Merge remote-tracking branch 'origin/master' into singlis/drop4

Author: singlis

build/Dependencies.props

@@ -38,7 +38,7 @@
   <!-- Test-only Dependencies -->
   <PropertyGroup>
     <BenchmarkDotNetVersion>0.11.1</BenchmarkDotNetVersion>
-    <MicrosoftMLTestModelsPackageVersion>0.0.2-test</MicrosoftMLTestModelsPackageVersion>
+    <MicrosoftMLTestModelsPackageVersion>0.0.3-test</MicrosoftMLTestModelsPackageVersion>
   </PropertyGroup>
 
 </Project>

docs/samples/Microsoft.ML.Samples/Microsoft.ML.Samples.csproj

@@ -7,7 +7,10 @@
 
   <ItemGroup>
     <ProjectReference Include="..\..\..\src\Microsoft.ML.StandardLearners\Microsoft.ML.StandardLearners.csproj" />
-     <ProjectReference Include="..\..\..\src\Microsoft.ML.SamplesUtils\Microsoft.ML.SamplesUtils.csproj" />
+    <ProjectReference Include="..\..\..\src\Microsoft.ML.SamplesUtils\Microsoft.ML.SamplesUtils.csproj" />
+    <ProjectReference Include="..\..\..\src\Microsoft.ML.FastTree\Microsoft.ML.FastTree.csproj" />
+    <ProjectReference Include="..\..\..\src\Microsoft.ML.LightGBM\Microsoft.ML.LightGBM.csproj" />
+
 
     <NativeAssemblyReference Include="CpuMathNative" />
 

docs/samples/Microsoft.ML.Samples/Trainers.cs

@@ -1,21 +1,24 @@
-// Licensed to the .NET Foundation under one or more agreements.
+// Licensed to the .NET Foundation under one or more agreements.
 // The .NET Foundation licenses this file to you under the MIT license.
 // See the LICENSE file in the project root for more information.
 
 // the alignment of the usings with the methods is intentional so they can display on the same level in the docs site. 
         using Microsoft.ML.Runtime.Data;
         using Microsoft.ML.Runtime.Learners;
+        using Microsoft.ML.Runtime.LightGBM;
+        using Microsoft.ML.Trainers.FastTree;
         using Microsoft.ML.StaticPipe;
         using System;
+        using System.Linq;
 
 // NOTE: WHEN ADDING TO THE FILE, ALWAYS APPEND TO THE END OF IT. 
 // If you change the existinc content, check that the files referencing it in the XML documentation are still correct, as they reference
 // line by line. 
 namespace Microsoft.ML.Samples
 {
     public static class Trainers
-    { 
-    
+    {
+
         public static void SdcaRegression()
         {
             // Downloading a regression dataset from github.com/dotnet/machinelearning
@@ -74,5 +77,119 @@ public static void SdcaRegression()
             Console.WriteLine($"RMS - {metrics.Rms}");  // 4.924493
             Console.WriteLine($"RSquared - {metrics.RSquared}");  // 0.565467
         }
+
+        public static void FastTreeRegression()
+        {
+            // Downloading a regression dataset from github.com/dotnet/machinelearning
+            // this will create a housing.txt file in the filsystem this code will run
+            // you can open the file to see the data. 
+            string dataFile = SamplesUtils.DatasetUtils.DownloadHousingRegressionDataset();
+
+            // Creating the ML.Net IHostEnvironment object, needed for the pipeline
+            var env = new LocalEnvironment(seed: 0);
+
+            // Creating the ML context, based on the task performed.
+            var regressionContext = new RegressionContext(env);
+
+            // Creating a data reader, based on the format of the data
+            var reader = TextLoader.CreateReader(env, c => (
+                        label: c.LoadFloat(0),
+                        features: c.LoadFloat(1, 6)
+                    ),
+                separator: '\t', hasHeader: true);
+
+            // Read the data, and leave 10% out, so we can use them for testing
+            var data = reader.Read(new MultiFileSource(dataFile));
+
+            // The predictor that gets produced out of training
+            FastTreeRegressionPredictor pred = null;
+
+            // Create the estimator
+            var learningPipeline = reader.MakeNewEstimator()
+                .Append(r => (r.label, score: regressionContext.Trainers.FastTree(
+                                            r.label,
+                                            r.features,
+                                            numTrees: 100, // try: (int) 20-2000
+                                            numLeaves: 20, // try: (int) 2-128
+                                            minDatapointsInLeafs: 10, // try: (int) 1-100
+                                            learningRate: 0.2, // try: (float) 0.025-0.4    
+                                        onFit: p => pred = p)
+                                )
+                        );
+
+            var cvResults = regressionContext.CrossValidate(data, learningPipeline, r => r.label, numFolds: 5);
+            var averagedMetrics = (
+                L1: cvResults.Select(r => r.metrics.L1).Average(),
+                L2: cvResults.Select(r => r.metrics.L2).Average(),
+                LossFn: cvResults.Select(r => r.metrics.LossFn).Average(),
+                Rms: cvResults.Select(r => r.metrics.Rms).Average(),
+                RSquared: cvResults.Select(r => r.metrics.RSquared).Average()
+            );
+            Console.WriteLine($"L1 - {averagedMetrics.L1}");
+            Console.WriteLine($"L2 - {averagedMetrics.L2}");
+            Console.WriteLine($"LossFunction - {averagedMetrics.LossFn}");
+            Console.WriteLine($"RMS - {averagedMetrics.Rms}");
+            Console.WriteLine($"RSquared - {averagedMetrics.RSquared}");
+        }
+
+        public static void LightGbmRegression()
+        {
+            // Downloading a regression dataset from github.com/dotnet/machinelearning
+            // this will create a housing.txt file in the filsystem this code will run
+            // you can open the file to see the data. 
+            string dataFile = SamplesUtils.DatasetUtils.DownloadHousingRegressionDataset();
+
+            // Creating the ML.Net IHostEnvironment object, needed for the pipeline
+            var env = new LocalEnvironment(seed: 0);
+
+            // Creating the ML context, based on the task performed.
+            var regressionContext = new RegressionContext(env);
+
+            // Creating a data reader, based on the format of the data
+            var reader = TextLoader.CreateReader(env, c => (
+                        label: c.LoadFloat(0),
+                        features: c.LoadFloat(1, 6)
+                    ),
+                separator: '\t', hasHeader: true);
+
+            // Read the data, and leave 10% out, so we can use them for testing
+            var data = reader.Read(new MultiFileSource(dataFile));
+            var (trainData, testData) = regressionContext.TrainTestSplit(data, testFraction: 0.1);
+
+            // The predictor that gets produced out of training
+            LightGbmRegressionPredictor pred = null;
+
+            // Create the estimator
+            var learningPipeline = reader.MakeNewEstimator()
+                .Append(r => (r.label, score: regressionContext.Trainers.LightGbm(
+                                            r.label,
+                                            r.features,
+                                            numLeaves: 4,
+                                            minDataPerLeaf: 6,
+                                            learningRate: 0.001,
+                                        onFit: p => pred = p)
+                                )
+                        );
+
+            // Fit this pipeline to the training data
+            var model = learningPipeline.Fit(trainData);
+
+            // Check the weights that the model learned
+            VBuffer<float> weights = default;
+            pred.GetFeatureWeights(ref weights);
+
+            Console.WriteLine($"weight 0 - {weights.Values[0]}");
+            Console.WriteLine($"weight 1 - {weights.Values[1]}");
+
+            // Evaluate how the model is doing on the test data
+            var dataWithPredictions = model.Transform(testData);
+            var metrics = regressionContext.Evaluate(dataWithPredictions, r => r.label, r => r.score);
+
+            Console.WriteLine($"L1 - {metrics.L1}");
+            Console.WriteLine($"L2 - {metrics.L2}");
+            Console.WriteLine($"LossFunction - {metrics.LossFn}");
+            Console.WriteLine($"RMS - {metrics.Rms}");
+            Console.WriteLine($"RSquared - {metrics.RSquared}");
+        }
     }
 }

src/Common/AssemblyLoadingUtils.cs

@@ -6,6 +6,7 @@
 using System;
 using System.IO;
 using System.IO.Compression;
+using System.Linq;
 using System.Reflection;
 
 namespace Microsoft.ML.Runtime

src/Microsoft.ML.Api/InternalSchemaDefinition.cs

@@ -217,7 +217,10 @@ public static InternalSchemaDefinition Create(Type userType, Direction direction
         public static InternalSchemaDefinition Create(Type userType, SchemaDefinition userSchemaDefinition)
         {
             Contracts.AssertValue(userType);
-            Contracts.AssertValue(userSchemaDefinition);
+            Contracts.AssertValueOrNull(userSchemaDefinition);
+
+            if (userSchemaDefinition == null)
+                userSchemaDefinition = SchemaDefinition.Create(userType);
 
             Column[] dstCols = new Column[userSchemaDefinition.Count];
 

src/Microsoft.ML.Api/TypedCursor.cs

@@ -231,7 +231,7 @@ public IRowCursor<TRow>[] GetCursorSet(out IRowCursorConsolidator consolidator,
         /// <summary>
         /// Create a Cursorable object on a given data view.
         /// </summary>
-        /// <param name="env">Host enviroment.</param>
+        /// <param name="env">Host environment.</param>
         /// <param name="data">The underlying data view.</param>
         /// <param name="ignoreMissingColumns">Whether to ignore missing columns in the data view.</param>
         /// <param name="schemaDefinition">The optional user-provided schema.</param>

src/Microsoft.ML.Core/ComponentModel/LoadableClassAttribute.cs

@@ -19,7 +19,7 @@ public sealed class LoadableClassAttribute : LoadableClassAttributeBase
     {
         /// <summary>
         /// Assembly attribute used to specify that a class is loadable by a machine learning
-        /// host enviroment, such as TLC
+        /// host environment, such as TLC
         /// </summary>
         /// <param name="instType">The class type that is loadable</param>
         /// <param name="argType">The argument type that the constructor takes (may be null)</param>
@@ -33,7 +33,7 @@ public LoadableClassAttribute(Type instType, Type argType, Type sigType, string
 
         /// <summary>
         /// Assembly attribute used to specify that a class is loadable by a machine learning
-        /// host enviroment, such as TLC
+        /// host environment, such as TLC
         /// </summary>
         /// <param name="instType">The class type that is loadable</param>
         /// <param name="loaderType">The class type that contains the construction method</param>
@@ -58,7 +58,7 @@ public LoadableClassAttribute(Type instType, Type loaderType, Type argType, Type
 
         /// <summary>
         /// Assembly attribute used to specify that a class is loadable by a machine learning
-        /// host enviroment, such as TLC
+        /// host environment, such as TLC
         /// </summary>
         /// <param name="summary">The description summary of the class type</param>
         /// <param name="instType">The class type that is loadable</param>
@@ -73,7 +73,7 @@ public LoadableClassAttribute(string summary, Type instType, Type argType, Type
 
         /// <summary>
         /// Assembly attribute used to specify that a class is loadable by a machine learning
-        /// host enviroment, such as TLC
+        /// host environment, such as TLC
         /// </summary>
         /// <param name="summary">The description summary of the class type</param>
         /// <param name="instType">The class type that is loadable</param>

src/Microsoft.ML.Core/Data/IHostEnvironment.cs

@@ -69,7 +69,7 @@ public interface IHostEnvironment : IChannelProvider, IProgressChannelProvider
         /// handles and ensure that they are disposed properly when the environment is "shut down".
         ///
         /// The suffix and prefix are optional. A common use for suffix is to specify an extension, eg, ".txt".
-        /// The use of suffix and prefix, including whether they have any affect, is up to the host enviroment.
+        /// The use of suffix and prefix, including whether they have any affect, is up to the host environment.
         /// </summary>
         IFileHandle CreateTempFile(string suffix = null, string prefix = null);
     }

src/Microsoft.ML.Core/Data/ProgressReporter.cs

@@ -468,6 +468,17 @@ public List<ProgressEvent> GetAllProgress()
 
                 return list;
             }
+
+            public void Reset()
+            {
+                lock (_lock)
+                {
+                    while (!_pendingEvents.IsEmpty)
+                        _pendingEvents.TryDequeue(out var res);
+                    _namesUsed.Clear();
+                    _index = 0;
+                }
+            }
         }
 
         /// <summary>

src/Microsoft.ML.Core/Environment/ConsoleEnvironment.cs

@@ -430,6 +430,11 @@ internal IDisposable RedirectChannelOutput(TextWriter newOutWriter, TextWriter n
             return new OutputRedirector(this, newOutWriter, newErrWriter);
         }
 
+        internal void ResetProgressChannel()
+        {
+            ProgressTracker.Reset();
+        }
+
         private sealed class OutputRedirector : IDisposable
         {
             private readonly ConsoleEnvironment _root;