dotnet · michaelgsharp · Aug 21, 2019
diff --git a/Microsoft.ML.sln b/Microsoft.ML.sln
@@ -273,6 +273,14 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.AutoML.Samples
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.Samples.GPU", "docs\samples\Microsoft.ML.Samples.GPU\Microsoft.ML.Samples.GPU.csproj", "{3C8F910B-7F23-4D25-B521-6D5AC9570ADD}"
 EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.Featurizers", "src\Microsoft.ML.Featurizers\Microsoft.ML.Featurizers.csproj", "{E2DD0721-5B0F-4606-8182-4C7EFB834518}"
+EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Microsoft.ML.Featurizers", "Microsoft.ML.Featurizers", "{1BA5C784-52E8-4A87-8525-26B2452F2882}"
+	ProjectSection(SolutionItems) = preProject
+		pkg\Microsoft.ML.Featurizers\Microsoft.ML.Featurizers.nupkgproj = pkg\Microsoft.ML.Featurizers\Microsoft.ML.Featurizers.nupkgproj
+		pkg\Microsoft.ML.Featurizers\Microsoft.ML.Featurizers.symbols.nupkgproj = pkg\Microsoft.ML.Featurizers\Microsoft.ML.Featurizers.symbols.nupkgproj
+	EndProjectSection
+EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.CodeGenerator", "src\Microsoft.ML.CodeGenerator\Microsoft.ML.CodeGenerator.csproj", "{56CB0850-7341-4D71-9AE4-9EFC472D93DD}"
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Microsoft.ML.CodeGenerator.Tests", "test\Microsoft.ML.CodeGenerator.Tests\Microsoft.ML.CodeGenerator.Tests.csproj", "{46CC5637-3DDF-4100-93FC-44BB87B2DB81}"
@@ -1690,6 +1698,30 @@ Global
 		{46CC5637-3DDF-4100-93FC-44BB87B2DB81}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
 		{46CC5637-3DDF-4100-93FC-44BB87B2DB81}.Release-netfx|x64.ActiveCfg = Release-netfx|Any CPU
 		{46CC5637-3DDF-4100-93FC-44BB87B2DB81}.Release-netfx|x64.Build.0 = Release-netfx|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug|x64.ActiveCfg = Debug|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug|x64.Build.0 = Debug|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug-netcoreapp3_0|Any CPU.ActiveCfg = Debug-netcoreapp3_0|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug-netcoreapp3_0|Any CPU.Build.0 = Debug-netcoreapp3_0|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug-netcoreapp3_0|x64.ActiveCfg = Debug-netcoreapp3_0|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug-netcoreapp3_0|x64.Build.0 = Debug-netcoreapp3_0|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug-netfx|Any CPU.ActiveCfg = Debug-netfx|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug-netfx|Any CPU.Build.0 = Debug-netfx|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug-netfx|x64.ActiveCfg = Debug-netfx|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Debug-netfx|x64.Build.0 = Debug-netfx|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release|Any CPU.Build.0 = Release|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release|x64.ActiveCfg = Release|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release|x64.Build.0 = Release|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release-netcoreapp3_0|Any CPU.ActiveCfg = Release-netcoreapp3_0|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release-netcoreapp3_0|Any CPU.Build.0 = Release-netcoreapp3_0|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release-netcoreapp3_0|x64.ActiveCfg = Release-netcoreapp3_0|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release-netcoreapp3_0|x64.Build.0 = Release-netcoreapp3_0|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release-netfx|Any CPU.ActiveCfg = Release-netfx|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release-netfx|Any CPU.Build.0 = Release-netfx|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release-netfx|x64.ActiveCfg = Release-netfx|Any CPU
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518}.Release-netfx|x64.Build.0 = Release-netfx|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE
@@ -1779,6 +1811,8 @@ Global
 		{56CB0850-7341-4D71-9AE4-9EFC472D93DD} = {09EADF06-BE25-4228-AB53-95AE3E15B530}
 		{46CC5637-3DDF-4100-93FC-44BB87B2DB81} = {AED9C836-31E3-4F3F-8ABC-929555D3F3C4}
 		{3817A875-278C-4140-BF66-3C4A8CA55F0D} = {D3D38B03-B557-484D-8348-8BADEE4DF592}
+		{E2DD0721-5B0F-4606-8182-4C7EFB834518} = {09EADF06-BE25-4228-AB53-95AE3E15B530}
+		{1BA5C784-52E8-4A87-8525-26B2452F2882} = {D3D38B03-B557-484D-8348-8BADEE4DF592}
 	EndGlobalSection
 	GlobalSection(ExtensibilityGlobals) = postSolution
 		SolutionGuid = {41165AF1-35BB-4832-A189-73060F82B01D}

diff --git a/build/BranchInfo.props b/build/BranchInfo.props
@@ -30,12 +30,12 @@
     <MajorVersion>1</MajorVersion>
     <MinorVersion>4</MinorVersion>
     <PatchVersion>0</PatchVersion>
-    <PreReleaseLabel>preview3</PreReleaseLabel>
+    <PreReleaseLabel>preview2</PreReleaseLabel>
   </PropertyGroup>
   <PropertyGroup Condition="'$(IsStableProject)' != 'true'">
     <MajorVersion>0</MajorVersion>
     <MinorVersion>16</MinorVersion>
     <PatchVersion>0</PatchVersion>
-    <PreReleaseLabel>preview3</PreReleaseLabel>
+    <PreReleaseLabel>preview2</PreReleaseLabel>
   </PropertyGroup>
 </Project>
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/CategoryImputer.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/CategoryImputer.cs
@@ -0,0 +1,69 @@
+using System;
+using System.Collections.Generic;
+using Microsoft.ML;
+using Microsoft.ML.Data;
+using Microsoft.ML.Featurizers;
+
+namespace Samples.Dynamic
+{
+    public static class CategoryImputer
+    {
+        public static void Example()
+        {
+            // Create a new ML context, for ML.NET operations. It can be used for
+            // exception tracking and logging, as well as the source of randomness.
+            var mlContext = new MLContext();
+
+            // Create a small dataset as an IEnumerable.
+            var samples = new List<InputData>()
+            {
+                new InputData(){ Feature1 = 1f },
+
+                new InputData(){ Feature1 = float.NaN },
+
+                new InputData(){ Feature1 = 1f },
+
+                new InputData(){ Feature1 = float.NaN },
+
+                new InputData(){ Feature1 = 9f },
+            };
+
+            // Convert training data to IDataView.
+            var dataview = mlContext.Data.LoadFromEnumerable(samples);
+
+            // A pipeline for filling in the missing values in the feature1 column
+            var pipeline = mlContext.Transforms.CatagoryImputerTransformer("Feature1");
+
+            // The transformed data.
+            var transformedData = pipeline.Fit(dataview).Transform(dataview);
+
+            // Now let's take a look at what this did. The NaN values should be filled in with the most frequent value, 1.
+            // We can extract the newly created columns as an IEnumerable of TransformedData.
+            var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
+                transformedData, reuseRowObject: false);
+
+            // And we can write out a few rows
+            Console.WriteLine($"Features column obtained post-transformation.");
+            foreach (var featureRow in featuresColumn)
+                Console.WriteLine(featureRow.Feature1);
+
+            // Expected output:
+            //  Features column obtained post-transformation.
+            //  1
+            //  1
+            //  1
+            //  1
+            //  9
+        }
+
+        private class InputData
+        {
+            public float Feature1;
+        }
+
+        private sealed class TransformedData
+        {
+            public float Feature1 { get; set; }
+        }
+    }
+}
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformer.cs
@@ -0,0 +1,84 @@
+using System;
+using System.Collections.Generic;
+using Microsoft.ML;
+using Microsoft.ML.Data;
+using Microsoft.ML.Featurizers;
+
+namespace Samples.Dynamic
+{
+    public static class DateTimeTransformer
+    {
+        private class DateTimeInput
+        {
+            public long Date;
+        }
+
+        public static void Example()
+        {
+            // Create a new ML context, for ML.NET operations. It can be used for
+            // exception tracking and logging, as well as the source of randomness.
+            var mlContext = new MLContext();
+
+            // Create a small dataset as an IEnumerable.
+            // Future Date - 2025 June 30
+            var samples = new[] { new DateTimeInput() { Date = 1751241600 } };
+
+            // Convert training data to IDataView.
+            var dataview = mlContext.Data.LoadFromEnumerable(samples);
+
+            // A pipeline for splitting the time features into individual columns
+            var pipeline = mlContext.Transforms.DateTimeTransformer("Date", "DTC");
+
+            // The transformed data.
+            var transformedData = pipeline.Fit(dataview).Transform(dataview);
+
+            // Now let's take a look at what this did. We should have created 21 more columns with all the
+            // DateTime information split into its own columns
+            var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
+                transformedData, reuseRowObject: false);
+
+            // And we can write out a few rows
+            Console.WriteLine($"Features column obtained post-transformation.");
+            foreach (var featureRow in featuresColumn)
+                Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
+                    featureRow.DTCDay + ", " + featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " +
+                    featureRow.DTCSecond + ", " + featureRow.DTCAmPm + ", " + featureRow.DTCHour12 + ", " +
+                    featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " + featureRow.DTCDayOfYear +
+                    ", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCQuarterOfYear + ", " + featureRow.DTCHalfOfYear +
+                    ", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
+                    featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel + ", " + featureRow.DTCHolidayName + ", " +
+                    featureRow.DTCIsPaidTimeOff);
+
+            // Expected output:
+            //  Features columns obtained post-transformation.
+            //  1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday, , 0
+        }
+
+        // These columns start with DTC because that is the prefix we picked
+        private sealed class TransformedData
+        {
+            public long Date { get; set; }
+            public int DTCYear { get; set; }
+            public byte DTCMonth { get; set; }
+            public byte DTCDay { get; set; }
+            public byte DTCHour { get; set; }
+            public byte DTCMinute { get; set; }
+            public byte DTCSecond { get; set; }
+            public byte DTCAmPm { get; set; }
+            public byte DTCHour12 { get; set; }
+            public byte DTCDayOfWeek { get; set; }
+            public byte DTCDayOfQuarter { get; set; }
+            public ushort DTCDayOfYear { get; set; }
+            public ushort DTCWeekOfMonth { get; set; }
+            public byte DTCQuarterOfYear { get; set; }
+            public byte DTCHalfOfYear { get; set; }
+            public byte DTCWeekIso { get; set; }
+            public int DTCYearIso { get; set; }
+            public string DTCMonthLabel { get; set; }
+            public string DTCAmPmLabel { get; set; }
+            public string DTCDayOfWeekLabel { get; set; }
+            public string DTCHolidayName { get; set; }
+            public byte DTCIsPaidTimeOff { get; set; }
+        }
+    }
+}
diff --git a/...les/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformerDropColumns.cs b/...les/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/DateTimeTransformerDropColumns.cs
@@ -0,0 +1,80 @@
+using System;
+using System.Collections.Generic;
+using Microsoft.ML;
+using Microsoft.ML.Data;
+using Microsoft.ML.Featurizers;
+
+namespace Samples.Dynamic
+{
+    public static class DateTimeTransformerDropColumns
+    {
+        private class DateTimeInput
+        {
+            public long Date;
+        }
+
+        public static void Example()
+        {
+            // Create a new ML context, for ML.NET operations. It can be used for
+            // exception tracking and logging, as well as the source of randomness.
+            var mlContext = new MLContext();
+
+            // Create a small dataset as an IEnumerable.
+            // Future Date - 2025 June 30
+            var samples = new[] { new DateTimeInput() { Date = 1751241600 } };
+
+            // Convert training data to IDataView.
+            var dataview = mlContext.Data.LoadFromEnumerable(samples);
+
+            // A pipeline for splitting the time features into individual columns
+            // All the columns listed here will be dropped.
+            var pipeline = mlContext.Transforms.DateTimeTransformer("Date", "DTC", DateTimeTransformerEstimator.ColumnsProduced.IsPaidTimeOff,
+                DateTimeTransformerEstimator.ColumnsProduced.Day, DateTimeTransformerEstimator.ColumnsProduced.QuarterOfYear,
+                DateTimeTransformerEstimator.ColumnsProduced.AmPm, DateTimeTransformerEstimator.ColumnsProduced.HolidayName);
+
+            // The transformed data.
+            var transformedData = pipeline.Fit(dataview).Transform(dataview);
+
+            // Now let's take a look at what this did. We should have created 16 more columns with all the
+            // DateTime information split into its own columns
+            var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
+                transformedData, reuseRowObject: false);
+
+            // And we can write out a few rows
+            Console.WriteLine($"Features column obtained post-transformation.");
+            foreach (var featureRow in featuresColumn)
+                Console.WriteLine(featureRow.Date + ", " + featureRow.DTCYear + ", " + featureRow.DTCMonth + ", " +
+                    featureRow.DTCHour + ", " + featureRow.DTCMinute + ", " + featureRow.DTCSecond + ", " +
+                    featureRow.DTCHour12 + ", " + featureRow.DTCDayOfWeek + ", " + featureRow.DTCDayOfQuarter + ", " +
+                    featureRow.DTCDayOfYear + ", " + featureRow.DTCWeekOfMonth + ", " + featureRow.DTCHalfOfYear +
+                    ", " + featureRow.DTCWeekIso + ", " + featureRow.DTCYearIso + ", " + featureRow.DTCMonthLabel + ", " +
+                    featureRow.DTCAmPmLabel + ", " + featureRow.DTCDayOfWeekLabel);
+
+            // Expected output:
+            //  Features columns obtained post-transformation.
+            //  1751241600, 2025, 6, 30, 0, 0, 0, 0, 0, 1, 91, 180, 4, 2, 1, 27, 2025, June, am, Monday
+        }
+
+        // These columns start with DTC because that is the prefix we picked
+        private sealed class TransformedData
+        {
+            public long Date { get; set; }
+            public int DTCYear { get; set; }
+            public byte DTCMonth { get; set; }
+            public byte DTCHour { get; set; }
+            public byte DTCMinute { get; set; }
+            public byte DTCSecond { get; set; }
+            public byte DTCHour12 { get; set; }
+            public byte DTCDayOfWeek { get; set; }
+            public byte DTCDayOfQuarter { get; set; }
+            public ushort DTCDayOfYear { get; set; }
+            public ushort DTCWeekOfMonth { get; set; }
+            public byte DTCHalfOfYear { get; set; }
+            public byte DTCWeekIso { get; set; }
+            public int DTCYearIso { get; set; }
+            public string DTCMonthLabel { get; set; }
+            public string DTCAmPmLabel { get; set; }
+            public string DTCDayOfWeekLabel { get; set; }
+        }
+    }
+}
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/RobustScaler.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/Featurizers/RobustScaler.cs
@@ -0,0 +1,69 @@
+using System;
+using System.Collections.Generic;
+using Microsoft.ML;
+using Microsoft.ML.Data;
+using Microsoft.ML.Featurizers;
+
+namespace Samples.Dynamic
+{
+    public static class RobustScaler
+    {
+        public static void Example()
+        {
+            // Create a new ML context, for ML.NET operations. It can be used for
+            // exception tracking and logging, as well as the source of randomness.
+            var mlContext = new MLContext();
+
+            // Create a small dataset as an IEnumerable.
+            var samples = new List<InputData>()
+            {
+                new InputData(){ Feature1 = 1f },
+
+                new InputData(){ Feature1 = 3f },
+
+                new InputData(){ Feature1 = 5f },
+
+                new InputData(){ Feature1 = 7f },
+
+                new InputData(){ Feature1 = 9f },
+            };
+
+            // Convert training data to IDataView.
+            var dataview = mlContext.Data.LoadFromEnumerable(samples);
+
+            // A pipeline for centering and scaling the feature1 column
+            var pipeline = mlContext.Transforms.RobustScalerTransformer("Feature1");
+
+            // The transformed data.
+            var transformedData = pipeline.Fit(dataview).Transform(dataview);
+
+            // Now let's take a look at what this did. The values should be centered around 0 and scaled.
+            // We can extract the newly created columns as an IEnumerable of TransformedData.
+            var featuresColumn = mlContext.Data.CreateEnumerable<TransformedData>(
+                transformedData, reuseRowObject: false);
+
+            // And we can write out a few rows
+            Console.WriteLine($"Features column obtained post-transformation.");
+            foreach (var featureRow in featuresColumn)
+                Console.WriteLine(featureRow.Feature1);
+
+            // Expected output:
+            //  Features column obtained post-transformation.
+            //  -1
+            //  -.5
+            //  0
+            //  .5
+            //  1
+        }
+
+        private class InputData
+        {
+            public float Feature1;
+        }
+
+        private sealed class TransformedData
+        {
+            public float Feature1 { get; set; }
+        }
+    }
+}