Merge pull request #7 from dotnet/master

Merge

Author: ganik

BuildToolsVersion.txt

@@ -1 +1 @@
-3.0.0-preview1-03721-01
+3.0.0-preview1-03801-01

README.md

@@ -18,7 +18,7 @@ Along with these ML capabilities, this first release of ML.NET also brings the f
 
 ML.NET runs on Windows, Linux, and macOS using [.NET Core](https://github.com/dotnet/core), or Windows using .NET Framework. 64 bit is supported on all platforms. 32 bit is supported on Windows, except for TensorFlow, LightGBM, and ONNX related functionality.
 
-The current release is 0.10. Check out the [release notes](docs/release-notes/0.10/release-0.10.md) to see what's new.
+The current release is 0.11. Check out the [release notes](docs/release-notes/0.11/release-0.11.md) to see what's new.
 
 First, ensure you have installed [.NET Core 2.1](https://www.microsoft.com/net/learn/get-started) or later. ML.NET also works on the .NET Framework 4.6.1 or later, but 4.7.2 or later is recommended.
 
@@ -46,7 +46,7 @@ To build ML.NET from source please visit our [developers guide](docs/project-doc
 
 |    | Debug | Release |
 |:---|----------------:|------------------:|
-|**Linux**|[![x64-debug](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobname=Linux&configuration=Build_Debug)](https://dnceng.visualstudio.com/DotNet-Public/_build/latest?definitionId=104&branch=master)|[![x64-release](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobname=Linux&configuration=Build_Release)](https://dnceng.visualstudio.com/DotNet-Public/_build/latest?definitionId=104&branch=master)|
+|**CentOS**|[![x64-debug](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobname=CentOS&configuration=Build_Debug_Intrinsics)](https://dnceng.visualstudio.com/DotNet-Public/_build/latest?definitionId=104&branch=master)|[![x64-release](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobname=CentOS&configuration=Build_Release)](https://dnceng.visualstudio.com/DotNet-Public/_build/latest?definitionId=104&branch=master)|
 |**macOS**|[![x64-debug](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobname=macOS&configuration=Build_Debug)](https://dnceng.visualstudio.com/DotNet-Public/_build/latest?definitionId=104&branch=master)|[![x64-release](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobname=macOS&configuration=Build_Release)](https://dnceng.visualstudio.com/DotNet-Public/_build/latest?definitionId=104&branch=master)|
 |**Windows x64**|[![x64-debug](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobname=Windows_x64&configuration=Build_Debug)](https://dnceng.visualstudio.com/DotNet-Public/_build/latest?definitionId=104&branch=master)|[![x64-release](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobname=Windows_x64&configuration=Build_Release)](https://dnceng.visualstudio.com/DotNet-Public/_build/latest?definitionId=104&branch=master)|
 |**Windows x86**|[![Build Status](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobName=Windows_x86&configuration=Build_Debug)](https://dnceng.visualstudio.com/public/_build/latest?definitionId=104?branchName=master)|[![Build Status](https://dnceng.visualstudio.com/public/_apis/build/status/dotnet/machinelearning/MachineLearning-CI?branchName=master&jobName=Windows_x86&configuration=Build_Release)](https://dnceng.visualstudio.com/public/_build/latest?definitionId=104?branchName=master)|
@@ -69,16 +69,14 @@ Here's an example of code to train a model to predict sentiment from text sample
 
 ```C#
 var mlContext = new MLContext();
-var reader = mlContext.Data.CreateTextLoader(new TextLoader.Arguments
-        {
-        Column = new[] {
-            new TextLoader.Column("SentimentText", DataKind.Text, 1),
-            new TextLoader.Column("Label", DataKind.Bool, 0),
-        },
-        HasHeader = true,
-        Separator = ","
-});
-var data = reader.Read(dataPath);
+var loader = mlContext.Data.CreateTextLoader(new[]
+    {
+        new TextLoader.Column("SentimentText", DataKind.String, 1),
+        new TextLoader.Column("Label", DataKind.Boolean, 0),
+    },
+    hasHeader: true,
+    separatorChar: ',');
+var data = loader.Load(dataPath);
 var learningPipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
         .Append(mlContext.BinaryClassification.Trainers.FastTree());
 var model = learningPipeline.Fit(data);
@@ -116,4 +114,3 @@ ML.NET is a [.NET Foundation](https://www.dotnetfoundation.org/projects) project
 There are many .NET related projects on GitHub.
 
 - [.NET home repo](https://github.com/Microsoft/dotnet) - links to 100s of .NET projects, from Microsoft and the community.
-

docs/building/MlNetMklDeps/MlNetMklDeps.nuspec

@@ -2,17 +2,22 @@
 <package xmlns="http://schemas.microsoft.com/packaging/2013/01/nuspec.xsd">
   <metadata>
     <id>MlNetMklDeps</id>
-    <version>0.0.0.7</version>
+    <version>0.0.0.9</version>
     <title>This NuGet package provides Intel(R) MKL dependencies for ML.NET</title>
     <authors>Intel Corporation</authors>
     <owners>Microsoft</owners>
     <projectUrl>https://dot.net/ml</projectUrl>
-    <licenseUrl>https://software.intel.com/en-us/license/intel-simplified-software-license</licenseUrl>
     <requireLicenseAcceptance>true</requireLicenseAcceptance>
     <description>
       Intel(R) MKL Dependencies for Microsoft ML.NET. 
     </description>
-    <copyright>Copyright (c) 2018 Intel Corporation.</copyright>
+    <copyright>Copyright (c) 2019 Intel Corporation.</copyright>
     <tags>ML.Net Mkl Deps</tags>
+    <license type="file">license.txt</license>
   </metadata>
+  <files>
+    <file src="licensing\license.txt" target="" />
+    <file src="licensing\third-party-programs.txt" target="" />
+    <file src="runtimes\**" target="runtimes" />
+  </files>
 </package>

docs/building/MlNetMklDeps/README.md

@@ -7,31 +7,48 @@ Windows (32 and 64 bit):
 - Open an admin command prompt and run the following commands, CAREFULLY INSPECTING THE COMMAND OUTPUT FOR ERRORS.
 - TLCROOT should be the root of your TLC_Resources folder.
 
+Directory layout for nuget file is as follows:
+* licensing (contains Intel's license.txt they ship MKL with along with any third party licenses)
+* runtimes
+**  linux-x64
+*** native (contains linux binaries)
+** osx-x64
+*** native (cntains osx binaries)
+** win-x64
+*** native (contains windows x64 binaries)
+** win-x86
+*** native (contains windows ia32 binaries)
+
 ##Windows
-1. Modify user_example_list file in directory to contain all required functions, that are present in the [mlnetmkl.list](mlnetmkl.list) file
-2. "C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat" x86
-3. nmake libia32 name=MklImports  (add threading=sequential if you are building without openmp)
-4. copy /Y Microsoft.ML.MklImports.* to the folder that will host the x86 binaries. 
-5. del Microsoft.ML.MklImports.*
-6. "C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat" amd64
-7. nmake intel64 name=MklImports (add threading=sequential if you are building without openmp)
-8. copy /Y Microsoft.ML.MklImports.* to the folder that will host the x64 binaries.
+1. In the Intel install directory, go to compilers_and_libraries\windows\mkl\tools\builder
+2. Modify user_example_list file in directory to contain all required functions, that are present in the [mlnetmkl.list
+](mlnetmkl.list) file
+3. "C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat" x86
+4. nmake libia32 name=MklImports (add threading=sequential if you are building without openmp)
+5. Copy MKL library: copy /Y MklImports.* to the folder that will host the x86 binaries.
+6. Copy openmp library:  copy /Y ..\..\..\redist\ia32_win\compiler\libiomp5md* to the folder for x86 binaries.
+7. del MklImports.*
+8. "C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat" amd64
+9. nmake intel64 name=MklImports (add threading=sequential if you are building without openmp)
+10. Copy mkl library: copy /Y MklImports.* to the folder that will host the x64 binaries.
+11. Copy openmp library:  copy /Y ..\..\..\redist\intel64_win\compiler\libiomp5md* to the folder for x86 binaries.
 
 ##Linux
+NOTE: Do not copy the libiomp5 file for Linux builds as this relies on OpenMP to be installed on the system.
 1. untar the linux sdk (tar -zxvf name_of_downloaded_file)
 2. Run installation script and follow the instuctions in the dialog screens that are presented ./install.sh
-3. Go to /opt/mkl/tools/builder.
+3. Go to /opt/intel/mkl/tools/builder.
 4. Modify makefile add -Wl,-rpath,'$$ORIGIN' \ -Wl,-z,origin \  after -Wl,--end-group \
 5. Modify user_example_list file in directory to contain all the required functions, that are present in the [mlnetmkl.list](mlnetmkl.list) file
 6. Run make intel64 name=libMklImports (add threading=sequential if you are building without openmp)
-7. Copy libMklImports.so the folder containing the Linux binaries.
 
 ##OSX
+NOTE: Do not copy the libiomp5 file for OSX builds as this relies on OpenMP to be installed on the system.
 1. extract and install the dmg (double-click and drag it in the Applications folder)
 2. Go to /opt/mkl/tools/builder.
 3. Modify user_example_list file in directory to contain all the required functions, that are present in the [mlnetmkl.list](mlnetmkl.list) file
-4. Run make intel64 name=libMklImports (add threading=sequential if you are building without openmp)
+4. Run make libintel64 name=libMklImports (add threading=sequential if you are building without openmp)
 5. Copy libMklImports.dylib from the builder directory to the folder containign the OSX binaries.
 6. Fix the id and the rpath running the following commands:
    sudo install_name_tool -id "@loader_path/libMklImports.dylib" libMklImports.dylib 
-   sudo install_name_tool -id "@rpath/libMklImports.dylib" libMklImports.dylib
+   sudo install_name_tool -id "@rpath/libMklImports.dylib" libMklImports.dylib

docs/building/MlNetMklDeps/version.md

@@ -7,4 +7,10 @@ mac: mkl 2018 update 1
 ##Exact versions, including minors
 mac: 2018.1.126
 linux: 2018.3.222
-windows: 2018.3.210
+windows: 2018.3.210
+
+#Intel MKl SDK versions used to build the MlNetMklDeps v0.0.0.9
+mkl 2019 Update 2
+mac:2019.2.187
+linux:2019.2.187
+windows:2019.2.187

docs/code/MlNetCookBook.md

@@ -944,9 +944,9 @@ public static IDataView PrepareData(MLContext mlContext, IDataView data)
 {
     // Define the operation code.
     Action<InputRow, OutputRow> mapping = (input, output) => output.Label = input.Income > 50000;
-    // Make a custom transformer and transform the data.
-    var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
-    return transformer.Transform(data);
+    // Make a custom estimator and transform the data.
+    var estimator = mlContext.Transforms.CustomMapping(mapping, null);
+    return estimator.Fit(data).Transform(data);
 }
 ```
 

docs/release-notes/0.11/release-0.11.md

@@ -0,0 +1,40 @@
+# ML.NET 0.11 Release Notes
+
+[ML.NET](https://aka.ms/mlnet) 0.11 will be the last preview release before we reach `Release Candidate` for v1. We continue to push for creating a coherent and clean API surface for [ML.NET](https://aka.ms/mlnet) users. This release includes several bug fixes as well as extensive work on reducing the public API surface. The work on the API is tracked via [this project](https://github.com/dotnet/machinelearning/projects/13). In the upcoming 0.12 (RC1) releases before we reach 1.0, we will continue on refining the API and improving documentation.
+
+### Installation
+
+ML.NET supports Windows, MacOS, and Linux. See [supported OS versions of .NET Core 2.0](https://github.com/dotnet/core/blob/master/release-notes/2.0/2.0-supported-os.md) for more details.
+
+You can install ML.NET NuGet from the CLI using:
+```
+dotnet add package Microsoft.ML
+```
+
+From package manager:
+```
+Install-Package Microsoft.ML
+```
+
+### Release Notes
+
+Below are a few of the highlights from this release. There are many other improvements in the API.
+
+* Creation of components through MLContext: advanced options and other feedback. ([#1798](https://github.coalsom/dotnet/machinelearning/issues/1798))
+* Several issues closed on internalizing public surface. ([19 issues](https://github.com/dotnet/machinelearning/issues?q=is%3Aissue+lockdown+is%3Aclosed))
+* Stop using MEF as part of the public API. ([#2422](https://github.com/dotnet/machinelearning/issues/2422))
+* Several `NameSpace` changes. ([#2326](https://github.com/dotnet/machinelearning/issues/2326))
+* `ONNX` is now `ONNXConverter`. ([#2625](https://github.com/dotnet/machinelearning/pull/2625))
+* `ONNXTransform` is now `ONNXTransformer`. ([#2544](https://github.com/dotnet/machinelearning/pull/2544))
+* `FastTree` has it's own package now. ([#2752](https://github.com/dotnet/machinelearning/issues/2752))
+* `Ensemble` has been moved out of `Microsoft.ML` package. ([#2717](https://github.com/dotnet/machinelearning/issues/2717))
+* Add support for string types in TensorFlowTransformer. ([#2545](https://github.com/dotnet/machinelearning/issues/2545))
+* Make FastTree/LightGBM learned model suitable for public consumption. ([#1960](https://github.com/dotnet/machinelearning/issues/1960))
+
+
+### Acknowledgements
+
+Shoutout to [PaulTFreedman](https://github.com/PaulTFreedman),
+[kant2002](https://github.com/kant2002),
+[jwood803](https://github.com/jwood803), [mareklinka](https://github.com/mareklinka), [elbruno](https://github.com/elbruno) and the [ML.NET](https://aka.ms/mlnet) team for their
+contributions as part of this release!

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

@@ -30,22 +30,12 @@ public static void Example()
             // We will train a FastTreeRegression model with 1 tree on these two columns to predict Age.
             string outputColumnName = "Features";
             var pipeline = ml.Transforms.Concatenate(outputColumnName, new[] { "Parity", "Induced" })
-                .Append(ml.Regression.Trainers.FastTree(labelColumnName: "Age", featureColumnName: outputColumnName, numTrees: 1, numLeaves: 2, minDatapointsInLeaves: 1));
+                .Append(ml.Regression.Trainers.FastTree(labelColumnName: "Age", featureColumnName: outputColumnName, numberOfTrees: 1, numberOfLeaves: 2, minimumExampleCountPerLeaf: 1));
 
             var model = pipeline.Fit(trainData);
 
             // Get the trained model parameters.
             var modelParams = model.LastTransformer.Model;
-
-            // Let's see where an example with Parity = 1 and Induced = 1 would end up in the single trained tree.
-            var testRow = new VBuffer<float>(2, new[] { 1.0f, 1.0f });
-            // Use the path object to pass to GetLeaf, which will populate path with the IDs of th nodes from root to leaf.
-            List<int> path = default;
-            // Get the ID of the leaf this example ends up in tree 0.
-            var leafID = modelParams.GetLeaf(0, in testRow, ref path);
-            // Get the leaf value for this leaf ID in tree 0.
-            var leafValue = modelParams.GetLeafValue(0, leafID);
-            Console.WriteLine("The leaf value in tree 0 is: " + leafValue);
         }
     }
 }

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

@@ -55,7 +55,7 @@ public static void Example()
             // specify the parameter `numBins', which controls the number of bins used in the approximation of the mutual information
             // between features and label.
             var mutualInfoEst = ml.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
-                outputColumnName: "FeaturesMISelect", inputColumnName: "FeaturesCountSelect", labelColumn: "Label", slotsInOutput: 5);
+                outputColumnName: "FeaturesMISelect", inputColumnName: "FeaturesCountSelect", labelColumnName: "Label", slotsInOutput: 5);
 
             // Now, we can put the previous two transformations together in a pipeline.
             var pipeline = countSelectEst.Append(mutualInfoEst);

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

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

docs/samples/Microsoft.ML.Samples/Dynamic/PermutationFeatureImportance/PFIHelper.cs

@@ -19,7 +19,7 @@ public static IDataView GetHousingRegressionIDataView(MLContext mlContext, out s
             if (binaryPrediction)
             {
                 labelColumn = nameof(BinaryOutputRow.AboveAverage);
-                data = mlContext.Transforms.CustomMappingTransformer(GreaterThanAverage, null).Transform(data);
+                data = mlContext.Transforms.CustomMapping(GreaterThanAverage, null).Fit(data).Transform(data);
                 data = mlContext.Transforms.DropColumns("MedianHomeValue").Fit(data).Transform(data);
             }
 

docs/samples/Microsoft.ML.Samples/Dynamic/PermutationFeatureImportance/PfiBinaryClassificationExample.cs

@@ -37,10 +37,10 @@ public static void Example()
             var permutationMetrics = mlContext.BinaryClassification.PermutationFeatureImportance(
                 linearPredictor, transformedData, label: labelName, features: "Features", permutationCount: 3);
 
-            // Now let's look at which features are most important to the model overall
-            // Get the feature indices sorted by their impact on AUC
-            var sortedIndices = permutationMetrics.Select((metrics, index) => new { index, metrics.Auc })
-                .OrderByDescending(feature => Math.Abs(feature.Auc.Mean))
+            // Now let's look at which features are most important to the model overall.
+            // Get the feature indices sorted by their impact on AreaUnderRocCurve.
+            var sortedIndices = permutationMetrics.Select((metrics, index) => new { index, metrics.AreaUnderRocCurve })
+                .OrderByDescending(feature => Math.Abs(feature.AreaUnderRocCurve.Mean))
                 .Select(feature => feature.index);
 
             // Print out the permutation results, with the model weights, in order of their impact:
@@ -66,7 +66,7 @@ public static void Example()
             // Third, some features show an *increase* in AUC. This means that the model actually improved 
             // when these features were shuffled. This is a sign to investigate these features further.
             Console.WriteLine("Feature\tModel Weight\tChange in AUC\t95% Confidence in the Mean Change in AUC");
-            var auc = permutationMetrics.Select(x => x.Auc).ToArray(); // Fetch AUC as an array
+            var auc = permutationMetrics.Select(x => x.AreaUnderRocCurve).ToArray(); // Fetch AUC as an array
             foreach (int i in sortedIndices)
             {
                 Console.WriteLine($"{featureNames[i]}\t{weights[i]:0.00}\t{auc[i].Mean:G4}\t{1.96 * auc[i].StandardError:G4}");