Cherrypick to update release for V0.3

Directory.Build.targets

@@ -5,5 +5,33 @@
            Text="The tools directory [$(ToolsDir)] does not exist. Please run build in the root of the repo to ensure the tools are installed before attempting to build an individual project." />
   </Target>
 
+  <Target Name="CopyNativeAssemblies"
+          BeforeTargets="PrepareForRun">
+
+    <PropertyGroup>
+      <LibPrefix Condition="'$(OS)' != 'Windows_NT'">lib</LibPrefix>
+      <LibExtension Condition="'$(OS)' == 'Windows_NT'">.dll</LibExtension>
+      <LibExtension Condition="'$(OS)' != 'Windows_NT'">.so</LibExtension>
+      <LibExtension Condition="$([MSBuild]::IsOSPlatform('osx'))">.dylib</LibExtension>
+    </PropertyGroup>
+
+    <ItemGroup>
+      <NativeAssemblyReference>
+        <FullAssemblyPath>$(NativeOutputPath)$(LibPrefix)%(NativeAssemblyReference.Identity)$(LibExtension)</FullAssemblyPath>
+      </NativeAssemblyReference>
+    </ItemGroup>
+
+    <Copy SourceFiles = "@(NativeAssemblyReference->'%(FullAssemblyPath)')"
+          DestinationFolder="$(OutputPath)"
+          OverwriteReadOnlyFiles="$(OverwriteReadOnlyFiles)"
+          Retries="$(CopyRetryCount)"
+          RetryDelayMilliseconds="$(CopyRetryDelayMilliseconds)"
+          UseHardlinksIfPossible="$(CreateHardLinksForPublishFilesIfPossible)"
+          UseSymboliclinksIfPossible="$(CreateSymbolicLinksForPublishFilesIfPossible)">
+      <Output TaskParameter="DestinationFiles" ItemName="FileWrites"/>
+    </Copy>
+
+  </Target>
+
   <Import Project="$(ToolsDir)/versioning.targets" Condition="Exists('$(ToolsDir)/versioning.targets')" />
 </Project>

docs/release-notes/0.3/release-0.3.md

@@ -0,0 +1,114 @@
+# ML.NET 0.3 Release Notes
+
+Today we are releasing ML.NET 0.3. This release focuses on adding components
+to ML.NET from the internal codebase (such as Factorization Machines,
+LightGBM, Ensembles, and LightLDA), enabling export to the ONNX model format,
+and bug fixes.
+
+### 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 some of the highlights from this release.
+
+* Added Field-Aware Factorization Machines (FFM) as a learner for binary
+  classification (#383)
+
+    * FFM is useful for various large sparse datasets, especially in areas
+      such as recommendations and click prediction. It has been used to win
+      various click prediction competitions such as the [Criteo Display
+      Advertising Challenge on
+      Kaggle](https://www.kaggle.com/c/criteo-display-ad-challenge). You can
+      learn more about the winning solution
+      [here](https://www.csie.ntu.edu.tw/~r01922136/kaggle-2014-criteo.pdf).
+    * FFM is a streaming learner so it does not require the entire dataset to
+      fit in memory.
+    * You can learn more about FFM
+      [here](http://www.csie.ntu.edu.tw/~cjlin/papers/ffm.pdf) and some of the
+      speedup approaches that are used in ML.NET
+      [here](https://github.com/wschin/fast-ffm/blob/master/fast-ffm.pdf).
+
+* Added [LightGBM](https://github.com/Microsoft/LightGBM) as a learner for
+  binary classification, multiclass classification, and regression (#392)
+
+    * LightGBM is a tree based gradient boosting machine. It is under the
+      umbrella of the [DMTK](http://github.com/microsoft/dmtk) project at
+      Microsoft.
+    * The LightGBM repository shows various [comparison
+      experiments](https://github.com/Microsoft/LightGBM/blob/6488f319f243f7ff679a8e388a33e758c5802303/docs/Experiments.rst#comparison-experiment)
+      that show good accuracy and speed, so it is a great learner to try out.
+      It has also been used in winning solutions in various [ML
+      challenges](https://github.com/Microsoft/LightGBM/blob/a6e878e2fc6e7f545921cbe337cc511fbd1f500d/examples/README.md).
+    * This addition wraps LightGBM and exposes it in ML.NET.
+    * Note that LightGBM can also be used for ranking, but the ranking
+      evaluator is not yet exposed in ML.NET.
+
+* Added Ensemble learners for binary classification, multiclass
+  classification, and regression (#379)
+
+    * [Ensemble learners](https://en.wikipedia.org/wiki/Ensemble_learning)
+      enable using multiple learners in one model. As an example, the Ensemble
+      learner could train both `FastTree` and `AveragedPerceptron` and average
+      their predictions to get the final prediction. 
+    * Combining multiple models of similar statistical performance may lead to
+      better performance than each model separately.
+
+* Added LightLDA transform for topic modeling (#377)
+
+    * LightLDA is an implementation of [Latent Dirichlet
+      Allocation](https://en.wikipedia.org/wiki/Latent_Dirichlet_allocation)
+      which infers topical structure from text data. 
+    * The implementation of LightLDA in ML.NET is based on [this
+      paper](https://arxiv.org/abs/1412.1576). There is a distributed
+      implementation of LightLDA
+      [here](https://github.com/Microsoft/lightlda).
+
+* Added One-Versus-All (OVA) learner for multiclass classification (#363)
+
+    * [OVA](https://en.wikipedia.org/wiki/Multiclass_classification#One-vs.-rest)
+      (sometimes known as One-Versus-Rest) is an approach to using binary
+      classifiers in multiclass classification problems. 
+    * While some binary classification learners in ML.NET natively support
+      multiclass classification (e.g. Logistic Regression), there are others
+      that do not (e.g. Averaged Perceptron). OVA enables using the latter
+      group for multiclass classification as well.
+
+* Enabled export of ML.NET models to the [ONNX](https://onnx.ai/) format
+  (#248)
+
+    * ONNX is a common format for representing deep learning models (also
+      supporting certain other types of models) which enables developers to
+      move models between different ML toolkits.
+    * ONNX models can be used in [Windows
+      ML](https://docs.microsoft.com/en-us/windows/uwp/machine-learning/overview)
+      which enables evaluating models on Windows 10 devices and taking
+      advantage of capabilities like hardware acceleration.
+    * Currently, only a subset of ML.NET components can be used in a model
+      that is converted to ONNX. 
+
+Additional issues closed in this milestone can be found
+[here](https://github.com/dotnet/machinelearning/milestone/2?closed=1).
+
+### Acknowledgements
+
+Shoutout to [pkulikov](https://github.com/pkulikov),
+[veikkoeeva](https://github.com/veikkoeeva),
+[ross-p-smith](https://github.com/ross-p-smith),
+[jwood803](https://github.com/jwood803),
+[Nepomuceno](https://github.com/Nepomuceno), and the ML.NET team for their
+contributions as part of this release! 

src/Microsoft.ML.Console/Console.cs

@@ -8,4 +8,4 @@ public static class Console
     {
         public static int Main(string[] args) => Maml.Main(args);
     }
-}
+}

src/Microsoft.ML.Console/Microsoft.ML.Console.csproj

@@ -3,17 +3,34 @@
   <PropertyGroup>
     <AllowUnsafeBlocks>true</AllowUnsafeBlocks>
     <DefineConstants>CORECLR</DefineConstants>
-	<TargetFramework>netcoreapp2.0</TargetFramework>
-	<OutputType>Exe</OutputType>
-	<AssemblyName>MML</AssemblyName> 
-	<StartupObject>Microsoft.ML.Runtime.Tools.Console.Console</StartupObject>
+    <TargetFramework>netcoreapp2.0</TargetFramework>
+    <OutputType>Exe</OutputType>
+    <AssemblyName>MML</AssemblyName> 
+    <StartupObject>Microsoft.ML.Runtime.Tools.Console.Console</StartupObject>
   </PropertyGroup>
 
   <ItemGroup>
     <ProjectReference Include="..\Microsoft.ML.Core\Microsoft.ML.Core.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.CpuMath\Microsoft.ML.CpuMath.csproj" />
     <ProjectReference Include="..\Microsoft.ML.Data\Microsoft.ML.Data.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.Ensemble\Microsoft.ML.Ensemble.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.FastTree\Microsoft.ML.FastTree.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.InternalStreams\Microsoft.ML.InternalStreams.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.KMeansClustering\Microsoft.ML.KMeansClustering.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.LightGBM\Microsoft.ML.LightGBM.csproj" />
     <ProjectReference Include="..\Microsoft.ML.Maml\Microsoft.ML.Maml.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.PCA\Microsoft.ML.PCA.csproj" />
     <ProjectReference Include="..\Microsoft.ML.PipelineInference\Microsoft.ML.PipelineInference.csproj" />
-  </ItemGroup>
+    <ProjectReference Include="..\Microsoft.ML.ResultProcessor\Microsoft.ML.ResultProcessor.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.StandardLearners\Microsoft.ML.StandardLearners.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.Sweeper\Microsoft.ML.Sweeper.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.Transforms\Microsoft.ML.Transforms.csproj" />
+    <ProjectReference Include="..\Microsoft.ML.UniversalModelFormat\Microsoft.ML.UniversalModelFormat.csproj" />
 
+    <NativeAssemblyReference Include="FastTreeNative" />
+    <NativeAssemblyReference Include="CpuMathNative" />
+    <NativeAssemblyReference Include="FactorizationMachineNative" />
+    <NativeAssemblyReference Include="LdaNative" />
+  </ItemGroup>
+
 </Project>

src/Microsoft.ML.Core/EntryPoints/ModuleArgs.cs

@@ -527,6 +527,11 @@ public sealed class EntryPointAttribute : Attribute
             /// Short name of the Entry Point
             /// </summary>
             public string ShortName { get; set; }
+
+            /// <summary>
+            /// Remarks on the Entry Point, for more extensive XML documentation on the C#API
+            /// </summary>
+            public string Remarks { get; set; }
         }
 
         /// <summary>

src/Microsoft.ML.Core/EntryPoints/ModuleCatalog.cs

@@ -44,6 +44,7 @@ public sealed class EntryPointInfo
             public readonly string Description;
             public readonly string ShortName;
             public readonly string FriendlyName;
+            public readonly string Remarks;
             public readonly MethodInfo Method;
             public readonly Type InputType;
             public readonly Type OutputType;
@@ -63,6 +64,7 @@ internal EntryPointInfo(IExceptionContext ectx, MethodInfo method,
                 Method = method;
                 ShortName = attribute.ShortName;
                 FriendlyName = attribute.UserName;
+                Remarks = attribute.Remarks;
                 ObsoleteAttribute = obsoleteAttribute;
 
                 // There are supposed to be 2 parameters, env and input for non-macro nodes.

src/Microsoft.ML.Data/Evaluators/EvaluatorUtils.cs

@@ -653,10 +653,10 @@ public static void ReconcileKeyValuesWithNoNames(IHostEnvironment env, IDataView
                 ValueMapper<uint, uint> mapper =
                     (ref uint src, ref uint dst) =>
                     {
-                        if (src == 0 || src > keyCount)
+                        if (src > keyCount)
                             dst = 0;
                         else
-                            dst = src + 1;
+                            dst = src;
                     };
                 views[i] = LambdaColumnMapper.Create(env, "ReconcileKeyValues", views[i], columnName, columnName,
                     views[i].Schema.GetColumnType(index), keyType, mapper);
@@ -866,7 +866,7 @@ private static IDataView AppendPerInstanceDataViews(IHostEnvironment env, string
                     }
                     else if (dvNumber == 0 && dv.Schema.HasKeyNames(i, type.KeyCount))
                         firstDvKeyWithNamesColumns.Add(name);
-                    else if (type.KeyCount > 0 && name != labelColName)
+                    else if (type.KeyCount > 0 && name != labelColName && !dv.Schema.HasKeyNames(i, type.KeyCount))
                     {
                         // For any other key column (such as GroupId) we do not reconcile the key values, we only convert to U4.
                         if (!firstDvKeyNoNamesColumns.ContainsKey(name))
@@ -901,7 +901,7 @@ private static IDataView AppendPerInstanceDataViews(IHostEnvironment env, string
             Func<IDataView, int, IDataView> keyToValue =
                 (idv, i) =>
                 {
-                    foreach (var keyCol in firstDvVectorKeyColumns.Prepend(labelColName))
+                    foreach (var keyCol in firstDvVectorKeyColumns.Concat(firstDvKeyWithNamesColumns).Prepend(labelColName))
                     {
                         if (keyCol == labelColName && labelColKeyValuesType == null)
                             continue;

src/Microsoft.ML.FastTree/FastTree.cs

@@ -82,6 +82,31 @@ public abstract class FastTreeTrainerBase<TArgs, TPredictor> :
 
         protected string InnerArgs => CmdParser.GetSettings(Host, Args, new TArgs());
 
+        internal const string Remarks = @"<remarks>
+<para>FastTrees is an efficient implementation of the <a href='https://arxiv.org/abs/1505.01866'>MART</a> gradient boosting algorithm. 
+Gradient boosting is a machine learning technique for regression problems. 
+It builds each regression tree in a step-wise fashion, using a predefined loss function to measure the error for each step and corrects for it in the next. 
+So this prediction model is actually an ensemble of weaker prediction models. In regression problems, boosting builds a series of of such trees in a step-wise fashion and then selects the optimal tree using an arbitrary differentiable loss function.
+</para>
+<para>
+MART learns an ensemble of regression trees, which is a decision tree with scalar values in its leaves. 
+A decision (or regression) tree is a binary tree-like flow chart, where at each interior node one decides which of the two child nodes to continue to based on one of the feature values from the input. 
+At each leaf node, a value is returned. In the interior nodes, the decision is based on the test 'x <= v' where x is the value of the feature in the input sample and v is one of the possible values of this feature. 
+The functions that can be produced by a regression tree are all the piece-wise constant functions.
+</para>
+<para>
+The ensemble of trees is produced by computing, in each step, a regression tree that approximates the gradient of the loss function, and adding it to the previous tree with coefficients that minimize the loss of the new tree.
+The output of the ensemble produced by MART on a given instance is the sum of the tree outputs.
+</para>
+<list type='bullet'>
+<item>In case of a binary classification problem, the output is converted to a probability by using some form of calibration.</item>
+<item>In case of a regression problem, the output is the predicted value of the function.</item>
+<item>In case of a ranking problem, the instances are ordered by the output value of the ensemble.</item>
+</list>
+<a href='https://en.wikipedia.org/wiki/Gradient_boosting#Gradient_tree_boosting'>Wikipedia: Gradient boosting (Gradient tree boosting)</a>.
+<a href='http://projecteuclid.org/DPubS?service=UI&version=1.0&verb=Display&handle=euclid.aos/1013203451'>Greedy function approximation: A gradient boosting machine.</a>.
+</remarks>";
+
         public override bool NeedNormalization => false;
 
         public override bool WantCaching => false;

src/Microsoft.ML.FastTree/FastTreeClassification.cs

@@ -338,7 +338,11 @@ public void AdjustTreeOutputs(IChannel ch, RegressionTree tree,
 
     public static partial class FastTree
     {
-        [TlcModule.EntryPoint(Name = "Trainers.FastTreeBinaryClassifier", Desc = FastTreeBinaryClassificationTrainer.Summary, UserName = FastTreeBinaryClassificationTrainer.UserNameValue, ShortName = FastTreeBinaryClassificationTrainer.ShortName)]
+        [TlcModule.EntryPoint(Name = "Trainers.FastTreeBinaryClassifier", 
+            Desc = FastTreeBinaryClassificationTrainer.Summary, 
+            Remarks = FastTreeBinaryClassificationTrainer.Remarks, 
+            UserName = FastTreeBinaryClassificationTrainer.UserNameValue, 
+            ShortName = FastTreeBinaryClassificationTrainer.ShortName)]
         public static CommonOutputs.BinaryClassificationOutput TrainBinary(IHostEnvironment env, FastTreeBinaryClassificationTrainer.Arguments input)
         {
             Contracts.CheckValue(env, nameof(env));

src/Microsoft.ML.FastTree/FastTreeRanking.cs

@@ -1096,7 +1096,11 @@ public static FastTreeRankingPredictor Create(IHostEnvironment env, ModelLoadCon
 
     public static partial class FastTree
     {
-        [TlcModule.EntryPoint(Name = "Trainers.FastTreeRanker", Desc = FastTreeRankingTrainer.Summary, UserName = FastTreeRankingTrainer.UserNameValue, ShortName = FastTreeRankingTrainer.ShortName)]
+        [TlcModule.EntryPoint(Name = "Trainers.FastTreeRanker", 
+            Desc = FastTreeRankingTrainer.Summary, 
+            Remarks = FastTreeRankingTrainer.Remarks,
+            UserName = FastTreeRankingTrainer.UserNameValue, 
+            ShortName = FastTreeRankingTrainer.ShortName)]
         public static CommonOutputs.RankingOutput TrainRanking(IHostEnvironment env, FastTreeRankingTrainer.Arguments input)
         {
             Contracts.CheckValue(env, nameof(env));

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -448,7 +448,11 @@ public static FastTreeRegressionPredictor Create(IHostEnvironment env, ModelLoad
 
     public static partial class FastTree
     {
-        [TlcModule.EntryPoint(Name = "Trainers.FastTreeRegressor", Desc = FastTreeRegressionTrainer.Summary, UserName = FastTreeRegressionTrainer.UserNameValue, ShortName = FastTreeRegressionTrainer.ShortName)]
+        [TlcModule.EntryPoint(Name = "Trainers.FastTreeRegressor",
+            Desc = FastTreeRegressionTrainer.Summary, 
+            Remarks = FastTreeRegressionTrainer.Remarks, 
+            UserName = FastTreeRegressionTrainer.UserNameValue, 
+            ShortName = FastTreeRegressionTrainer.ShortName)]
         public static CommonOutputs.RegressionOutput TrainRegression(IHostEnvironment env, FastTreeRegressionTrainer.Arguments input)
         {
             Contracts.CheckValue(env, nameof(env));

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -36,8 +36,11 @@ public sealed partial class FastTreeTweedieTrainer : BoostingFastTreeTrainerBase
     {
         public const string LoadNameValue = "FastTreeTweedieRegression";
         public const string UserNameValue = "FastTree (Boosted Trees) Tweedie Regression";
-        public const string Summary = "Trains gradient boosted decision trees to fit target values using a Tweedie loss function. This learner " +
-                                        "is a generalization of Poisson, compound Poisson, and gamma regression.";
+        public const string Summary = "Trains gradient boosted decision trees to fit target values using a Tweedie loss function. This learner is a generalization of Poisson, compound Poisson, and gamma regression.";
+        new public const string Remarks = @"<remarks>
+<a href='https://en.wikipedia.org/wiki/Gradient_boosting#Gradient_tree_boosting'>Wikipedia: Gradient boosting (Gradient tree boosting)</a>
+<a href='http://projecteuclid.org/DPubS?service=UI&version=1.0&verb=Display&handle=euclid.aos/1013203451'>Greedy function approximation: A gradient boosting machine</a>
+</remarks>";
 
         public const string ShortName = "fttweedie";
 
@@ -460,7 +463,10 @@ protected override void Map(ref VBuffer<float> src, ref float dst)
 
     public static partial class FastTree
     {
-        [TlcModule.EntryPoint(Name = "Trainers.FastTreeTweedieRegressor", Desc = FastTreeTweedieTrainer.Summary, UserName = FastTreeTweedieTrainer.UserNameValue, ShortName = FastTreeTweedieTrainer.ShortName)]
+        [TlcModule.EntryPoint(Name = "Trainers.FastTreeTweedieRegressor", 
+            Desc = FastTreeTweedieTrainer.Summary, 
+            UserName = FastTreeTweedieTrainer.UserNameValue, 
+            ShortName = FastTreeTweedieTrainer.ShortName)]
         public static CommonOutputs.RegressionOutput TrainTweedieRegression(IHostEnvironment env, FastTreeTweedieTrainer.Arguments input)
         {
             Contracts.CheckValue(env, nameof(env));