Merge branch 'master' of https://github.com/dotnet/machinelearning into addx86prbuild

Author: artidoro

README.md

@@ -16,7 +16,7 @@ Along with these ML capabilities, this first release of ML.NET also brings the f
 
 [![NuGet Status](https://img.shields.io/nuget/v/Microsoft.ML.svg?style=flat)](https://www.nuget.org/packages/Microsoft.ML/)
 
-ML.NET runs on Windows, Linux, and macOS - any platform where 64 bit [.NET Core](https://github.com/dotnet/core) or later is available.
+ML.NET runs on Windows, Linux, and macOS - any platform where x64 [.NET Core](https://github.com/dotnet/core) or later is available. In addition, .NET Framework on Windows x64 is also supported.
 
 The current release is 0.6. Check out the [release notes](docs/release-notes/0.6/release-0.6.md) to see what's new.
 

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/code/MlNetCookBook.md

@@ -103,7 +103,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
     hasHeader: true);
 
 // Now read the file (remember though, readers are lazy, so the actual reading will happen when the data is accessed).
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 ```
 
 If the schema of the data is not known at compile time, or too cumbersome, you can revert to the dynamically-typed API: 
@@ -128,9 +128,43 @@ var reader = new TextLoader(mlContext, new TextLoader.Arguments
 });
 
 // Now read the file (remember though, readers are lazy, so the actual reading will happen when the data is accessed).
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 ```
 
+## How do I load data from multiple files?
+
+You can again use the `TextLoader`, and specify an array of files to its Read method.
+The files need to have the same schema (same number and type of columns) 
+
+[Example file1](../../test/data/adult.train):
+[Example file2](../../test/data/adult.test):
+```
+Label	Workclass	education	marital-status
+0	Private	11th	Never-married
+0	Private	HS-grad	Married-civ-spouse
+1	Local-gov	Assoc-acdm	Married-civ-spouse
+1	Private	Some-college	Married-civ-spouse
+```
+
+This is how you can read this data:
+```csharp
+// Create a new environment for ML.NET operations. It can be used for exception tracking and logging, 
+// as well as the source of randomness.
+var env = new LocalEnvironment();
+
+// Create the reader: define the data columns and where to find them in the text file.
+var reader = TextLoader.CreateReader(env, ctx => (
+        // A boolean column depicting the 'target label'.
+        IsOver50K: ctx.LoadBool(14),
+        // Three text columns.
+        Workclass: ctx.LoadText(1),
+        Education: ctx.LoadText(3),
+        MaritalStatus: ctx.LoadText(5)),
+    hasHeader: true);
+
+// Now read the files (remember though, readers are lazy, so the actual reading will happen when the data is accessed).
+var data = reader.Read(exampleFile1, exampleFile2);
+
 ## How do I load data with many columns from a CSV?
 `TextLoader` is used to load data from text files. You will need to specify what are the data columns, what are their types, and where to find them in the text file. 
 
@@ -162,7 +196,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
 
 
 // Now read the file (remember though, readers are lazy, so the actual reading will happen when the data is accessed).
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 ```
 
 
@@ -183,7 +217,7 @@ var reader = mlContext.Data.TextReader(new[] {
     s => s.Separator = ",");
 
 // Now read the file (remember though, readers are lazy, so the actual reading will happen when the data is accessed).
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 ```
 
 ## How do I look at the intermediate data?
@@ -231,7 +265,7 @@ var dataPipeline = reader.MakeNewEstimator()
 
 // Let's verify that the data has been read correctly. 
 // First, we read the data file.
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 
 // Fit our data pipeline and transform data with it.
 var transformedData = dataPipeline.Fit(data).Transform(data);
@@ -305,7 +339,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
 
 
 // Now read the file (remember though, readers are lazy, so the actual reading will happen when the data is accessed).
-var trainData = reader.Read(new MultiFileSource(trainDataPath));
+var trainData = reader.Read(trainDataPath);
 
 // Step two: define the learning pipeline. 
 
@@ -334,7 +368,7 @@ You can use the corresponding 'context' of the task to evaluate the model.
 Assuming the example above was used to train the model, here's how you calculate the metrics.
 ```csharp
 // Read the test dataset.
-var testData = reader.Read(new MultiFileSource(testDataPath));
+var testData = reader.Read(testDataPath);
 // Calculate metrics of the model on the test data.
 var metrics = mlContext.Regression.Evaluate(model.Transform(testData), label: r => r.Target, score: r => r.Prediction);
 ```
@@ -390,7 +424,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
     separator: ',');
 
 // Retrieve the training data.
-var trainData = reader.Read(new MultiFileSource(irisDataPath));
+var trainData = reader.Read(irisDataPath);
 
 // Build the training pipeline.
 var learningPipeline = reader.MakeNewEstimator()
@@ -557,7 +591,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
     separator: ',');
 
 // Retrieve the training data.
-var trainData = reader.Read(new MultiFileSource(dataPath));
+var trainData = reader.Read(dataPath);
 
 // This is the predictor ('weights collection') that we will train.
 MulticlassLogisticRegressionPredictor predictor = null;
@@ -648,7 +682,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
     separator: ',');
 
 // Read the training data.
-var trainData = reader.Read(new MultiFileSource(dataPath));
+var trainData = reader.Read(dataPath);
 
 // Apply all kinds of standard ML.NET normalization to the raw features.
 var pipeline = reader.MakeNewEstimator()
@@ -707,7 +741,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
     ), hasHeader: true);
 
 // Read the data.
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 
 // Inspect the categorical columns to check that they are correctly read.
 var catColumns = data.GetColumn(r => r.CategoricalFeatures).Take(10).ToArray();
@@ -784,7 +818,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
     ), hasHeader: true);
 
 // Read the data.
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 
 // Inspect the message texts that are read from the file.
 var messageTexts = data.GetColumn(x => x.Message).Take(20).ToArray();
@@ -849,7 +883,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
     separator: ',');
 
 // Read the data.
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 
 // Build the training pipeline.
 var learningPipeline = reader.MakeNewEstimator()
@@ -910,7 +944,7 @@ var reader = TextLoader.CreateReader(mlContext, ctx => (
     separator: ',');
 
 // Read the data.
-var data = reader.Read(new MultiFileSource(dataPath));
+var data = reader.Read(dataPath);
 
 // Build the pre-processing pipeline.
 var learningPipeline = reader.MakeNewEstimator()

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.Runtime.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
@@ -37,7 +40,7 @@ public static void SdcaRegression()
                 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 data = reader.Read(dataFile);
             var (trainData, testData) = regressionContext.TrainTestSplit(data, testFraction: 0.1);
 
             // The predictor that gets produced out of training
@@ -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/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];