Tree estimators

src/Microsoft.ML.Api/TypedCursor.cs

@@ -622,7 +622,7 @@ public ICursor GetRootCursor()
  /// </summary>
  public static class CursoringUtils
  {
- private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new TlcEnvironment().";
+ private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new LocalEnvironment().";
 
  /// <summary>
  /// Generate a strongly-typed cursorable wrapper of the <see cref="IDataView"/>.

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -18,6 +18,9 @@
 [assembly: LoadableClass(typeof(RegressionPredictionTransformer<IPredictorProducing<float>>), typeof(RegressionPredictionTransformer), null, typeof(SignatureLoadModel),
  "", RegressionPredictionTransformer.LoaderSignature)]
 
+[assembly: LoadableClass(typeof(RankingPredictionTransformer<IPredictorProducing<float>>), typeof(RankingPredictionTransformer), null, typeof(SignatureLoadModel),
+ "", RankingPredictionTransformer.LoaderSignature)]
+
 namespace Microsoft.ML.Runtime.Data
 {
  public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer<TModel>, ICanSaveModel
@@ -301,6 +304,52 @@ private static VersionInfo GetVersionInfo()
  }
  }
 
+ public sealed class RankingPredictionTransformer<TModel> : PredictionTransformerBase<TModel>
+ where TModel : class, IPredictorProducing<float>
+ {
+ private readonly GenericScorer _scorer;
+
+ public RankingPredictionTransformer(IHostEnvironment env, TModel model, ISchema inputSchema, string featureColumn)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), model, inputSchema, featureColumn)
+ {
+ var schema = new RoleMappedSchema(inputSchema, null, featureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, inputSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ internal RankingPredictionTransformer(IHostEnvironment env, ModelLoadContext ctx)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), ctx)
+ {
+ var schema = new RoleMappedSchema(TrainSchema, null, FeatureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, TrainSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ public override IDataView Transform(IDataView input)
+ {
+ Host.CheckValue(input, nameof(input));
+ return _scorer.ApplyToData(Host, input);
+ }
+
+ protected override void SaveCore(ModelSaveContext ctx)
+ {
+ Contracts.AssertValue(ctx);
+ ctx.SetVersionInfo(GetVersionInfo());
+
+ // *** Binary format ***
+ // <base info>
+ base.SaveCore(ctx);
+ }
+
+ private static VersionInfo GetVersionInfo()
+ {
+ return new VersionInfo(
+ modelSignature: "MC RANK",
+ verWrittenCur: 0x00010001, // Initial
+ verReadableCur: 0x00010001,
+ verWeCanReadBack: 0x00010001,
+ loaderSignature: RankingPredictionTransformer.LoaderSignature);
+ }
+ }
+
  internal static class BinaryPredictionTransformer
  {
  public const string LoaderSignature = "BinaryPredXfer";
@@ -324,4 +373,12 @@ internal static class RegressionPredictionTransformer
  public static RegressionPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
  => new RegressionPredictionTransformer<IPredictorProducing<float>>(env, ctx);
  }
+
+ internal static class RankingPredictionTransformer
+ {
+ public const string LoaderSignature = "RankingPredXfer";
+
+ public static RankingPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
+ => new RankingPredictionTransformer<IPredictorProducing<float>>(env, ctx);
+ }
 }

src/Microsoft.ML.Ensemble/OutputCombiners/MultiStacking.cs

@@ -57,7 +57,7 @@ public Arguments()
  env => new Ova(env, new Ova.Arguments()
  {
  PredictorType = ComponentFactoryUtils.CreateFromFunction(
-e => new AveragedPerceptronTrainer(e, new AveragedPerceptronTrainer.Arguments()))
+ e => new FastTreeBinaryClassificationTrainer(e, DefaultColumnNames.Label, DefaultColumnNames.Features))
  }));
  }
  }

src/Microsoft.ML.Ensemble/OutputCombiners/RegressionStacking.cs

@@ -49,7 +49,7 @@ public sealed class Arguments : ArgumentsBase, ISupportRegressionOutputCombinerF
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeRegressionTrainer(env, new FastTreeRegressionTrainer.Arguments()));
+ env => new FastTreeRegressionTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IRegressionOutputCombiner CreateComponent(IHostEnvironment env) => new RegressionStacking(env, this);

src/Microsoft.ML.Ensemble/OutputCombiners/Stacking.cs

@@ -5,6 +5,7 @@
 using System;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Ensemble.OutputCombiners;
 using Microsoft.ML.Runtime.EntryPoints;
 using Microsoft.ML.Runtime.FastTree;
@@ -46,7 +47,7 @@ public sealed class Arguments : ArgumentsBase, ISupportBinaryOutputCombinerFacto
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()));
+ env => new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IBinaryOutputCombiner CreateComponent(IHostEnvironment env) => new Stacking(env, this);

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -6,17 +6,25 @@
 
 using System;
 using System.Linq;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.FastTree.Internal;
 using Microsoft.ML.Runtime.Internal.Internallearn;
 
 namespace Microsoft.ML.Runtime.FastTree
 {
- public abstract class BoostingFastTreeTrainerBase<TArgs, TPredictor> : FastTreeTrainerBase<TArgs, TPredictor>
+ public abstract class BoostingFastTreeTrainerBase<TArgs, TTransformer, TModel> : FastTreeTrainerBase<TArgs, TTransformer, TModel>
+ where TTransformer : IPredictionTransformer<TModel>
  where TArgs : BoostedTreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
- public BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args) : base(env, args)
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label) : base(env, args, label)
+ {
+ }
+
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(env, label, featureColumn, weightColumn, groupIdColumn, advancedSettings)
  {
  }
 

src/Microsoft.ML.FastTree/FastTree.cs

@@ -12,6 +12,7 @@
 using System.IO;
 using System.Linq;
 using System.Text;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Data.Conversion;
@@ -43,10 +44,11 @@ internal static class FastTreeShared
  public static readonly object TrainLock = new object();
  }
 
- public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
- TrainerBase<TPredictor>
+ public abstract class FastTreeTrainerBase<TArgs, TTransformer, TModel> :
+ TrainerEstimatorBase<TTransformer, TModel>
+ where TTransformer: IPredictionTransformer<TModel>
  where TArgs : TreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
  protected readonly TArgs Args;
  protected readonly bool AllowGC;
@@ -87,34 +89,53 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
  private protected virtual bool NeedCalibration => false;
 
- private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args)
- : base(env, RegisterName)
+ /// <summary>
+ /// Constructor to use when instantiating the classing deriving from here through the API.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(featureColumn), label, MakeWeightColumn(weightColumn))
+ {
+ Args = new TArgs();
+
+ //apply the advanced args, if the user supplied any
+ advancedSettings?.Invoke(Args);
+ Args.LabelColumn = label.Name;
+
+ if (weightColumn != null)
+ Args.WeightColumn = weightColumn;
+
+ if (groupIdColumn != null)
+ Args.GroupIdColumn = 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.
+ // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
+ Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
+ // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
+
+ Initialize(env);
+ }
+
+ /// <summary>
+ /// Legacy constructor that is used when invoking the classsing deriving from this, through maml.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(args.FeatureColumn), label, MakeWeightColumn(args.WeightColumn))
  {
  Host.CheckValue(args, nameof(args));
  Args = args;
  // 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.
  // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
  Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
- int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
- if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
- {
- using (var ch = Host.Start("FastTreeTrainerBase"))
- {
- numThreads = Host.ConcurrencyFactor;
- ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
- + "setting of the environment. Using {0} training threads instead.", numThreads);
- ch.Done();
- }
- }
- ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
- ParallelTraining.InitEnvironment();
  // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
- // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from ConsoleEnvironment.
- AllowGC = (env is HostEnvironmentBase<ConsoleEnvironment>);
- Tests = new List<Test>();
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
 
-InitializeThreads(numThreads);
+Initialize(env);
  }
 
  protected abstract void PrepareLabels(IChannel ch);
@@ -133,6 +154,39 @@ protected virtual Float GetMaxLabel()
  return Float.PositiveInfinity;
  }
 
+ private static SchemaShape.Column MakeWeightColumn(string weightColumn)
+ {
+ if (weightColumn == null)
+ return null;
+ return new SchemaShape.Column(weightColumn, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false);
+ }
+
+ private static SchemaShape.Column MakeFeatureColumn(string featureColumn)
+ {
+ return new SchemaShape.Column(featureColumn, SchemaShape.Column.VectorKind.Vector, NumberType.R4, false);
+ }
+
+ private void Initialize(IHostEnvironment env)
+ {
+ int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
+ if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
+ {
+ using (var ch = Host.Start("FastTreeTrainerBase"))
+ {
+ numThreads = Host.ConcurrencyFactor;
+ ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
+ + "setting of the environment. Using {0} training threads instead.", numThreads);
+ ch.Done();
+ }
+ }
+ ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
+ ParallelTraining.InitEnvironment();
+
+ Tests = new List<Test>();
+
+ InitializeThreads(numThreads);
+ }
+
  protected void ConvertData(RoleMappedData trainData)
  {
  trainData.Schema.Schema.TryGetColumnIndex(DefaultColumnNames.Features, out int featureIndex);

src/Microsoft.ML.Api/TypedCursor.cs

@@ -622,7 +622,7 @@ public ICursor GetRootCursor()
  /// </summary>
  public static class CursoringUtils
  {
- private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new TlcEnvironment().";
+ private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new LocalEnvironment().";
 
  /// <summary>
  /// Generate a strongly-typed cursorable wrapper of the <see cref="IDataView"/>.

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -18,6 +18,9 @@
 [assembly: LoadableClass(typeof(RegressionPredictionTransformer<IPredictorProducing<float>>), typeof(RegressionPredictionTransformer), null, typeof(SignatureLoadModel),
  "", RegressionPredictionTransformer.LoaderSignature)]
 
+[assembly: LoadableClass(typeof(RankingPredictionTransformer<IPredictorProducing<float>>), typeof(RankingPredictionTransformer), null, typeof(SignatureLoadModel),
+ "", RankingPredictionTransformer.LoaderSignature)]
+
 namespace Microsoft.ML.Runtime.Data
 {
  public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer<TModel>, ICanSaveModel
@@ -301,6 +304,52 @@ private static VersionInfo GetVersionInfo()
  }
  }
 
+ public sealed class RankingPredictionTransformer<TModel> : PredictionTransformerBase<TModel>
+ where TModel : class, IPredictorProducing<float>
+ {
+ private readonly GenericScorer _scorer;
+
+ public RankingPredictionTransformer(IHostEnvironment env, TModel model, ISchema inputSchema, string featureColumn)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), model, inputSchema, featureColumn)
+ {
+ var schema = new RoleMappedSchema(inputSchema, null, featureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, inputSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ internal RankingPredictionTransformer(IHostEnvironment env, ModelLoadContext ctx)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), ctx)
+ {
+ var schema = new RoleMappedSchema(TrainSchema, null, FeatureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, TrainSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ public override IDataView Transform(IDataView input)
+ {
+ Host.CheckValue(input, nameof(input));
+ return _scorer.ApplyToData(Host, input);
+ }
+
+ protected override void SaveCore(ModelSaveContext ctx)
+ {
+ Contracts.AssertValue(ctx);
+ ctx.SetVersionInfo(GetVersionInfo());
+
+ // *** Binary format ***
+ // <base info>
+ base.SaveCore(ctx);
+ }
+
+ private static VersionInfo GetVersionInfo()
+ {
+ return new VersionInfo(
+ modelSignature: "MC RANK",
+ verWrittenCur: 0x00010001, // Initial
+ verReadableCur: 0x00010001,
+ verWeCanReadBack: 0x00010001,
+ loaderSignature: RankingPredictionTransformer.LoaderSignature);
+ }
+ }
+
  internal static class BinaryPredictionTransformer
  {
  public const string LoaderSignature = "BinaryPredXfer";
@@ -324,4 +373,12 @@ internal static class RegressionPredictionTransformer
  public static RegressionPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
  => new RegressionPredictionTransformer<IPredictorProducing<float>>(env, ctx);
  }
+
+ internal static class RankingPredictionTransformer
+ {
+ public const string LoaderSignature = "RankingPredXfer";
+
+ public static RankingPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
+ => new RankingPredictionTransformer<IPredictorProducing<float>>(env, ctx);
+ }
 }

src/Microsoft.ML.Ensemble/OutputCombiners/MultiStacking.cs

@@ -57,7 +57,7 @@ public Arguments()
  env => new Ova(env, new Ova.Arguments()
  {
  PredictorType = ComponentFactoryUtils.CreateFromFunction(
-e => new AveragedPerceptronTrainer(e, new AveragedPerceptronTrainer.Arguments()))
+ e => new FastTreeBinaryClassificationTrainer(e, DefaultColumnNames.Label, DefaultColumnNames.Features))
  }));
  }
  }

src/Microsoft.ML.Ensemble/OutputCombiners/RegressionStacking.cs

@@ -49,7 +49,7 @@ public sealed class Arguments : ArgumentsBase, ISupportRegressionOutputCombinerF
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeRegressionTrainer(env, new FastTreeRegressionTrainer.Arguments()));
+ env => new FastTreeRegressionTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IRegressionOutputCombiner CreateComponent(IHostEnvironment env) => new RegressionStacking(env, this);

src/Microsoft.ML.Ensemble/OutputCombiners/Stacking.cs

@@ -5,6 +5,7 @@
 using System;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Ensemble.OutputCombiners;
 using Microsoft.ML.Runtime.EntryPoints;
 using Microsoft.ML.Runtime.FastTree;
@@ -46,7 +47,7 @@ public sealed class Arguments : ArgumentsBase, ISupportBinaryOutputCombinerFacto
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()));
+ env => new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IBinaryOutputCombiner CreateComponent(IHostEnvironment env) => new Stacking(env, this);

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -6,17 +6,25 @@
 
 using System;
 using System.Linq;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.FastTree.Internal;
 using Microsoft.ML.Runtime.Internal.Internallearn;
 
 namespace Microsoft.ML.Runtime.FastTree
 {
- public abstract class BoostingFastTreeTrainerBase<TArgs, TPredictor> : FastTreeTrainerBase<TArgs, TPredictor>
+ public abstract class BoostingFastTreeTrainerBase<TArgs, TTransformer, TModel> : FastTreeTrainerBase<TArgs, TTransformer, TModel>
+ where TTransformer : IPredictionTransformer<TModel>
  where TArgs : BoostedTreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
- public BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args) : base(env, args)
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label) : base(env, args, label)
+ {
+ }
+
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(env, label, featureColumn, weightColumn, groupIdColumn, advancedSettings)
  {
  }
 

src/Microsoft.ML.FastTree/FastTree.cs

@@ -12,6 +12,7 @@
 using System.IO;
 using System.Linq;
 using System.Text;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Data.Conversion;
@@ -43,10 +44,11 @@ internal static class FastTreeShared
  public static readonly object TrainLock = new object();
  }
 
- public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
- TrainerBase<TPredictor>
+ public abstract class FastTreeTrainerBase<TArgs, TTransformer, TModel> :
+ TrainerEstimatorBase<TTransformer, TModel>
+ where TTransformer: IPredictionTransformer<TModel>
  where TArgs : TreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
  protected readonly TArgs Args;
  protected readonly bool AllowGC;
@@ -87,34 +89,53 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
  private protected virtual bool NeedCalibration => false;
 
- private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args)
- : base(env, RegisterName)
+ /// <summary>
+ /// Constructor to use when instantiating the classing deriving from here through the API.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(featureColumn), label, MakeWeightColumn(weightColumn))
+ {
+ Args = new TArgs();
+
+ //apply the advanced args, if the user supplied any
+ advancedSettings?.Invoke(Args);
+ Args.LabelColumn = label.Name;
+
+ if (weightColumn != null)
+ Args.WeightColumn = weightColumn;
+
+ if (groupIdColumn != null)
+ Args.GroupIdColumn = 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.
+ // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
+ Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
+ // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
+
+ Initialize(env);
+ }
+
+ /// <summary>
+ /// Legacy constructor that is used when invoking the classsing deriving from this, through maml.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(args.FeatureColumn), label, MakeWeightColumn(args.WeightColumn))
  {
  Host.CheckValue(args, nameof(args));
  Args = args;
  // 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.
  // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
  Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
- int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
- if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
- {
- using (var ch = Host.Start("FastTreeTrainerBase"))
- {
- numThreads = Host.ConcurrencyFactor;
- ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
- + "setting of the environment. Using {0} training threads instead.", numThreads);
- ch.Done();
- }
- }
- ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
- ParallelTraining.InitEnvironment();
  // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
- // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from ConsoleEnvironment.
- AllowGC = (env is HostEnvironmentBase<ConsoleEnvironment>);
- Tests = new List<Test>();
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
 
-InitializeThreads(numThreads);
+Initialize(env);
  }
 
  protected abstract void PrepareLabels(IChannel ch);
@@ -133,6 +154,39 @@ protected virtual Float GetMaxLabel()
  return Float.PositiveInfinity;
  }
 
+ private static SchemaShape.Column MakeWeightColumn(string weightColumn)
+ {
+ if (weightColumn == null)
+ return null;
+ return new SchemaShape.Column(weightColumn, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false);
+ }
+
+ private static SchemaShape.Column MakeFeatureColumn(string featureColumn)
+ {
+ return new SchemaShape.Column(featureColumn, SchemaShape.Column.VectorKind.Vector, NumberType.R4, false);
+ }
+
+ private void Initialize(IHostEnvironment env)
+ {
+ int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
+ if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
+ {
+ using (var ch = Host.Start("FastTreeTrainerBase"))
+ {
+ numThreads = Host.ConcurrencyFactor;
+ ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
+ + "setting of the environment. Using {0} training threads instead.", numThreads);
+ ch.Done();
+ }
+ }
+ ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
+ ParallelTraining.InitEnvironment();
+
+ Tests = new List<Test>();
+
+ InitializeThreads(numThreads);
+ }
+
  protected void ConvertData(RoleMappedData trainData)
  {
  trainData.Schema.Schema.TryGetColumnIndex(DefaultColumnNames.Features, out int featureIndex);

src/Microsoft.ML.Api/TypedCursor.cs

@@ -622,7 +622,7 @@ public ICursor GetRootCursor()
  /// </summary>
  public static class CursoringUtils
  {
- private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new TlcEnvironment().";
+ private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new LocalEnvironment().";
 
  /// <summary>
  /// Generate a strongly-typed cursorable wrapper of the <see cref="IDataView"/>.

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -18,6 +18,9 @@
 [assembly: LoadableClass(typeof(RegressionPredictionTransformer<IPredictorProducing<float>>), typeof(RegressionPredictionTransformer), null, typeof(SignatureLoadModel),
  "", RegressionPredictionTransformer.LoaderSignature)]
 
+[assembly: LoadableClass(typeof(RankingPredictionTransformer<IPredictorProducing<float>>), typeof(RankingPredictionTransformer), null, typeof(SignatureLoadModel),
+ "", RankingPredictionTransformer.LoaderSignature)]
+
 namespace Microsoft.ML.Runtime.Data
 {
  public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer<TModel>, ICanSaveModel
@@ -301,6 +304,52 @@ private static VersionInfo GetVersionInfo()
  }
  }
 
+ public sealed class RankingPredictionTransformer<TModel> : PredictionTransformerBase<TModel>
+ where TModel : class, IPredictorProducing<float>
+ {
+ private readonly GenericScorer _scorer;
+
+ public RankingPredictionTransformer(IHostEnvironment env, TModel model, ISchema inputSchema, string featureColumn)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), model, inputSchema, featureColumn)
+ {
+ var schema = new RoleMappedSchema(inputSchema, null, featureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, inputSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ internal RankingPredictionTransformer(IHostEnvironment env, ModelLoadContext ctx)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), ctx)
+ {
+ var schema = new RoleMappedSchema(TrainSchema, null, FeatureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, TrainSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ public override IDataView Transform(IDataView input)
+ {
+ Host.CheckValue(input, nameof(input));
+ return _scorer.ApplyToData(Host, input);
+ }
+
+ protected override void SaveCore(ModelSaveContext ctx)
+ {
+ Contracts.AssertValue(ctx);
+ ctx.SetVersionInfo(GetVersionInfo());
+
+ // *** Binary format ***
+ // <base info>
+ base.SaveCore(ctx);
+ }
+
+ private static VersionInfo GetVersionInfo()
+ {
+ return new VersionInfo(
+ modelSignature: "MC RANK",
+ verWrittenCur: 0x00010001, // Initial
+ verReadableCur: 0x00010001,
+ verWeCanReadBack: 0x00010001,
+ loaderSignature: RankingPredictionTransformer.LoaderSignature);
+ }
+ }
+
  internal static class BinaryPredictionTransformer
  {
  public const string LoaderSignature = "BinaryPredXfer";
@@ -324,4 +373,12 @@ internal static class RegressionPredictionTransformer
  public static RegressionPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
  => new RegressionPredictionTransformer<IPredictorProducing<float>>(env, ctx);
  }
+
+ internal static class RankingPredictionTransformer
+ {
+ public const string LoaderSignature = "RankingPredXfer";
+
+ public static RankingPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
+ => new RankingPredictionTransformer<IPredictorProducing<float>>(env, ctx);
+ }
 }

src/Microsoft.ML.Ensemble/OutputCombiners/MultiStacking.cs

@@ -57,7 +57,7 @@ public Arguments()
  env => new Ova(env, new Ova.Arguments()
  {
  PredictorType = ComponentFactoryUtils.CreateFromFunction(
-e => new AveragedPerceptronTrainer(e, new AveragedPerceptronTrainer.Arguments()))
+ e => new FastTreeBinaryClassificationTrainer(e, DefaultColumnNames.Label, DefaultColumnNames.Features))
  }));
  }
  }

src/Microsoft.ML.Ensemble/OutputCombiners/RegressionStacking.cs

@@ -49,7 +49,7 @@ public sealed class Arguments : ArgumentsBase, ISupportRegressionOutputCombinerF
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeRegressionTrainer(env, new FastTreeRegressionTrainer.Arguments()));
+ env => new FastTreeRegressionTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IRegressionOutputCombiner CreateComponent(IHostEnvironment env) => new RegressionStacking(env, this);

src/Microsoft.ML.Ensemble/OutputCombiners/Stacking.cs

@@ -5,6 +5,7 @@
 using System;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Ensemble.OutputCombiners;
 using Microsoft.ML.Runtime.EntryPoints;
 using Microsoft.ML.Runtime.FastTree;
@@ -46,7 +47,7 @@ public sealed class Arguments : ArgumentsBase, ISupportBinaryOutputCombinerFacto
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()));
+ env => new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IBinaryOutputCombiner CreateComponent(IHostEnvironment env) => new Stacking(env, this);

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -6,17 +6,25 @@
 
 using System;
 using System.Linq;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.FastTree.Internal;
 using Microsoft.ML.Runtime.Internal.Internallearn;
 
 namespace Microsoft.ML.Runtime.FastTree
 {
- public abstract class BoostingFastTreeTrainerBase<TArgs, TPredictor> : FastTreeTrainerBase<TArgs, TPredictor>
+ public abstract class BoostingFastTreeTrainerBase<TArgs, TTransformer, TModel> : FastTreeTrainerBase<TArgs, TTransformer, TModel>
+ where TTransformer : IPredictionTransformer<TModel>
  where TArgs : BoostedTreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
- public BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args) : base(env, args)
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label) : base(env, args, label)
+ {
+ }
+
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(env, label, featureColumn, weightColumn, groupIdColumn, advancedSettings)
  {
  }
 

src/Microsoft.ML.FastTree/FastTree.cs

@@ -12,6 +12,7 @@
 using System.IO;
 using System.Linq;
 using System.Text;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Data.Conversion;
@@ -43,10 +44,11 @@ internal static class FastTreeShared
  public static readonly object TrainLock = new object();
  }
 
- public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
- TrainerBase<TPredictor>
+ public abstract class FastTreeTrainerBase<TArgs, TTransformer, TModel> :
+ TrainerEstimatorBase<TTransformer, TModel>
+ where TTransformer: IPredictionTransformer<TModel>
  where TArgs : TreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
  protected readonly TArgs Args;
  protected readonly bool AllowGC;
@@ -87,34 +89,53 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
  private protected virtual bool NeedCalibration => false;
 
- private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args)
- : base(env, RegisterName)
+ /// <summary>
+ /// Constructor to use when instantiating the classing deriving from here through the API.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(featureColumn), label, MakeWeightColumn(weightColumn))
+ {
+ Args = new TArgs();
+
+ //apply the advanced args, if the user supplied any
+ advancedSettings?.Invoke(Args);
+ Args.LabelColumn = label.Name;
+
+ if (weightColumn != null)
+ Args.WeightColumn = weightColumn;
+
+ if (groupIdColumn != null)
+ Args.GroupIdColumn = 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.
+ // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
+ Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
+ // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
+
+ Initialize(env);
+ }
+
+ /// <summary>
+ /// Legacy constructor that is used when invoking the classsing deriving from this, through maml.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(args.FeatureColumn), label, MakeWeightColumn(args.WeightColumn))
  {
  Host.CheckValue(args, nameof(args));
  Args = args;
  // 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.
  // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
  Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
- int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
- if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
- {
- using (var ch = Host.Start("FastTreeTrainerBase"))
- {
- numThreads = Host.ConcurrencyFactor;
- ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
- + "setting of the environment. Using {0} training threads instead.", numThreads);
- ch.Done();
- }
- }
- ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
- ParallelTraining.InitEnvironment();
  // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
- // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from ConsoleEnvironment.
- AllowGC = (env is HostEnvironmentBase<ConsoleEnvironment>);
- Tests = new List<Test>();
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
 
-InitializeThreads(numThreads);
+Initialize(env);
  }
 
  protected abstract void PrepareLabels(IChannel ch);
@@ -133,6 +154,39 @@ protected virtual Float GetMaxLabel()
  return Float.PositiveInfinity;
  }
 
+ private static SchemaShape.Column MakeWeightColumn(string weightColumn)
+ {
+ if (weightColumn == null)
+ return null;
+ return new SchemaShape.Column(weightColumn, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false);
+ }
+
+ private static SchemaShape.Column MakeFeatureColumn(string featureColumn)
+ {
+ return new SchemaShape.Column(featureColumn, SchemaShape.Column.VectorKind.Vector, NumberType.R4, false);
+ }
+
+ private void Initialize(IHostEnvironment env)
+ {
+ int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
+ if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
+ {
+ using (var ch = Host.Start("FastTreeTrainerBase"))
+ {
+ numThreads = Host.ConcurrencyFactor;
+ ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
+ + "setting of the environment. Using {0} training threads instead.", numThreads);
+ ch.Done();
+ }
+ }
+ ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
+ ParallelTraining.InitEnvironment();
+
+ Tests = new List<Test>();
+
+ InitializeThreads(numThreads);
+ }
+
  protected void ConvertData(RoleMappedData trainData)
  {
  trainData.Schema.Schema.TryGetColumnIndex(DefaultColumnNames.Features, out int featureIndex);

src/Microsoft.ML.Api/TypedCursor.cs

@@ -622,7 +622,7 @@ public ICursor GetRootCursor()
  /// </summary>
  public static class CursoringUtils
  {
- private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new TlcEnvironment().";
+ private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new LocalEnvironment().";
 
  /// <summary>
  /// Generate a strongly-typed cursorable wrapper of the <see cref="IDataView"/>.

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -18,6 +18,9 @@
 [assembly: LoadableClass(typeof(RegressionPredictionTransformer<IPredictorProducing<float>>), typeof(RegressionPredictionTransformer), null, typeof(SignatureLoadModel),
  "", RegressionPredictionTransformer.LoaderSignature)]
 
+[assembly: LoadableClass(typeof(RankingPredictionTransformer<IPredictorProducing<float>>), typeof(RankingPredictionTransformer), null, typeof(SignatureLoadModel),
+ "", RankingPredictionTransformer.LoaderSignature)]
+
 namespace Microsoft.ML.Runtime.Data
 {
  public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer<TModel>, ICanSaveModel
@@ -301,6 +304,52 @@ private static VersionInfo GetVersionInfo()
  }
  }
 
+ public sealed class RankingPredictionTransformer<TModel> : PredictionTransformerBase<TModel>
+ where TModel : class, IPredictorProducing<float>
+ {
+ private readonly GenericScorer _scorer;
+
+ public RankingPredictionTransformer(IHostEnvironment env, TModel model, ISchema inputSchema, string featureColumn)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), model, inputSchema, featureColumn)
+ {
+ var schema = new RoleMappedSchema(inputSchema, null, featureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, inputSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ internal RankingPredictionTransformer(IHostEnvironment env, ModelLoadContext ctx)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), ctx)
+ {
+ var schema = new RoleMappedSchema(TrainSchema, null, FeatureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, TrainSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ public override IDataView Transform(IDataView input)
+ {
+ Host.CheckValue(input, nameof(input));
+ return _scorer.ApplyToData(Host, input);
+ }
+
+ protected override void SaveCore(ModelSaveContext ctx)
+ {
+ Contracts.AssertValue(ctx);
+ ctx.SetVersionInfo(GetVersionInfo());
+
+ // *** Binary format ***
+ // <base info>
+ base.SaveCore(ctx);
+ }
+
+ private static VersionInfo GetVersionInfo()
+ {
+ return new VersionInfo(
+ modelSignature: "MC RANK",
+ verWrittenCur: 0x00010001, // Initial
+ verReadableCur: 0x00010001,
+ verWeCanReadBack: 0x00010001,
+ loaderSignature: RankingPredictionTransformer.LoaderSignature);
+ }
+ }
+
  internal static class BinaryPredictionTransformer
  {
  public const string LoaderSignature = "BinaryPredXfer";
@@ -324,4 +373,12 @@ internal static class RegressionPredictionTransformer
  public static RegressionPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
  => new RegressionPredictionTransformer<IPredictorProducing<float>>(env, ctx);
  }
+
+ internal static class RankingPredictionTransformer
+ {
+ public const string LoaderSignature = "RankingPredXfer";
+
+ public static RankingPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
+ => new RankingPredictionTransformer<IPredictorProducing<float>>(env, ctx);
+ }
 }

src/Microsoft.ML.Ensemble/OutputCombiners/MultiStacking.cs

@@ -57,7 +57,7 @@ public Arguments()
  env => new Ova(env, new Ova.Arguments()
  {
  PredictorType = ComponentFactoryUtils.CreateFromFunction(
-e => new AveragedPerceptronTrainer(e, new AveragedPerceptronTrainer.Arguments()))
+ e => new FastTreeBinaryClassificationTrainer(e, DefaultColumnNames.Label, DefaultColumnNames.Features))
  }));
  }
  }

src/Microsoft.ML.Ensemble/OutputCombiners/RegressionStacking.cs

@@ -49,7 +49,7 @@ public sealed class Arguments : ArgumentsBase, ISupportRegressionOutputCombinerF
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeRegressionTrainer(env, new FastTreeRegressionTrainer.Arguments()));
+ env => new FastTreeRegressionTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IRegressionOutputCombiner CreateComponent(IHostEnvironment env) => new RegressionStacking(env, this);

src/Microsoft.ML.Ensemble/OutputCombiners/Stacking.cs

@@ -5,6 +5,7 @@
 using System;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Ensemble.OutputCombiners;
 using Microsoft.ML.Runtime.EntryPoints;
 using Microsoft.ML.Runtime.FastTree;
@@ -46,7 +47,7 @@ public sealed class Arguments : ArgumentsBase, ISupportBinaryOutputCombinerFacto
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()));
+ env => new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IBinaryOutputCombiner CreateComponent(IHostEnvironment env) => new Stacking(env, this);

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -6,17 +6,25 @@
 
 using System;
 using System.Linq;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.FastTree.Internal;
 using Microsoft.ML.Runtime.Internal.Internallearn;
 
 namespace Microsoft.ML.Runtime.FastTree
 {
- public abstract class BoostingFastTreeTrainerBase<TArgs, TPredictor> : FastTreeTrainerBase<TArgs, TPredictor>
+ public abstract class BoostingFastTreeTrainerBase<TArgs, TTransformer, TModel> : FastTreeTrainerBase<TArgs, TTransformer, TModel>
+ where TTransformer : IPredictionTransformer<TModel>
  where TArgs : BoostedTreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
- public BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args) : base(env, args)
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label) : base(env, args, label)
+ {
+ }
+
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(env, label, featureColumn, weightColumn, groupIdColumn, advancedSettings)
  {
  }
 

src/Microsoft.ML.FastTree/FastTree.cs

@@ -12,6 +12,7 @@
 using System.IO;
 using System.Linq;
 using System.Text;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Data.Conversion;
@@ -43,10 +44,11 @@ internal static class FastTreeShared
  public static readonly object TrainLock = new object();
  }
 
- public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
- TrainerBase<TPredictor>
+ public abstract class FastTreeTrainerBase<TArgs, TTransformer, TModel> :
+ TrainerEstimatorBase<TTransformer, TModel>
+ where TTransformer: IPredictionTransformer<TModel>
  where TArgs : TreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
  protected readonly TArgs Args;
  protected readonly bool AllowGC;
@@ -87,34 +89,53 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
  private protected virtual bool NeedCalibration => false;
 
- private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args)
- : base(env, RegisterName)
+ /// <summary>
+ /// Constructor to use when instantiating the classing deriving from here through the API.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(featureColumn), label, MakeWeightColumn(weightColumn))
+ {
+ Args = new TArgs();
+
+ //apply the advanced args, if the user supplied any
+ advancedSettings?.Invoke(Args);
+ Args.LabelColumn = label.Name;
+
+ if (weightColumn != null)
+ Args.WeightColumn = weightColumn;
+
+ if (groupIdColumn != null)
+ Args.GroupIdColumn = 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.
+ // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
+ Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
+ // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
+
+ Initialize(env);
+ }
+
+ /// <summary>
+ /// Legacy constructor that is used when invoking the classsing deriving from this, through maml.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(args.FeatureColumn), label, MakeWeightColumn(args.WeightColumn))
  {
  Host.CheckValue(args, nameof(args));
  Args = args;
  // 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.
  // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
  Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
- int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
- if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
- {
- using (var ch = Host.Start("FastTreeTrainerBase"))
- {
- numThreads = Host.ConcurrencyFactor;
- ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
- + "setting of the environment. Using {0} training threads instead.", numThreads);
- ch.Done();
- }
- }
- ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
- ParallelTraining.InitEnvironment();
  // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
- // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from ConsoleEnvironment.
- AllowGC = (env is HostEnvironmentBase<ConsoleEnvironment>);
- Tests = new List<Test>();
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
 
-InitializeThreads(numThreads);
+Initialize(env);
  }
 
  protected abstract void PrepareLabels(IChannel ch);
@@ -133,6 +154,39 @@ protected virtual Float GetMaxLabel()
  return Float.PositiveInfinity;
  }
 
+ private static SchemaShape.Column MakeWeightColumn(string weightColumn)
+ {
+ if (weightColumn == null)
+ return null;
+ return new SchemaShape.Column(weightColumn, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false);
+ }
+
+ private static SchemaShape.Column MakeFeatureColumn(string featureColumn)
+ {
+ return new SchemaShape.Column(featureColumn, SchemaShape.Column.VectorKind.Vector, NumberType.R4, false);
+ }
+
+ private void Initialize(IHostEnvironment env)
+ {
+ int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
+ if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
+ {
+ using (var ch = Host.Start("FastTreeTrainerBase"))
+ {
+ numThreads = Host.ConcurrencyFactor;
+ ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
+ + "setting of the environment. Using {0} training threads instead.", numThreads);
+ ch.Done();
+ }
+ }
+ ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
+ ParallelTraining.InitEnvironment();
+
+ Tests = new List<Test>();
+
+ InitializeThreads(numThreads);
+ }
+
  protected void ConvertData(RoleMappedData trainData)
  {
  trainData.Schema.Schema.TryGetColumnIndex(DefaultColumnNames.Features, out int featureIndex);

src/Microsoft.ML.Api/TypedCursor.cs

@@ -622,7 +622,7 @@ public ICursor GetRootCursor()
  /// </summary>
  public static class CursoringUtils
  {
- private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new TlcEnvironment().";
+ private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new LocalEnvironment().";
 
  /// <summary>
  /// Generate a strongly-typed cursorable wrapper of the <see cref="IDataView"/>.

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -18,6 +18,9 @@
 [assembly: LoadableClass(typeof(RegressionPredictionTransformer<IPredictorProducing<float>>), typeof(RegressionPredictionTransformer), null, typeof(SignatureLoadModel),
  "", RegressionPredictionTransformer.LoaderSignature)]
 
+[assembly: LoadableClass(typeof(RankingPredictionTransformer<IPredictorProducing<float>>), typeof(RankingPredictionTransformer), null, typeof(SignatureLoadModel),
+ "", RankingPredictionTransformer.LoaderSignature)]
+
 namespace Microsoft.ML.Runtime.Data
 {
  public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer<TModel>, ICanSaveModel
@@ -301,6 +304,52 @@ private static VersionInfo GetVersionInfo()
  }
  }
 
+ public sealed class RankingPredictionTransformer<TModel> : PredictionTransformerBase<TModel>
+ where TModel : class, IPredictorProducing<float>
+ {
+ private readonly GenericScorer _scorer;
+
+ public RankingPredictionTransformer(IHostEnvironment env, TModel model, ISchema inputSchema, string featureColumn)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), model, inputSchema, featureColumn)
+ {
+ var schema = new RoleMappedSchema(inputSchema, null, featureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, inputSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ internal RankingPredictionTransformer(IHostEnvironment env, ModelLoadContext ctx)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), ctx)
+ {
+ var schema = new RoleMappedSchema(TrainSchema, null, FeatureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, TrainSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ public override IDataView Transform(IDataView input)
+ {
+ Host.CheckValue(input, nameof(input));
+ return _scorer.ApplyToData(Host, input);
+ }
+
+ protected override void SaveCore(ModelSaveContext ctx)
+ {
+ Contracts.AssertValue(ctx);
+ ctx.SetVersionInfo(GetVersionInfo());
+
+ // *** Binary format ***
+ // <base info>
+ base.SaveCore(ctx);
+ }
+
+ private static VersionInfo GetVersionInfo()
+ {
+ return new VersionInfo(
+ modelSignature: "MC RANK",
+ verWrittenCur: 0x00010001, // Initial
+ verReadableCur: 0x00010001,
+ verWeCanReadBack: 0x00010001,
+ loaderSignature: RankingPredictionTransformer.LoaderSignature);
+ }
+ }
+
  internal static class BinaryPredictionTransformer
  {
  public const string LoaderSignature = "BinaryPredXfer";
@@ -324,4 +373,12 @@ internal static class RegressionPredictionTransformer
  public static RegressionPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
  => new RegressionPredictionTransformer<IPredictorProducing<float>>(env, ctx);
  }
+
+ internal static class RankingPredictionTransformer
+ {
+ public const string LoaderSignature = "RankingPredXfer";
+
+ public static RankingPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
+ => new RankingPredictionTransformer<IPredictorProducing<float>>(env, ctx);
+ }
 }

src/Microsoft.ML.Ensemble/OutputCombiners/MultiStacking.cs

@@ -57,7 +57,7 @@ public Arguments()
  env => new Ova(env, new Ova.Arguments()
  {
  PredictorType = ComponentFactoryUtils.CreateFromFunction(
-e => new AveragedPerceptronTrainer(e, new AveragedPerceptronTrainer.Arguments()))
+ e => new FastTreeBinaryClassificationTrainer(e, DefaultColumnNames.Label, DefaultColumnNames.Features))
  }));
  }
  }

src/Microsoft.ML.Ensemble/OutputCombiners/RegressionStacking.cs

@@ -49,7 +49,7 @@ public sealed class Arguments : ArgumentsBase, ISupportRegressionOutputCombinerF
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeRegressionTrainer(env, new FastTreeRegressionTrainer.Arguments()));
+ env => new FastTreeRegressionTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IRegressionOutputCombiner CreateComponent(IHostEnvironment env) => new RegressionStacking(env, this);

src/Microsoft.ML.Ensemble/OutputCombiners/Stacking.cs

@@ -5,6 +5,7 @@
 using System;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Ensemble.OutputCombiners;
 using Microsoft.ML.Runtime.EntryPoints;
 using Microsoft.ML.Runtime.FastTree;
@@ -46,7 +47,7 @@ public sealed class Arguments : ArgumentsBase, ISupportBinaryOutputCombinerFacto
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()));
+ env => new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IBinaryOutputCombiner CreateComponent(IHostEnvironment env) => new Stacking(env, this);

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -6,17 +6,25 @@
 
 using System;
 using System.Linq;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.FastTree.Internal;
 using Microsoft.ML.Runtime.Internal.Internallearn;
 
 namespace Microsoft.ML.Runtime.FastTree
 {
- public abstract class BoostingFastTreeTrainerBase<TArgs, TPredictor> : FastTreeTrainerBase<TArgs, TPredictor>
+ public abstract class BoostingFastTreeTrainerBase<TArgs, TTransformer, TModel> : FastTreeTrainerBase<TArgs, TTransformer, TModel>
+ where TTransformer : IPredictionTransformer<TModel>
  where TArgs : BoostedTreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
- public BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args) : base(env, args)
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label) : base(env, args, label)
+ {
+ }
+
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(env, label, featureColumn, weightColumn, groupIdColumn, advancedSettings)
  {
  }
 

src/Microsoft.ML.FastTree/FastTree.cs

@@ -12,6 +12,7 @@
 using System.IO;
 using System.Linq;
 using System.Text;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Data.Conversion;
@@ -43,10 +44,11 @@ internal static class FastTreeShared
  public static readonly object TrainLock = new object();
  }
 
- public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
- TrainerBase<TPredictor>
+ public abstract class FastTreeTrainerBase<TArgs, TTransformer, TModel> :
+ TrainerEstimatorBase<TTransformer, TModel>
+ where TTransformer: IPredictionTransformer<TModel>
  where TArgs : TreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
  protected readonly TArgs Args;
  protected readonly bool AllowGC;
@@ -87,34 +89,53 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
  private protected virtual bool NeedCalibration => false;
 
- private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args)
- : base(env, RegisterName)
+ /// <summary>
+ /// Constructor to use when instantiating the classing deriving from here through the API.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(featureColumn), label, MakeWeightColumn(weightColumn))
+ {
+ Args = new TArgs();
+
+ //apply the advanced args, if the user supplied any
+ advancedSettings?.Invoke(Args);
+ Args.LabelColumn = label.Name;
+
+ if (weightColumn != null)
+ Args.WeightColumn = weightColumn;
+
+ if (groupIdColumn != null)
+ Args.GroupIdColumn = 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.
+ // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
+ Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
+ // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
+
+ Initialize(env);
+ }
+
+ /// <summary>
+ /// Legacy constructor that is used when invoking the classsing deriving from this, through maml.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(args.FeatureColumn), label, MakeWeightColumn(args.WeightColumn))
  {
  Host.CheckValue(args, nameof(args));
  Args = args;
  // 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.
  // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
  Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
- int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
- if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
- {
- using (var ch = Host.Start("FastTreeTrainerBase"))
- {
- numThreads = Host.ConcurrencyFactor;
- ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
- + "setting of the environment. Using {0} training threads instead.", numThreads);
- ch.Done();
- }
- }
- ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
- ParallelTraining.InitEnvironment();
  // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
- // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from ConsoleEnvironment.
- AllowGC = (env is HostEnvironmentBase<ConsoleEnvironment>);
- Tests = new List<Test>();
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
 
-InitializeThreads(numThreads);
+Initialize(env);
  }
 
  protected abstract void PrepareLabels(IChannel ch);
@@ -133,6 +154,39 @@ protected virtual Float GetMaxLabel()
  return Float.PositiveInfinity;
  }
 
+ private static SchemaShape.Column MakeWeightColumn(string weightColumn)
+ {
+ if (weightColumn == null)
+ return null;
+ return new SchemaShape.Column(weightColumn, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false);
+ }
+
+ private static SchemaShape.Column MakeFeatureColumn(string featureColumn)
+ {
+ return new SchemaShape.Column(featureColumn, SchemaShape.Column.VectorKind.Vector, NumberType.R4, false);
+ }
+
+ private void Initialize(IHostEnvironment env)
+ {
+ int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
+ if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
+ {
+ using (var ch = Host.Start("FastTreeTrainerBase"))
+ {
+ numThreads = Host.ConcurrencyFactor;
+ ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
+ + "setting of the environment. Using {0} training threads instead.", numThreads);
+ ch.Done();
+ }
+ }
+ ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
+ ParallelTraining.InitEnvironment();
+
+ Tests = new List<Test>();
+
+ InitializeThreads(numThreads);
+ }
+
  protected void ConvertData(RoleMappedData trainData)
  {
  trainData.Schema.Schema.TryGetColumnIndex(DefaultColumnNames.Features, out int featureIndex);

src/Microsoft.ML.Api/TypedCursor.cs

@@ -622,7 +622,7 @@ public ICursor GetRootCursor()
  /// </summary>
  public static class CursoringUtils
  {
- private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new TlcEnvironment().";
+ private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new LocalEnvironment().";
 
  /// <summary>
  /// Generate a strongly-typed cursorable wrapper of the <see cref="IDataView"/>.

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -18,6 +18,9 @@
 [assembly: LoadableClass(typeof(RegressionPredictionTransformer<IPredictorProducing<float>>), typeof(RegressionPredictionTransformer), null, typeof(SignatureLoadModel),
  "", RegressionPredictionTransformer.LoaderSignature)]
 
+[assembly: LoadableClass(typeof(RankingPredictionTransformer<IPredictorProducing<float>>), typeof(RankingPredictionTransformer), null, typeof(SignatureLoadModel),
+ "", RankingPredictionTransformer.LoaderSignature)]
+
 namespace Microsoft.ML.Runtime.Data
 {
  public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer<TModel>, ICanSaveModel
@@ -301,6 +304,52 @@ private static VersionInfo GetVersionInfo()
  }
  }
 
+ public sealed class RankingPredictionTransformer<TModel> : PredictionTransformerBase<TModel>
+ where TModel : class, IPredictorProducing<float>
+ {
+ private readonly GenericScorer _scorer;
+
+ public RankingPredictionTransformer(IHostEnvironment env, TModel model, ISchema inputSchema, string featureColumn)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), model, inputSchema, featureColumn)
+ {
+ var schema = new RoleMappedSchema(inputSchema, null, featureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, inputSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ internal RankingPredictionTransformer(IHostEnvironment env, ModelLoadContext ctx)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), ctx)
+ {
+ var schema = new RoleMappedSchema(TrainSchema, null, FeatureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, TrainSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ public override IDataView Transform(IDataView input)
+ {
+ Host.CheckValue(input, nameof(input));
+ return _scorer.ApplyToData(Host, input);
+ }
+
+ protected override void SaveCore(ModelSaveContext ctx)
+ {
+ Contracts.AssertValue(ctx);
+ ctx.SetVersionInfo(GetVersionInfo());
+
+ // *** Binary format ***
+ // <base info>
+ base.SaveCore(ctx);
+ }
+
+ private static VersionInfo GetVersionInfo()
+ {
+ return new VersionInfo(
+ modelSignature: "MC RANK",
+ verWrittenCur: 0x00010001, // Initial
+ verReadableCur: 0x00010001,
+ verWeCanReadBack: 0x00010001,
+ loaderSignature: RankingPredictionTransformer.LoaderSignature);
+ }
+ }
+
  internal static class BinaryPredictionTransformer
  {
  public const string LoaderSignature = "BinaryPredXfer";
@@ -324,4 +373,12 @@ internal static class RegressionPredictionTransformer
  public static RegressionPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
  => new RegressionPredictionTransformer<IPredictorProducing<float>>(env, ctx);
  }
+
+ internal static class RankingPredictionTransformer
+ {
+ public const string LoaderSignature = "RankingPredXfer";
+
+ public static RankingPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
+ => new RankingPredictionTransformer<IPredictorProducing<float>>(env, ctx);
+ }
 }

src/Microsoft.ML.Ensemble/OutputCombiners/MultiStacking.cs

@@ -57,7 +57,7 @@ public Arguments()
  env => new Ova(env, new Ova.Arguments()
  {
  PredictorType = ComponentFactoryUtils.CreateFromFunction(
-e => new AveragedPerceptronTrainer(e, new AveragedPerceptronTrainer.Arguments()))
+ e => new FastTreeBinaryClassificationTrainer(e, DefaultColumnNames.Label, DefaultColumnNames.Features))
  }));
  }
  }

src/Microsoft.ML.Ensemble/OutputCombiners/RegressionStacking.cs

@@ -49,7 +49,7 @@ public sealed class Arguments : ArgumentsBase, ISupportRegressionOutputCombinerF
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeRegressionTrainer(env, new FastTreeRegressionTrainer.Arguments()));
+ env => new FastTreeRegressionTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IRegressionOutputCombiner CreateComponent(IHostEnvironment env) => new RegressionStacking(env, this);

src/Microsoft.ML.Ensemble/OutputCombiners/Stacking.cs

@@ -5,6 +5,7 @@
 using System;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Ensemble.OutputCombiners;
 using Microsoft.ML.Runtime.EntryPoints;
 using Microsoft.ML.Runtime.FastTree;
@@ -46,7 +47,7 @@ public sealed class Arguments : ArgumentsBase, ISupportBinaryOutputCombinerFacto
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()));
+ env => new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IBinaryOutputCombiner CreateComponent(IHostEnvironment env) => new Stacking(env, this);

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -6,17 +6,25 @@
 
 using System;
 using System.Linq;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.FastTree.Internal;
 using Microsoft.ML.Runtime.Internal.Internallearn;
 
 namespace Microsoft.ML.Runtime.FastTree
 {
- public abstract class BoostingFastTreeTrainerBase<TArgs, TPredictor> : FastTreeTrainerBase<TArgs, TPredictor>
+ public abstract class BoostingFastTreeTrainerBase<TArgs, TTransformer, TModel> : FastTreeTrainerBase<TArgs, TTransformer, TModel>
+ where TTransformer : IPredictionTransformer<TModel>
  where TArgs : BoostedTreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
- public BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args) : base(env, args)
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label) : base(env, args, label)
+ {
+ }
+
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(env, label, featureColumn, weightColumn, groupIdColumn, advancedSettings)
  {
  }
 

src/Microsoft.ML.FastTree/FastTree.cs

@@ -12,6 +12,7 @@
 using System.IO;
 using System.Linq;
 using System.Text;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Data.Conversion;
@@ -43,10 +44,11 @@ internal static class FastTreeShared
  public static readonly object TrainLock = new object();
  }
 
- public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
- TrainerBase<TPredictor>
+ public abstract class FastTreeTrainerBase<TArgs, TTransformer, TModel> :
+ TrainerEstimatorBase<TTransformer, TModel>
+ where TTransformer: IPredictionTransformer<TModel>
  where TArgs : TreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
  protected readonly TArgs Args;
  protected readonly bool AllowGC;
@@ -87,34 +89,53 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
  private protected virtual bool NeedCalibration => false;
 
- private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args)
- : base(env, RegisterName)
+ /// <summary>
+ /// Constructor to use when instantiating the classing deriving from here through the API.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(featureColumn), label, MakeWeightColumn(weightColumn))
+ {
+ Args = new TArgs();
+
+ //apply the advanced args, if the user supplied any
+ advancedSettings?.Invoke(Args);
+ Args.LabelColumn = label.Name;
+
+ if (weightColumn != null)
+ Args.WeightColumn = weightColumn;
+
+ if (groupIdColumn != null)
+ Args.GroupIdColumn = 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.
+ // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
+ Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
+ // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
+
+ Initialize(env);
+ }
+
+ /// <summary>
+ /// Legacy constructor that is used when invoking the classsing deriving from this, through maml.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(args.FeatureColumn), label, MakeWeightColumn(args.WeightColumn))
  {
  Host.CheckValue(args, nameof(args));
  Args = args;
  // 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.
  // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
  Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
- int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
- if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
- {
- using (var ch = Host.Start("FastTreeTrainerBase"))
- {
- numThreads = Host.ConcurrencyFactor;
- ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
- + "setting of the environment. Using {0} training threads instead.", numThreads);
- ch.Done();
- }
- }
- ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
- ParallelTraining.InitEnvironment();
  // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
- // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from ConsoleEnvironment.
- AllowGC = (env is HostEnvironmentBase<ConsoleEnvironment>);
- Tests = new List<Test>();
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
 
-InitializeThreads(numThreads);
+Initialize(env);
  }
 
  protected abstract void PrepareLabels(IChannel ch);
@@ -133,6 +154,39 @@ protected virtual Float GetMaxLabel()
  return Float.PositiveInfinity;
  }
 
+ private static SchemaShape.Column MakeWeightColumn(string weightColumn)
+ {
+ if (weightColumn == null)
+ return null;
+ return new SchemaShape.Column(weightColumn, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false);
+ }
+
+ private static SchemaShape.Column MakeFeatureColumn(string featureColumn)
+ {
+ return new SchemaShape.Column(featureColumn, SchemaShape.Column.VectorKind.Vector, NumberType.R4, false);
+ }
+
+ private void Initialize(IHostEnvironment env)
+ {
+ int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
+ if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
+ {
+ using (var ch = Host.Start("FastTreeTrainerBase"))
+ {
+ numThreads = Host.ConcurrencyFactor;
+ ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
+ + "setting of the environment. Using {0} training threads instead.", numThreads);
+ ch.Done();
+ }
+ }
+ ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
+ ParallelTraining.InitEnvironment();
+
+ Tests = new List<Test>();
+
+ InitializeThreads(numThreads);
+ }
+
  protected void ConvertData(RoleMappedData trainData)
  {
  trainData.Schema.Schema.TryGetColumnIndex(DefaultColumnNames.Features, out int featureIndex);

src/Microsoft.ML.Api/TypedCursor.cs

@@ -622,7 +622,7 @@ public ICursor GetRootCursor()
  /// </summary>
  public static class CursoringUtils
  {
- private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new TlcEnvironment().";
+ private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new LocalEnvironment().";
 
  /// <summary>
  /// Generate a strongly-typed cursorable wrapper of the <see cref="IDataView"/>.

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -18,6 +18,9 @@
 [assembly: LoadableClass(typeof(RegressionPredictionTransformer<IPredictorProducing<float>>), typeof(RegressionPredictionTransformer), null, typeof(SignatureLoadModel),
  "", RegressionPredictionTransformer.LoaderSignature)]
 
+[assembly: LoadableClass(typeof(RankingPredictionTransformer<IPredictorProducing<float>>), typeof(RankingPredictionTransformer), null, typeof(SignatureLoadModel),
+ "", RankingPredictionTransformer.LoaderSignature)]
+
 namespace Microsoft.ML.Runtime.Data
 {
  public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer<TModel>, ICanSaveModel
@@ -301,6 +304,52 @@ private static VersionInfo GetVersionInfo()
  }
  }
 
+ public sealed class RankingPredictionTransformer<TModel> : PredictionTransformerBase<TModel>
+ where TModel : class, IPredictorProducing<float>
+ {
+ private readonly GenericScorer _scorer;
+
+ public RankingPredictionTransformer(IHostEnvironment env, TModel model, ISchema inputSchema, string featureColumn)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), model, inputSchema, featureColumn)
+ {
+ var schema = new RoleMappedSchema(inputSchema, null, featureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, inputSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ internal RankingPredictionTransformer(IHostEnvironment env, ModelLoadContext ctx)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), ctx)
+ {
+ var schema = new RoleMappedSchema(TrainSchema, null, FeatureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, TrainSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ public override IDataView Transform(IDataView input)
+ {
+ Host.CheckValue(input, nameof(input));
+ return _scorer.ApplyToData(Host, input);
+ }
+
+ protected override void SaveCore(ModelSaveContext ctx)
+ {
+ Contracts.AssertValue(ctx);
+ ctx.SetVersionInfo(GetVersionInfo());
+
+ // *** Binary format ***
+ // <base info>
+ base.SaveCore(ctx);
+ }
+
+ private static VersionInfo GetVersionInfo()
+ {
+ return new VersionInfo(
+ modelSignature: "MC RANK",
+ verWrittenCur: 0x00010001, // Initial
+ verReadableCur: 0x00010001,
+ verWeCanReadBack: 0x00010001,
+ loaderSignature: RankingPredictionTransformer.LoaderSignature);
+ }
+ }
+
  internal static class BinaryPredictionTransformer
  {
  public const string LoaderSignature = "BinaryPredXfer";
@@ -324,4 +373,12 @@ internal static class RegressionPredictionTransformer
  public static RegressionPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
  => new RegressionPredictionTransformer<IPredictorProducing<float>>(env, ctx);
  }
+
+ internal static class RankingPredictionTransformer
+ {
+ public const string LoaderSignature = "RankingPredXfer";
+
+ public static RankingPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
+ => new RankingPredictionTransformer<IPredictorProducing<float>>(env, ctx);
+ }
 }

src/Microsoft.ML.Ensemble/OutputCombiners/MultiStacking.cs

@@ -57,7 +57,7 @@ public Arguments()
  env => new Ova(env, new Ova.Arguments()
  {
  PredictorType = ComponentFactoryUtils.CreateFromFunction(
-e => new AveragedPerceptronTrainer(e, new AveragedPerceptronTrainer.Arguments()))
+ e => new FastTreeBinaryClassificationTrainer(e, DefaultColumnNames.Label, DefaultColumnNames.Features))
  }));
  }
  }

src/Microsoft.ML.Ensemble/OutputCombiners/RegressionStacking.cs

@@ -49,7 +49,7 @@ public sealed class Arguments : ArgumentsBase, ISupportRegressionOutputCombinerF
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeRegressionTrainer(env, new FastTreeRegressionTrainer.Arguments()));
+ env => new FastTreeRegressionTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IRegressionOutputCombiner CreateComponent(IHostEnvironment env) => new RegressionStacking(env, this);

src/Microsoft.ML.Ensemble/OutputCombiners/Stacking.cs

@@ -5,6 +5,7 @@
 using System;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Ensemble.OutputCombiners;
 using Microsoft.ML.Runtime.EntryPoints;
 using Microsoft.ML.Runtime.FastTree;
@@ -46,7 +47,7 @@ public sealed class Arguments : ArgumentsBase, ISupportBinaryOutputCombinerFacto
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()));
+ env => new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IBinaryOutputCombiner CreateComponent(IHostEnvironment env) => new Stacking(env, this);

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -6,17 +6,25 @@
 
 using System;
 using System.Linq;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.FastTree.Internal;
 using Microsoft.ML.Runtime.Internal.Internallearn;
 
 namespace Microsoft.ML.Runtime.FastTree
 {
- public abstract class BoostingFastTreeTrainerBase<TArgs, TPredictor> : FastTreeTrainerBase<TArgs, TPredictor>
+ public abstract class BoostingFastTreeTrainerBase<TArgs, TTransformer, TModel> : FastTreeTrainerBase<TArgs, TTransformer, TModel>
+ where TTransformer : IPredictionTransformer<TModel>
  where TArgs : BoostedTreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
- public BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args) : base(env, args)
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label) : base(env, args, label)
+ {
+ }
+
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(env, label, featureColumn, weightColumn, groupIdColumn, advancedSettings)
  {
  }
 

src/Microsoft.ML.FastTree/FastTree.cs

@@ -12,6 +12,7 @@
 using System.IO;
 using System.Linq;
 using System.Text;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Data.Conversion;
@@ -43,10 +44,11 @@ internal static class FastTreeShared
  public static readonly object TrainLock = new object();
  }
 
- public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
- TrainerBase<TPredictor>
+ public abstract class FastTreeTrainerBase<TArgs, TTransformer, TModel> :
+ TrainerEstimatorBase<TTransformer, TModel>
+ where TTransformer: IPredictionTransformer<TModel>
  where TArgs : TreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
  protected readonly TArgs Args;
  protected readonly bool AllowGC;
@@ -87,34 +89,53 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
  private protected virtual bool NeedCalibration => false;
 
- private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args)
- : base(env, RegisterName)
+ /// <summary>
+ /// Constructor to use when instantiating the classing deriving from here through the API.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(featureColumn), label, MakeWeightColumn(weightColumn))
+ {
+ Args = new TArgs();
+
+ //apply the advanced args, if the user supplied any
+ advancedSettings?.Invoke(Args);
+ Args.LabelColumn = label.Name;
+
+ if (weightColumn != null)
+ Args.WeightColumn = weightColumn;
+
+ if (groupIdColumn != null)
+ Args.GroupIdColumn = 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.
+ // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
+ Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
+ // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
+
+ Initialize(env);
+ }
+
+ /// <summary>
+ /// Legacy constructor that is used when invoking the classsing deriving from this, through maml.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(args.FeatureColumn), label, MakeWeightColumn(args.WeightColumn))
  {
  Host.CheckValue(args, nameof(args));
  Args = args;
  // 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.
  // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
  Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
- int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
- if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
- {
- using (var ch = Host.Start("FastTreeTrainerBase"))
- {
- numThreads = Host.ConcurrencyFactor;
- ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
- + "setting of the environment. Using {0} training threads instead.", numThreads);
- ch.Done();
- }
- }
- ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
- ParallelTraining.InitEnvironment();
  // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
- // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from ConsoleEnvironment.
- AllowGC = (env is HostEnvironmentBase<ConsoleEnvironment>);
- Tests = new List<Test>();
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
 
-InitializeThreads(numThreads);
+Initialize(env);
  }
 
  protected abstract void PrepareLabels(IChannel ch);
@@ -133,6 +154,39 @@ protected virtual Float GetMaxLabel()
  return Float.PositiveInfinity;
  }
 
+ private static SchemaShape.Column MakeWeightColumn(string weightColumn)
+ {
+ if (weightColumn == null)
+ return null;
+ return new SchemaShape.Column(weightColumn, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false);
+ }
+
+ private static SchemaShape.Column MakeFeatureColumn(string featureColumn)
+ {
+ return new SchemaShape.Column(featureColumn, SchemaShape.Column.VectorKind.Vector, NumberType.R4, false);
+ }
+
+ private void Initialize(IHostEnvironment env)
+ {
+ int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
+ if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
+ {
+ using (var ch = Host.Start("FastTreeTrainerBase"))
+ {
+ numThreads = Host.ConcurrencyFactor;
+ ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
+ + "setting of the environment. Using {0} training threads instead.", numThreads);
+ ch.Done();
+ }
+ }
+ ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
+ ParallelTraining.InitEnvironment();
+
+ Tests = new List<Test>();
+
+ InitializeThreads(numThreads);
+ }
+
  protected void ConvertData(RoleMappedData trainData)
  {
  trainData.Schema.Schema.TryGetColumnIndex(DefaultColumnNames.Features, out int featureIndex);

src/Microsoft.ML.Api/TypedCursor.cs

@@ -622,7 +622,7 @@ public ICursor GetRootCursor()
  /// </summary>
  public static class CursoringUtils
  {
- private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new TlcEnvironment().";
+ private const string NeedEnvObsoleteMessage = "This method is obsolete. Please use the overload that takes an additional 'env' argument. An environment can be created via new LocalEnvironment().";
 
  /// <summary>
  /// Generate a strongly-typed cursorable wrapper of the <see cref="IDataView"/>.

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -18,6 +18,9 @@
 [assembly: LoadableClass(typeof(RegressionPredictionTransformer<IPredictorProducing<float>>), typeof(RegressionPredictionTransformer), null, typeof(SignatureLoadModel),
  "", RegressionPredictionTransformer.LoaderSignature)]
 
+[assembly: LoadableClass(typeof(RankingPredictionTransformer<IPredictorProducing<float>>), typeof(RankingPredictionTransformer), null, typeof(SignatureLoadModel),
+ "", RankingPredictionTransformer.LoaderSignature)]
+
 namespace Microsoft.ML.Runtime.Data
 {
  public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer<TModel>, ICanSaveModel
@@ -301,6 +304,52 @@ private static VersionInfo GetVersionInfo()
  }
  }
 
+ public sealed class RankingPredictionTransformer<TModel> : PredictionTransformerBase<TModel>
+ where TModel : class, IPredictorProducing<float>
+ {
+ private readonly GenericScorer _scorer;
+
+ public RankingPredictionTransformer(IHostEnvironment env, TModel model, ISchema inputSchema, string featureColumn)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), model, inputSchema, featureColumn)
+ {
+ var schema = new RoleMappedSchema(inputSchema, null, featureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, inputSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ internal RankingPredictionTransformer(IHostEnvironment env, ModelLoadContext ctx)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(nameof(RankingPredictionTransformer<TModel>)), ctx)
+ {
+ var schema = new RoleMappedSchema(TrainSchema, null, FeatureColumn);
+ _scorer = new GenericScorer(Host, new GenericScorer.Arguments(), new EmptyDataView(Host, TrainSchema), BindableMapper.Bind(Host, schema), schema);
+ }
+
+ public override IDataView Transform(IDataView input)
+ {
+ Host.CheckValue(input, nameof(input));
+ return _scorer.ApplyToData(Host, input);
+ }
+
+ protected override void SaveCore(ModelSaveContext ctx)
+ {
+ Contracts.AssertValue(ctx);
+ ctx.SetVersionInfo(GetVersionInfo());
+
+ // *** Binary format ***
+ // <base info>
+ base.SaveCore(ctx);
+ }
+
+ private static VersionInfo GetVersionInfo()
+ {
+ return new VersionInfo(
+ modelSignature: "MC RANK",
+ verWrittenCur: 0x00010001, // Initial
+ verReadableCur: 0x00010001,
+ verWeCanReadBack: 0x00010001,
+ loaderSignature: RankingPredictionTransformer.LoaderSignature);
+ }
+ }
+
  internal static class BinaryPredictionTransformer
  {
  public const string LoaderSignature = "BinaryPredXfer";
@@ -324,4 +373,12 @@ internal static class RegressionPredictionTransformer
  public static RegressionPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
  => new RegressionPredictionTransformer<IPredictorProducing<float>>(env, ctx);
  }
+
+ internal static class RankingPredictionTransformer
+ {
+ public const string LoaderSignature = "RankingPredXfer";
+
+ public static RankingPredictionTransformer<IPredictorProducing<float>> Create(IHostEnvironment env, ModelLoadContext ctx)
+ => new RankingPredictionTransformer<IPredictorProducing<float>>(env, ctx);
+ }
 }

src/Microsoft.ML.Ensemble/OutputCombiners/MultiStacking.cs

@@ -57,7 +57,7 @@ public Arguments()
  env => new Ova(env, new Ova.Arguments()
  {
  PredictorType = ComponentFactoryUtils.CreateFromFunction(
-e => new AveragedPerceptronTrainer(e, new AveragedPerceptronTrainer.Arguments()))
+ e => new FastTreeBinaryClassificationTrainer(e, DefaultColumnNames.Label, DefaultColumnNames.Features))
  }));
  }
  }

src/Microsoft.ML.Ensemble/OutputCombiners/RegressionStacking.cs

@@ -49,7 +49,7 @@ public sealed class Arguments : ArgumentsBase, ISupportRegressionOutputCombinerF
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeRegressionTrainer(env, new FastTreeRegressionTrainer.Arguments()));
+ env => new FastTreeRegressionTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IRegressionOutputCombiner CreateComponent(IHostEnvironment env) => new RegressionStacking(env, this);

src/Microsoft.ML.Ensemble/OutputCombiners/Stacking.cs

@@ -5,6 +5,7 @@
 using System;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Runtime.CommandLine;
+using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Ensemble.OutputCombiners;
 using Microsoft.ML.Runtime.EntryPoints;
 using Microsoft.ML.Runtime.FastTree;
@@ -46,7 +47,7 @@ public sealed class Arguments : ArgumentsBase, ISupportBinaryOutputCombinerFacto
  public Arguments()
  {
  BasePredictorType = ComponentFactoryUtils.CreateFromFunction(
- env => new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()));
+ env => new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features));
  }
 
  public IBinaryOutputCombiner CreateComponent(IHostEnvironment env) => new Stacking(env, this);

src/Microsoft.ML.FastTree/BoostingFastTree.cs

@@ -6,17 +6,25 @@
 
 using System;
 using System.Linq;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.FastTree.Internal;
 using Microsoft.ML.Runtime.Internal.Internallearn;
 
 namespace Microsoft.ML.Runtime.FastTree
 {
- public abstract class BoostingFastTreeTrainerBase<TArgs, TPredictor> : FastTreeTrainerBase<TArgs, TPredictor>
+ public abstract class BoostingFastTreeTrainerBase<TArgs, TTransformer, TModel> : FastTreeTrainerBase<TArgs, TTransformer, TModel>
+ where TTransformer : IPredictionTransformer<TModel>
  where TArgs : BoostedTreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
- public BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args) : base(env, args)
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label) : base(env, args, label)
+ {
+ }
+
+ protected BoostingFastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(env, label, featureColumn, weightColumn, groupIdColumn, advancedSettings)
  {
  }
 

src/Microsoft.ML.FastTree/FastTree.cs

@@ -12,6 +12,7 @@
 using System.IO;
 using System.Linq;
 using System.Text;
+using Microsoft.ML.Core.Data;
 using Microsoft.ML.Runtime.CommandLine;
 using Microsoft.ML.Runtime.Data;
 using Microsoft.ML.Runtime.Data.Conversion;
@@ -43,10 +44,11 @@ internal static class FastTreeShared
  public static readonly object TrainLock = new object();
  }
 
- public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
- TrainerBase<TPredictor>
+ public abstract class FastTreeTrainerBase<TArgs, TTransformer, TModel> :
+ TrainerEstimatorBase<TTransformer, TModel>
+ where TTransformer: IPredictionTransformer<TModel>
  where TArgs : TreeArgs, new()
- where TPredictor : IPredictorProducing<Float>
+ where TModel : IPredictorProducing<Float>
  {
  protected readonly TArgs Args;
  protected readonly bool AllowGC;
@@ -87,34 +89,53 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
  private protected virtual bool NeedCalibration => false;
 
- private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args)
- : base(env, RegisterName)
+ /// <summary>
+ /// Constructor to use when instantiating the classing deriving from here through the API.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, SchemaShape.Column label, string featureColumn,
+ string weightColumn = null, string groupIdColumn = null, Action<TArgs> advancedSettings = null)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(featureColumn), label, MakeWeightColumn(weightColumn))
+ {
+ Args = new TArgs();
+
+ //apply the advanced args, if the user supplied any
+ advancedSettings?.Invoke(Args);
+ Args.LabelColumn = label.Name;
+
+ if (weightColumn != null)
+ Args.WeightColumn = weightColumn;
+
+ if (groupIdColumn != null)
+ Args.GroupIdColumn = 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.
+ // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
+ Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
+ // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
+
+ Initialize(env);
+ }
+
+ /// <summary>
+ /// Legacy constructor that is used when invoking the classsing deriving from this, through maml.
+ /// </summary>
+ private protected FastTreeTrainerBase(IHostEnvironment env, TArgs args, SchemaShape.Column label)
+ : base(Contracts.CheckRef(env, nameof(env)).Register(RegisterName), MakeFeatureColumn(args.FeatureColumn), label, MakeWeightColumn(args.WeightColumn))
  {
  Host.CheckValue(args, nameof(args));
  Args = args;
  // 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.
  // Finally, even the binary classifiers, being logitboost, tend to not benefit from external calibration.
  Info = new TrainerInfo(normalization: false, caching: false, calibration: NeedCalibration, supportValid: true);
- int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
- if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
- {
- using (var ch = Host.Start("FastTreeTrainerBase"))
- {
- numThreads = Host.ConcurrencyFactor;
- ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
- + "setting of the environment. Using {0} training threads instead.", numThreads);
- ch.Done();
- }
- }
- ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
- ParallelTraining.InitEnvironment();
  // REVIEW: CLR 4.6 has a bug that is only exposed in Scope, and if we trigger GC.Collect in scope environment
- // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from ConsoleEnvironment.
- AllowGC = (env is HostEnvironmentBase<ConsoleEnvironment>);
- Tests = new List<Test>();
+ // with memory consumption more than 5GB, GC get stuck in infinite loop. So for now let's call GC only if we call things from LocalEnvironment.
+ AllowGC = (env is HostEnvironmentBase<LocalEnvironment>);
 
-InitializeThreads(numThreads);
+Initialize(env);
  }
 
  protected abstract void PrepareLabels(IChannel ch);
@@ -133,6 +154,39 @@ protected virtual Float GetMaxLabel()
  return Float.PositiveInfinity;
  }
 
+ private static SchemaShape.Column MakeWeightColumn(string weightColumn)
+ {
+ if (weightColumn == null)
+ return null;
+ return new SchemaShape.Column(weightColumn, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false);
+ }
+
+ private static SchemaShape.Column MakeFeatureColumn(string featureColumn)
+ {
+ return new SchemaShape.Column(featureColumn, SchemaShape.Column.VectorKind.Vector, NumberType.R4, false);
+ }
+
+ private void Initialize(IHostEnvironment env)
+ {
+ int numThreads = Args.NumThreads ?? Environment.ProcessorCount;
+ if (Host.ConcurrencyFactor > 0 && numThreads > Host.ConcurrencyFactor)
+ {
+ using (var ch = Host.Start("FastTreeTrainerBase"))
+ {
+ numThreads = Host.ConcurrencyFactor;
+ ch.Warning("The number of threads specified in trainer arguments is larger than the concurrency factor "
+ + "setting of the environment. Using {0} training threads instead.", numThreads);
+ ch.Done();
+ }
+ }
+ ParallelTraining = Args.ParallelTrainer != null ? Args.ParallelTrainer.CreateComponent(env) : new SingleTrainer();
+ ParallelTraining.InitEnvironment();
+
+ Tests = new List<Test>();
+
+ InitializeThreads(numThreads);
+ }
+
  protected void ConvertData(RoleMappedData trainData)
  {
  trainData.Schema.Schema.TryGetColumnIndex(DefaultColumnNames.Features, out int featureIndex);