code migration from machinelearning-automl to machinelearning repo feature branch

Microsoft.ML.AutoML.sln

@@ -0,0 +1,91 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio 15
+VisualStudioVersion = 15.0.28010.2050
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.Auto", "src\Microsoft.ML.Auto\Microsoft.ML.Auto.csproj", "{B3727729-3DF8-47E0-8710-9B41DAF55817}"
+EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.AutoML.Tests", "test\Microsoft.ML.AutoML.Tests\Microsoft.ML.AutoML.Tests.csproj", "{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}"
+EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "mlnet", "src\mlnet\mlnet.csproj", "{ED714FA5-6F89-401B-9E7F-CADF1373C553}"
+EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "mlnet.Tests", "test\mlnet.Tests\mlnet.Tests.csproj", "{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Debug-Intrinsics|Any CPU = Debug-Intrinsics|Any CPU
+		Debug-netfx|Any CPU = Debug-netfx|Any CPU
+		Release|Any CPU = Release|Any CPU
+		Release-Intrinsics|Any CPU = Release-Intrinsics|Any CPU
+		Release-netfx|Any CPU = Release-netfx|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Debug-Intrinsics|Any CPU.ActiveCfg = Debug|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Debug-Intrinsics|Any CPU.Build.0 = Debug|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Debug-netfx|Any CPU.ActiveCfg = Debug-netfx|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Debug-netfx|Any CPU.Build.0 = Debug-netfx|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Release|Any CPU.Build.0 = Release|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Release-Intrinsics|Any CPU.ActiveCfg = Release|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Release-Intrinsics|Any CPU.Build.0 = Release|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Release-netfx|Any CPU.ActiveCfg = Release-netfx|Any CPU
+		{B3727729-3DF8-47E0-8710-9B41DAF55817}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Debug-Intrinsics|Any CPU.ActiveCfg = Debug|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Debug-Intrinsics|Any CPU.Build.0 = Debug|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Debug-netfx|Any CPU.ActiveCfg = Debug-netfx|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Debug-netfx|Any CPU.Build.0 = Debug-netfx|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Release|Any CPU.Build.0 = Release|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Release-Intrinsics|Any CPU.ActiveCfg = Release|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Release-Intrinsics|Any CPU.Build.0 = Release|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Release-netfx|Any CPU.ActiveCfg = Release-netfx|Any CPU
+		{64A7294E-A2C7-4499-8F0B-4BB074047C6B}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Debug-Intrinsics|Any CPU.ActiveCfg = Debug-Intrinsics|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Debug-Intrinsics|Any CPU.Build.0 = Debug-Intrinsics|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Debug-netfx|Any CPU.ActiveCfg = Debug-netfx|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Debug-netfx|Any CPU.Build.0 = Debug-netfx|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Release|Any CPU.Build.0 = Release|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Release-Intrinsics|Any CPU.ActiveCfg = Release-Intrinsics|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Release-Intrinsics|Any CPU.Build.0 = Release-Intrinsics|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Release-netfx|Any CPU.ActiveCfg = Release-netfx|Any CPU
+		{55ACB7E2-053D-43BB-88E8-0E102FBD62F0}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Debug-Intrinsics|Any CPU.ActiveCfg = Debug-Intrinsics|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Debug-Intrinsics|Any CPU.Build.0 = Debug-Intrinsics|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Debug-netfx|Any CPU.ActiveCfg = Debug-netfx|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Debug-netfx|Any CPU.Build.0 = Debug-netfx|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Release|Any CPU.Build.0 = Release|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Release-Intrinsics|Any CPU.ActiveCfg = Release-Intrinsics|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Release-Intrinsics|Any CPU.Build.0 = Release-Intrinsics|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Release-netfx|Any CPU.ActiveCfg = Release-netfx|Any CPU
+		{ED714FA5-6F89-401B-9E7F-CADF1373C553}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Debug-Intrinsics|Any CPU.ActiveCfg = Debug-Intrinsics|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Debug-Intrinsics|Any CPU.Build.0 = Debug-Intrinsics|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Debug-netfx|Any CPU.ActiveCfg = Debug-netfx|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Debug-netfx|Any CPU.Build.0 = Debug-netfx|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Release|Any CPU.Build.0 = Release|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Release-Intrinsics|Any CPU.ActiveCfg = Release-Intrinsics|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Release-Intrinsics|Any CPU.Build.0 = Release-Intrinsics|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Release-netfx|Any CPU.ActiveCfg = Release-netfx|Any CPU
+		{AAC3E4E6-C146-44BB-8873-A1E61D563F2A}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {8C1BC26C-B87E-47CD-928E-00EFE4353B40}
+	EndGlobalSection
+EndGlobal

build.proj

@@ -22,6 +22,7 @@
 
   <ItemGroup>
     <Project Include="Microsoft.ML.sln" />
+    <Project Include="Microsoft.ML.AutoML.sln" />
   </ItemGroup>
 
   <Import Project="dir.traversal.targets" />

src/Microsoft.ML.Auto/API/AutoInferenceCatalog.cs

@@ -0,0 +1,79 @@
+// 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.
+
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Auto
+{
+    public sealed class AutoMLCatalog
+    {
+        private readonly MLContext _context;
+
+        internal AutoMLCatalog(MLContext context)
+        {
+            _context = context;
+        }
+
+        public RegressionExperiment CreateRegressionExperiment(uint maxExperimentTimeInSeconds)
+        {
+            return new RegressionExperiment(_context, new RegressionExperimentSettings()
+            {
+                MaxExperimentTimeInSeconds = maxExperimentTimeInSeconds
+            });
+        }
+
+        public RegressionExperiment CreateRegressionExperiment(RegressionExperimentSettings experimentSettings)
+        {
+            return new RegressionExperiment(_context, experimentSettings);
+        }
+
+        public BinaryClassificationExperiment CreateBinaryClassificationExperiment(uint maxExperimentTimeInSeconds)
+        {
+            return new BinaryClassificationExperiment(_context, new BinaryExperimentSettings()
+            {
+                MaxExperimentTimeInSeconds = maxExperimentTimeInSeconds
+            });
+        }
+
+        public BinaryClassificationExperiment CreateBinaryClassificationExperiment(BinaryExperimentSettings experimentSettings)
+        {
+            return new BinaryClassificationExperiment(_context, experimentSettings);
+        }
+
+        public MulticlassClassificationExperiment CreateMulticlassClassificationExperiment(uint maxExperimentTimeInSeconds)
+        {
+            return new MulticlassClassificationExperiment(_context, new MulticlassExperimentSettings()
+            {
+                MaxExperimentTimeInSeconds = maxExperimentTimeInSeconds
+            });
+        }
+
+        public MulticlassClassificationExperiment CreateMulticlassClassificationExperiment(MulticlassExperimentSettings experimentSettings)
+        {
+            return new MulticlassClassificationExperiment(_context, experimentSettings);
+        }
+
+        public ColumnInferenceResults InferColumns(string path, string labelColumn = DefaultColumnNames.Label, char? separatorChar = null, bool? allowQuotedStrings = null, 
+            bool? supportSparse = null, bool trimWhitespace = false, bool groupColumns = true)
+        {
+            UserInputValidationUtil.ValidateInferColumnsArgs(path, labelColumn);
+            return ColumnInferenceApi.InferColumns(_context, path, labelColumn, separatorChar, allowQuotedStrings, supportSparse, trimWhitespace, groupColumns);
+        }
+
+        public ColumnInferenceResults InferColumns(string path, ColumnInformation columnInformation, char? separatorChar = null, bool? allowQuotedStrings = null,
+            bool? supportSparse = null, bool trimWhitespace = false, bool groupColumns = true)
+        {
+            columnInformation = columnInformation ?? new ColumnInformation();
+            UserInputValidationUtil.ValidateInferColumnsArgs(path, columnInformation);
+            return ColumnInferenceApi.InferColumns(_context, path, columnInformation, separatorChar, allowQuotedStrings, supportSparse, trimWhitespace, groupColumns);
+        }
+
+        public ColumnInferenceResults InferColumns(string path, uint labelColumnIndex, bool hasHeader = false, char? separatorChar = null, 
+            bool? allowQuotedStrings = null, bool? supportSparse = null, bool trimWhitespace = false, bool groupColumns = true)
+        {
+            UserInputValidationUtil.ValidateInferColumnsArgs(path);
+            return ColumnInferenceApi.InferColumns(_context, path, labelColumnIndex, hasHeader, separatorChar, allowQuotedStrings, supportSparse, trimWhitespace, groupColumns);
+        }
+    }
+}

src/Microsoft.ML.Auto/API/BinaryClassificationExperiment.cs

@@ -0,0 +1,73 @@
+// 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.
+
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Auto
+{
+    public sealed class BinaryExperimentSettings : ExperimentSettings
+    {
+        public BinaryClassificationMetric OptimizingMetric { get; set; } = BinaryClassificationMetric.Accuracy;
+        public ICollection<BinaryClassificationTrainer> Trainers { get; } =
+                    Enum.GetValues(typeof(BinaryClassificationTrainer)).OfType<BinaryClassificationTrainer>().ToList();
+    }
+
+    public enum BinaryClassificationMetric
+    {
+        Accuracy,
+        AreaUnderRocCurve,
+        AreaUnderPrecisionRecallCurve,
+        F1Score,
+        PositivePrecision,
+        PositiveRecall,
+        NegativePrecision,
+        NegativeRecall,
+    }
+
+    public enum BinaryClassificationTrainer
+    {
+        AveragedPerceptron,
+        FastForest,
+        FastTree,
+        LightGbm,
+        LinearSupportVectorMachines,
+        LbfgsLogisticRegression,
+        SdcaLogisticRegression,
+        SgdCalibrated,
+        SymbolicSgdLogisticRegression,
+    }
+
+    public sealed class BinaryClassificationExperiment : ExperimentBase<BinaryClassificationMetrics>
+    {
+        internal BinaryClassificationExperiment(MLContext context, BinaryExperimentSettings settings)
+            : base(context,
+                  new BinaryMetricsAgent(context, settings.OptimizingMetric),
+                  new OptimizingMetricInfo(settings.OptimizingMetric),
+                  settings,
+                  TaskKind.BinaryClassification,
+                  TrainerExtensionUtil.GetTrainerNames(settings.Trainers))
+        {
+        }
+    }
+
+    public static class BinaryExperimentResultExtensions
+    {
+        public static RunDetail<BinaryClassificationMetrics> Best(this IEnumerable<RunDetail<BinaryClassificationMetrics>> results, BinaryClassificationMetric metric = BinaryClassificationMetric.Accuracy)
+        {
+            var metricsAgent = new BinaryMetricsAgent(null, metric);
+            var isMetricMaximizing = new OptimizingMetricInfo(metric).IsMaximizing;
+            return BestResultUtil.GetBestRun(results, metricsAgent, isMetricMaximizing);
+        }
+
+        public static CrossValidationRunDetail<BinaryClassificationMetrics> Best(this IEnumerable<CrossValidationRunDetail<BinaryClassificationMetrics>> results, BinaryClassificationMetric metric = BinaryClassificationMetric.Accuracy)
+        {
+            var metricsAgent = new BinaryMetricsAgent(null, metric);
+            var isMetricMaximizing = new OptimizingMetricInfo(metric).IsMaximizing;
+            return BestResultUtil.GetBestRun(results, metricsAgent, isMetricMaximizing);
+        }
+    }
+}

src/Microsoft.ML.Auto/API/ColumnInference.cs

@@ -0,0 +1,27 @@
+// 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.
+
+using System.Collections.Generic;
+using System.Collections.ObjectModel;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Auto
+{
+    public sealed class ColumnInferenceResults
+    {
+        public TextLoader.Options TextLoaderOptions { get; internal set; } = new TextLoader.Options();
+        public ColumnInformation ColumnInformation { get; internal set; } = new ColumnInformation();
+    }
+
+    public sealed class ColumnInformation
+    {
+        public string LabelColumnName { get; set; } = DefaultColumnNames.Label;
+        public string ExampleWeightColumnName { get; set; }
+        public string SamplingKeyColumnName { get; set; }
+        public ICollection<string> CategoricalColumnNames { get; } = new Collection<string>();
+        public ICollection<string> NumericColumnNames { get; } = new Collection<string>();
+        public ICollection<string> TextColumnNames { get; } = new Collection<string>();
+        public ICollection<string> IgnoredColumnNames { get; } = new Collection<string>();
+    }
+}