountPerLeaf,
             double learningRate = Defaults.LearningRate)
             : base(env, TrainerUtils.MakeR4ScalarColumn(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDatapointsInLeaves, learningRate)
         {
@@ -127,7 +126,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
             {
                 var lossCalculator = new RegressionTest(optimizationAlgorithm.TrainingScores);
                 // REVIEW: We should make loss indices an enum in BinaryClassificationTest.
-                optimizationAlgorithm.AdjustTreeOutputsOverride = new LineSearch(lossCalculator, 1 /*L2 error*/, FastTreeTrainerOptions.MaxNumberOfLinearSearchSteps, FastTreeTrainerOptions.MinStepSize);
+                optimizationAlgorithm.AdjustTreeOutputsOverride = new LineSearch(lossCalculator, 1 /*L2 error*/, FastTreeTrainerOptions.MaximumNumberOfLineSearchSteps, FastTreeTrainerOptions.MinimumStepSize);
             }
 
             return optimizationAlgorithm;
@@ -390,12 +389,12 @@ internal sealed class ObjectiveImpl : ObjectiveFunctionBase, IStepSearch
             public ObjectiveImpl(Dataset trainData, RegressionGamTrainer.Options options) :
                 base(
                     trainData,
-                    options.LearningRates,
+                    options.LearningRate,
                     0,
-                    options.MaxOutput,
+                    options.MaximumTreeOutput,
                     options.GetDerivativesSampleRate,
                     false,
-                    options.RngSeed)
+                    options.Seed)
             {
                 _labels = GetDatasetRegressionLabels(trainData);
             }
@@ -405,7 +404,7 @@ public ObjectiveImpl(Dataset trainData, Options options)
                     trainData,
                     options.LearningRate,
                     options.Shrinkage,
-                    options.MaxTreeOutput,
+                    options.MaximumTreeOutput,
                     options.GetDerivativesSampleRate,
                     options.BestStepRankingRegressionTrees,
                     options.RandomSeed)

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -9,7 +9,6 @@
 using Microsoft.ML;
 using Microsoft.ML.Data;
 using Microsoft.ML.EntryPoints;
-using Microsoft.ML.Internal.Internallearn;
 using Microsoft.ML.Internal.Utilities;
 using Microsoft.ML.Model;
 using Microsoft.ML.Trainers.FastTree;
@@ -63,7 +62,7 @@ internal FastTreeTweedieTrainer(IHostEnvironment env,
             string weightColumn = null,
             int numLeaves = Defaults.NumberOfLeaves,
             int numTrees = Defaults.NumberOfTrees,
-            int minDatapointsInLeaves = Defaults.MinExampleCountInLeaves,
+            int minDatapointsInLeaves = Defaults.MinimumExampleCountPerLeaf,
             double learningRate = Defaults.LearningRate)
             : base(env, TrainerUtils.MakeR4ScalarColumn(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDatapointsInLeaves, learningRate)
         {
@@ -134,7 +133,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
                 var lossCalculator = new RegressionTest(optimizationAlgorithm.TrainingScores);
                 // REVIEW: We should make loss indices an enum in BinaryClassificationTest.
                 // REVIEW: Nope, subcomponent.
-                optimizationAlgorithm.AdjustTreeOutputsOverride = new LineSearch(lossCalculator, 1 /*L2 error*/, FastTreeTrainerOptions.MaxNumberOfLinearSearchSteps, FastTreeTrainerOptions.MinStepSize);
+                optimizationAlgorithm.AdjustTreeOutputsOverride = new LineSearch(lossCalculator, 1 /*L2 error*/, FastTreeTrainerOptions.MaximumNumberOfLineSearchSteps, FastTreeTrainerOptions.MinimumStepSize);
             }
 
             return optimizationAlgorithm;
@@ -343,7 +342,7 @@ public ObjectiveImpl(Dataset trainData, Options options)
                     trainData,
                     options.LearningRate,
                     options.Shrinkage,
-                    options.MaxTreeOutput,
+                    options.MaximumTreeOutput,
                     options.GetDerivativesSampleRate,
                     options.BestStepRankingRegressionTrees,
                     options.RandomSeed)
@@ -361,7 +360,7 @@ public ObjectiveImpl(Dataset trainData, Options options)
 
                 _index1 = 1 - options.Index;
                 _index2 = 2 - options.Index;
-                _maxClamp = Math.Abs(options.MaxTreeOutput);
+                _maxClamp = Math.Abs(options.MaximumTreeOutput);
             }
 
             public void AdjustTreeOutputs(IChannel ch, InternalRegressionTree tree, DocumentPartitioning partitioning, ScoreTracker trainingScores)

src/Microsoft.ML.FastTree/GamClassification.cs

@@ -69,9 +69,9 @@ internal BinaryClassificationGamTrainer(IHostEnvironment env,
             string labelColumn = DefaultColumnNames.Label,
             string featureColumn = DefaultColumnNames.Features,
             string weightColumn = null,
-            int numIterations = GamDefaults.NumIterations,
-            double learningRate = GamDefaults.LearningRates,
-            int maxBins = GamDefaults.MaxBins)
+            int numIterations = GamDefaults.NumberOfIterations,
+            double learningRate = GamDefaults.LearningRate,
+            int maxBins = GamDefaults.MaximumBinCountPerFeature)
             : base(env, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, numIterations, learningRate, maxBins)
         {
             _sigmoidParameter = 1;
@@ -115,14 +115,14 @@ private protected override ObjectiveFunctionBase CreateObjectiveFunction()
             return new FastTreeBinaryClassificationTrainer.ObjectiveImpl(
                 TrainSet,
                 ConvertTargetsToBool(TrainSet.Targets),
-                GamTrainerOptions.LearningRates,
+                GamTrainerOptions.LearningRate,
                 0,
                 _sigmoidParameter,
                 GamTrainerOptions.UnbalancedSets,
-                GamTrainerOptions.MaxOutput,
+                GamTrainerOptions.MaximumTreeOutput,
                 GamTrainerOptions.GetDerivativesSampleRate,
                 false,
-                GamTrainerOptions.RngSeed,
+                GamTrainerOptions.Seed,
                 ParallelTraining
             );
         }