From 7545d5aa339f53485b1bcea97b805973d45c49aa Mon Sep 17 00:00:00 2001
From: Abhishek Goswami <abgoswam@gmail.com>
Date: Wed, 3 Apr 2019 00:13:00 +0000
Subject: [PATCH 1/6] samples for FeatureSelection transform estimators

---
 .../Dynamic/FeatureSelectionTransform.cs      | 120 ----------------
 .../SelectFeaturesBasedOnCount.cs             | 117 ++++++++++++++++
 .../SelectFeaturesBasedOnMutualInformation.cs | 129 ++++++++++++++++++
 .../FeatureSelectionCatalog.cs                |  25 ++--
 4 files changed, 262 insertions(+), 129 deletions(-)
 delete mode 100644 docs/samples/Microsoft.ML.Samples/Dynamic/FeatureSelectionTransform.cs
 create mode 100644 docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
 create mode 100644 docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/FeatureSelectionTransform.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/FeatureSelectionTransform.cs
deleted file mode 100644
index de98b1ddb0..0000000000
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/FeatureSelectionTransform.cs
+++ /dev/null
@@ -1,120 +0,0 @@
-using System;
-using System.Collections.Generic;
-using Microsoft.ML.Data;
-
-namespace Microsoft.ML.Samples.Dynamic
-{
-    public static class FeatureSelectionTransform
-    {
-        public static void Example()
-        {
-            // Downloading a classification dataset from github.com/dotnet/machinelearning.
-            // It will be stored in the same path as the executable
-            string dataFilePath = SamplesUtils.DatasetUtils.DownloadBreastCancerDataset();
-
-            // Data Preview
-            //    1. Label							0=benign, 1=malignant
-            //    2. Clump Thickness               1 - 10
-            //    3. Uniformity of Cell Size       1 - 10
-            //    4. Uniformity of Cell Shape      1 - 10
-            //    5. Marginal Adhesion             1 - 10
-            //    6. Single Epithelial Cell Size   1 - 10
-            //    7. Bare Nuclei                   1 - 10
-            //    8. Bland Chromatin               1 - 10
-            //    9. Normal Nucleoli               1 - 10
-            //   10. Mitoses                       1 - 10
-
-            // 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 ml = new MLContext();
-
-            // First, we define the loader: specify the data columns and where to find them in the text file. Notice that we combine entries from
-            // all the feature columns into entries of a vector of a single column named "Features".
-            var loader = ml.Data.CreateTextLoader(
-                columns: new[]
-                    {
-                        new TextLoader.Column("Label", DataKind.Boolean, 0),
-                        new TextLoader.Column("Features", DataKind.Single, new [] { new TextLoader.Range(1, 9) })
-                    },
-                hasHeader: true
-            );
-
-            // Then, we use the loader to load the data as an IDataView.
-            var data = loader.Load(dataFilePath);
-
-            // Second, we define the transformations that we apply on the data. Remember that an Estimator does not transform data
-            // directly, but it needs to be trained on data using .Fit(), and it will output a Transformer, which can transform data.
-
-            // In this example we define a CountFeatureSelectingEstimator, that selects slots in a feature vector that have more non-default 
-            // values than the specified count. This transformation can be used to remove slots with too many missing values.
-            var countSelectEst = ml.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                outputColumnName: "FeaturesCountSelect", inputColumnName: "Features", count: 695);
-
-            // We also define a MutualInformationFeatureSelectingEstimator that selects the top k slots in a feature 
-            // vector based on highest mutual information between that slot and a specified label. Notice that it is possible to 
-            // 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", labelColumnName: "Label", slotsInOutput: 5);
-
-            // Now, we can put the previous two transformations together in a pipeline.
-            var pipeline = countSelectEst.Append(mutualInfoEst);
-
-            // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
-            var transformedData = pipeline.Fit(data).Transform(data);
-
-            // Small helper to print the data inside a column, in the console. Only prints the first 10 rows.
-            Action<string, IEnumerable<VBuffer<float>>> printHelper = (columnName, column) =>
-            {
-                Console.WriteLine($"{columnName} column obtained post-transformation.");
-                int count = 0;
-                foreach (var row in column)
-                {
-                    foreach (var value in row.GetValues())
-                        Console.Write($"{value}\t");
-                    Console.WriteLine("");
-                    count++;
-                    if (count >= 10)
-                        break;
-                }
-
-                Console.WriteLine("===================================================");
-            };
-
-            // Print the data that results from the transformations.
-            var countSelectColumn = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema["FeaturesCountSelect"]);
-            var MISelectColumn = transformedData.GetColumn<VBuffer<float>>(transformedData.Schema["FeaturesMISelect"]);
-            printHelper("FeaturesCountSelect", countSelectColumn);
-            printHelper("FeaturesMISelect", MISelectColumn);
-
-            // Below is the output of the this code. We see that some slots habe been dropped by the first transformation.
-            // Among the remaining slots, the second transformation only preserves the top 5 slots based on mutualinformation 
-            // with the label column.
-
-            // FeaturesCountSelect column obtained post-transformation.
-            // 5       4       4       5       7       3       2       1
-            // 3       1       1       1       2       3       1       1
-            // 6       8       8       1       3       3       7       1
-            // 4       1       1       3       2       3       1       1
-            // 8       10      10      8       7       9       7       1
-            // 1       1       1       1       2       3       1       1
-            // 2       1       2       1       2       3       1       1
-            // 2       1       1       1       2       1       1       5
-            // 4       2       1       1       2       2       1       1
-            // 1       1       1       1       1       3       1       1
-            // ===================================================
-            // FeaturesMISelect column obtained post-transformation.
-            // 4       4       7       3       2
-            // 1       1       2       3       1
-            // 8       8       3       3       7
-            // 1       1       2       3       1
-            // 10      10      7       9       7
-            // 1       1       2       3       1
-            // 1       2       2       3       1
-            // 1       1       2       1       1
-            // 2       1       2       2       1
-            // 1       1       1       3       1
-            // ===================================================
-        }
-    }
-}
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
new file mode 100644
index 0000000000..3a0aff4f35
--- /dev/null
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
@@ -0,0 +1,117 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+    public static class SelectFeaturesBasedOnCount
+    {
+        private static readonly int printRowCount = 4;
+
+        public static void Example()
+        {
+            // Downloading a classification dataset from github.com/dotnet/machinelearning.
+            // It will be stored in the same path as the executable
+            string dataFilePath = SamplesUtils.DatasetUtils.DownloadBreastCancerDataset();
+
+            // Data Preview
+            //    1. Label							0=benign, 1=malignant
+            //    2. Clump Thickness               1 - 10
+            //    3. Uniformity of Cell Size       1 - 10
+            //    4. Uniformity of Cell Shape      1 - 10
+            //    5. Marginal Adhesion             1 - 10
+            //    6. Single Epithelial Cell Size   1 - 10
+            //    7. Bare Nuclei                   1 - 10
+            //    8. Bland Chromatin               1 - 10
+            //    9. Normal Nucleoli               1 - 10
+            //   10. Mitoses                       1 - 10
+
+            // 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();
+
+            // First, we define the loader: specify the data columns and where to find them in the text file. Notice that we combine entries from
+            // all the feature columns into entries of a vector of a single column named "Features".
+            var loader = mlContext.Data.CreateTextLoader(
+                columns: new[]
+                    {
+                        new TextLoader.Column("Label", DataKind.Boolean, 0),
+                        new TextLoader.Column("GroupA", DataKind.Single, new [] { new TextLoader.Range(1, 3) }),
+                        new TextLoader.Column("GroupB", DataKind.Single, new [] { new TextLoader.Range(4, 6) }),
+                        new TextLoader.Column("GroupC", DataKind.Single, new [] { new TextLoader.Range(7, 9) }),
+                    },
+                hasHeader: true
+            );
+
+            // Then, we use the loader to load the data as an IDataView.
+            var data = loader.Load(dataFilePath);
+
+            Console.WriteLine("Contents of column 'GroupB'");
+            PrintDataColumn(data, "GroupB");
+            // 5 7 10
+            // 1 2 2
+            // 1 3 4
+            // 3 2 1
+            
+            // Second, we define the transformations that we apply on the data. Remember that an Estimator does not transform data
+            // directly, but it needs to be trained on data using .Fit(), and it will output a Transformer, which can transform data.
+
+            // In this example we define a CountFeatureSelectingEstimator, that selects slots in a feature vector that have more non-default 
+            // values than the specified count. This transformation can be used to remove slots with too many missing values.
+            var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
+                outputColumnName: "FeaturesSelectedGroupB", inputColumnName: "GroupB", count: 695);
+
+            // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
+            var transformedData = pipeline.Fit(data).Transform(data);
+
+            Console.WriteLine("Contents of column 'FeaturesSelectedGroupB'");
+            PrintDataColumn(transformedData, "FeaturesSelectedGroupB");
+            // Note, SelectFeaturesBasedOnCount retained only 2 slots (out of 3).  
+            // 5 7
+            // 1 2
+            // 1 3
+            // 3 2
+
+            // Multi column example : This pipeline uses two columns for transformation
+            pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
+                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupB"), new InputOutputColumnPair("GroupC") },
+                count: 695);
+
+            transformedData = pipeline.Fit(data).Transform(data);
+
+            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true).Take(printRowCount);
+            Console.WriteLine("Contents of two columns 'GroupB' and 'GroupC'.");
+            foreach (var item in convertedData)
+                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
+
+            // 5 7             3 2 1
+            // 1 2             3 1 1
+            // 1 3             3 7 1
+            // 3 2             3 1 1
+        }
+
+        private static void PrintDataColumn(IDataView transformedData, string columnName)
+        {
+            var countSelectColumn = transformedData.GetColumn<float[]>(transformedData.Schema[columnName]);
+
+            int count = 0;
+            foreach (var row in countSelectColumn)
+            {
+                for (var i = 0; i < row.Length; i++)
+                    Console.Write($"{row[i]} ");
+                Console.WriteLine();
+
+                count += 1;
+                if (count >= printRowCount)
+                    break;
+            }
+        }
+
+        private class TransformedData
+        {
+            public float[] GroupB { get; set; }
+
+            public float[] GroupC { get; set; }
+        }
+    }
+}
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
new file mode 100644
index 0000000000..c0599b14b7
--- /dev/null
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
@@ -0,0 +1,129 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+    public static class SelectFeaturesBasedOnMutualInformation
+    {
+        private static readonly int printRowCount = 4;
+
+        public static void Example()
+        {
+            // Downloading a classification dataset from github.com/dotnet/machinelearning.
+            // It will be stored in the same path as the executable
+            string dataFilePath = SamplesUtils.DatasetUtils.DownloadBreastCancerDataset();
+
+            // Data Preview
+            //    1. Label							0=benign, 1=malignant
+            //    2. Clump Thickness               1 - 10
+            //    3. Uniformity of Cell Size       1 - 10
+            //    4. Uniformity of Cell Shape      1 - 10
+            //    5. Marginal Adhesion             1 - 10
+            //    6. Single Epithelial Cell Size   1 - 10
+            //    7. Bare Nuclei                   1 - 10
+            //    8. Bland Chromatin               1 - 10
+            //    9. Normal Nucleoli               1 - 10
+            //   10. Mitoses                       1 - 10
+
+            // 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();
+
+            // First, we define the loader: specify the data columns and where to find them in the text file. Notice that we combine entries from
+            // all the feature columns into entries of a vector of a single column named "Features".
+            var loader = mlContext.Data.CreateTextLoader(
+                columns: new[]
+                    {
+                        new TextLoader.Column("Label", DataKind.Boolean, 0),
+                        new TextLoader.Column("GroupA", DataKind.Single, new [] { new TextLoader.Range(1, 3) }),
+                        new TextLoader.Column("GroupB", DataKind.Single, new [] { new TextLoader.Range(4, 6) }),
+                        new TextLoader.Column("GroupC", DataKind.Single, new [] { new TextLoader.Range(7, 9) }),
+                    },
+                hasHeader: true
+            );
+
+            // Then, we use the loader to load the data as an IDataView.
+            var data = loader.Load(dataFilePath);
+
+            Console.WriteLine("Contents of column 'GroupB'");
+            PrintDataColumn(data, "GroupB");
+            // 5 7 10
+            // 1 2 2
+            // 1 3 4
+            // 3 2 1
+
+            Console.WriteLine("Contents of column 'GroupC'");
+            PrintDataColumn(data, "GroupC");
+            // 3 2 1
+            // 3 1 1
+            // 3 7 1
+            // 3 1 1
+
+            // Second, we define the transformations that we apply on the data. Remember that an Estimator does not transform data
+            // directly, but it needs to be trained on data using .Fit(), and it will output a Transformer, which can transform data.
+
+            // We define a MutualInformationFeatureSelectingEstimator that selects the top k slots in a feature 
+            // vector based on highest mutual information between that slot and a specified label. Notice that it is possible to 
+            // specify the parameter `numBins', which controls the number of bins used in the approximation of the mutual information
+            // between features and label.
+
+            var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
+                outputColumnName: "FeaturesSelectedGroupB", inputColumnName: "GroupB", labelColumnName: "Label", slotsInOutput: 2);
+
+            // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
+            var transformedData = pipeline.Fit(data).Transform(data);
+
+            Console.WriteLine("Contents of column 'FeaturesSelectedGroupB'");
+            PrintDataColumn(transformedData, "FeaturesSelectedGroupB");
+            // Note, SelectFeaturesBasedOnMutualInformation retained 2 slots (out of 3).  
+            // 7 10
+            // 2 2
+            // 3 4
+            // 2 1
+
+            // Multi column example : This pipeline uses two columns for transformation
+            pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
+                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupB"), new InputOutputColumnPair("GroupC") },
+                labelColumnName: "Label",
+                slotsInOutput:4);
+
+            transformedData = pipeline.Fit(data).Transform(data);
+
+            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true).Take(printRowCount);
+            Console.WriteLine("Contents of two columns 'GroupB' and 'GroupC'.");
+            foreach (var item in convertedData)
+                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
+
+            // 7 10            3 2
+            // 2 2             3 1
+            // 3 4             3 7
+            // 2 1             3 1
+        }
+
+        private static void PrintDataColumn(IDataView transformedData, string columnName)
+        {
+            var countSelectColumn = transformedData.GetColumn<float[]>(transformedData.Schema[columnName]);
+
+            int count = 0;
+            foreach (var row in countSelectColumn)
+            {
+                for (var i = 0; i < row.Length; i++)
+                    Console.Write($"{row[i]} ");
+                Console.WriteLine();
+
+                count += 1;
+                if (count >= printRowCount)
+                    break;
+            }
+        }
+
+        private class TransformedData
+        {
+            public float[] GroupB { get; set; }
+
+            public float[] GroupC { get; set; }
+        }
+    }
+}
diff --git a/src/Microsoft.ML.Transforms/FeatureSelectionCatalog.cs b/src/Microsoft.ML.Transforms/FeatureSelectionCatalog.cs
index 1b9d35d251..0cdea6b269 100644
--- a/src/Microsoft.ML.Transforms/FeatureSelectionCatalog.cs
+++ b/src/Microsoft.ML.Transforms/FeatureSelectionCatalog.cs
@@ -24,7 +24,7 @@ public static class FeatureSelectionCatalog
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        /// [!code-csharp[SelectFeaturesBasedOnMutualInformation](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/FeatureSelectionTransform.cs?range=1-4,10-121)]
+        /// [!code-csharp[SelectFeaturesBasedOnMutualInformation](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/SelectFeaturesBasedOnMutualInformation.cs)]
         /// ]]>
         /// </format>
         /// </example>
@@ -41,6 +41,13 @@ public static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMu
         /// <param name="labelColumnName">The name of the label column.</param>
         /// <param name="slotsInOutput">The maximum number of slots to preserve in the output. The number of slots to preserve is taken across all input columns.</param>
         /// <param name="numberOfBins">Max number of bins used to approximate mutual information between each input column and the label column. Power of 2 recommended.</param>
+        /// <example>
+        /// <format type="text/markdown">
+        /// <![CDATA[
+        /// [!code-csharp[SelectFeaturesBasedOnMutualInformation](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/SelectFeaturesBasedOnMutualInformation.cs)]
+        /// ]]>
+        /// </format>
+        /// </example>
         public static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMutualInformation(this TransformsCatalog.FeatureSelectionTransforms catalog,
             InputOutputColumnPair[] columns,
             string labelColumnName = MutualInfoSelectDefaults.LabelColumn,
@@ -56,13 +63,6 @@ public static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMu
         /// <include file='doc.xml' path='doc/members/member[@name="CountFeatureSelection"]' />
         /// <param name="catalog">The transform's catalog.</param>
         /// <param name="columns">Describes the parameters of the feature selection process for each column pair.</param>
-        /// <example>
-        /// <format type="text/markdown">
-        /// <![CDATA[
-        /// [!code-csharp[SelectFeaturesBasedOnCount](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/FeatureSelectionTransform.cs?range=1-4,10-121)]
-        /// ]]>
-        /// </format>
-        /// </example>
         [BestFriend]
         internal static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this TransformsCatalog.FeatureSelectionTransforms catalog,
             params CountFeatureSelectingEstimator.ColumnOptions[] columns)
@@ -76,7 +76,7 @@ internal static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this T
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        /// [!code-csharp[SelectFeaturesBasedOnCount](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/FeatureSelectionTransform.cs?range=1-4,10-121)]
+        /// [!code-csharp[SelectFeaturesBasedOnCount](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/SelectFeaturesBasedOnCount.cs)]
         /// ]]>
         /// </format>
         /// </example>
@@ -90,6 +90,13 @@ public static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this Tra
         /// <param name="catalog">The transform's catalog.</param>
         /// <param name="columns">Specifies the names of the columns on which to apply the transformation.</param>
         /// <param name="count">If the count of non-default values for a slot is greater than or equal to this threshold in the training data, the slot is preserved.</param>
+        /// <example>
+        /// <format type="text/markdown">
+        /// <![CDATA[
+        /// [!code-csharp[SelectFeaturesBasedOnCount](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/SelectFeaturesBasedOnCount.cs)]
+        /// ]]>
+        /// </format>
+        /// </example>
         public static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this TransformsCatalog.FeatureSelectionTransforms catalog,
             InputOutputColumnPair[] columns,
             long count = CountSelectDefaults.Count)

From fdcc01254b02a8c74ff5d0b2565bca1b5e5290d6 Mon Sep 17 00:00:00 2001
From: Abhishek Goswami <abgoswam@gmail.com>
Date: Wed, 3 Apr 2019 23:13:09 +0000
Subject: [PATCH 2/6] fix review comments

---
 .../SelectFeaturesBasedOnCount.cs             | 135 ++++++++--------
 .../SelectFeaturesBasedOnCountMultiColumn.cs  | 128 +++++++++++++++
 .../SelectFeaturesBasedOnMutualInformation.cs | 146 ++++++++----------
 ...uresBasedOnMutualInformationMultiColumn.cs | 111 +++++++++++++
 .../FeatureSelectionCatalog.cs                |   8 +-
 5 files changed, 371 insertions(+), 157 deletions(-)
 create mode 100644 docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
 create mode 100644 docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
index 3a0aff4f35..a1cad6af94 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
@@ -1,117 +1,110 @@
 using System;
-using System.Linq;
+using System.Collections.Generic;
 using Microsoft.ML.Data;
 
 namespace Microsoft.ML.Samples.Dynamic
 {
     public static class SelectFeaturesBasedOnCount
     {
-        private static readonly int printRowCount = 4;
-
         public static void Example()
         {
-            // Downloading a classification dataset from github.com/dotnet/machinelearning.
-            // It will be stored in the same path as the executable
-            string dataFilePath = SamplesUtils.DatasetUtils.DownloadBreastCancerDataset();
-
-            // Data Preview
-            //    1. Label							0=benign, 1=malignant
-            //    2. Clump Thickness               1 - 10
-            //    3. Uniformity of Cell Size       1 - 10
-            //    4. Uniformity of Cell Shape      1 - 10
-            //    5. Marginal Adhesion             1 - 10
-            //    6. Single Epithelial Cell Size   1 - 10
-            //    7. Bare Nuclei                   1 - 10
-            //    8. Bland Chromatin               1 - 10
-            //    9. Normal Nucleoli               1 - 10
-            //   10. Mitoses                       1 - 10
-
             // 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();
 
-            // First, we define the loader: specify the data columns and where to find them in the text file. Notice that we combine entries from
-            // all the feature columns into entries of a vector of a single column named "Features".
-            var loader = mlContext.Data.CreateTextLoader(
-                columns: new[]
-                    {
-                        new TextLoader.Column("Label", DataKind.Boolean, 0),
-                        new TextLoader.Column("GroupA", DataKind.Single, new [] { new TextLoader.Range(1, 3) }),
-                        new TextLoader.Column("GroupB", DataKind.Single, new [] { new TextLoader.Range(4, 6) }),
-                        new TextLoader.Column("GroupC", DataKind.Single, new [] { new TextLoader.Range(7, 9) }),
-                    },
-                hasHeader: true
-            );
-
-            // Then, we use the loader to load the data as an IDataView.
-            var data = loader.Load(dataFilePath);
+            // Get a small dataset as an IEnumerable and convert it to an IDataView.
+            var rawData = GetData();
+            var data = mlContext.Data.LoadFromEnumerable(rawData);
 
             Console.WriteLine("Contents of column 'GroupB'");
             PrintDataColumn(data, "GroupB");
-            // 5 7 10
-            // 1 2 2
-            // 1 3 4
-            // 3 2 1
-            
+            // 4       NaN     6
+            // 4       5       6
+            // 4       5       6
+            // 4       NaN     NaN
+
             // Second, we define the transformations that we apply on the data. Remember that an Estimator does not transform data
             // directly, but it needs to be trained on data using .Fit(), and it will output a Transformer, which can transform data.
 
-            // In this example we define a CountFeatureSelectingEstimator, that selects slots in a feature vector that have more non-default 
-            // values than the specified count. This transformation can be used to remove slots with too many missing values.
+            // We will use the SelectFeaturesBasedOnCount transform estimator, to retain only those slots which have 
+            // at least 'count' non-default values per slot.
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                outputColumnName: "FeaturesSelectedGroupB", inputColumnName: "GroupB", count: 695);
+                outputColumnName: "FeaturesSelectedGroupB", inputColumnName: "GroupB", count: 3);
 
             // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
             var transformedData = pipeline.Fit(data).Transform(data);
 
             Console.WriteLine("Contents of column 'FeaturesSelectedGroupB'");
             PrintDataColumn(transformedData, "FeaturesSelectedGroupB");
-            // Note, SelectFeaturesBasedOnCount retained only 2 slots (out of 3).  
-            // 5 7
-            // 1 2
-            // 1 3
-            // 3 2
-
-            // Multi column example : This pipeline uses two columns for transformation
-            pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupB"), new InputOutputColumnPair("GroupC") },
-                count: 695);
-
-            transformedData = pipeline.Fit(data).Transform(data);
-
-            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true).Take(printRowCount);
-            Console.WriteLine("Contents of two columns 'GroupB' and 'GroupC'.");
-            foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
-
-            // 5 7             3 2 1
-            // 1 2             3 1 1
-            // 1 3             3 7 1
-            // 3 2             3 1 1
+            // 4       6
+            // 4       6
+            // 4       6
+            // 4       NaN
         }
 
         private static void PrintDataColumn(IDataView transformedData, string columnName)
         {
             var countSelectColumn = transformedData.GetColumn<float[]>(transformedData.Schema[columnName]);
 
-            int count = 0;
             foreach (var row in countSelectColumn)
             {
                 for (var i = 0; i < row.Length; i++)
-                    Console.Write($"{row[i]} ");
+                    Console.Write($"{row[i]}\t");
                 Console.WriteLine();
-
-                count += 1;
-                if (count >= printRowCount)
-                    break;
             }
         }
 
-        private class TransformedData
+        public class NumericData
         {
+            public bool Label;
+
+            [VectorType(3)]
+            public float[] GroupA { get; set; }
+
+            [VectorType(3)]
             public float[] GroupB { get; set; }
 
+            [VectorType(3)]
             public float[] GroupC { get; set; }
         }
+
+        /// <summary>
+        /// Returns a few rows of numeric data.
+        /// </summary>
+        public static IEnumerable<NumericData> GetData()
+        {
+            var data = new List<NumericData>
+            {
+                new NumericData
+                {
+                    Label = true,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, float.NaN, 6 },
+                    GroupC = new float[] { 7, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = false,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, 5, 6 },
+                    GroupC = new float[] { 7, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = true,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, 5, 6 },
+                    GroupC = new float[] { 7, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = false,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, float.NaN, float.NaN },
+                    GroupC = new float[] { 7, 8, 9 },
+                }
+            };
+            return data;
+        }
     }
 }
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
new file mode 100644
index 0000000000..0b73a6d0fd
--- /dev/null
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
@@ -0,0 +1,128 @@
+using System;
+using System.Collections.Generic;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+    public static class SelectFeaturesBasedOnCountMultiColumn
+    {
+        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();
+
+            // Get a small dataset as an IEnumerable and convert it to an IDataView.
+            var rawData = GetData();
+            var data = mlContext.Data.LoadFromEnumerable(rawData);
+
+            Console.WriteLine("Contents of column 'GroupB'");
+            PrintDataColumn(data, "GroupB");
+            // 4       NaN     6
+            // 4       5       6
+            // 4       5       6
+            // 4       NaN     NaN
+
+            Console.WriteLine("Contents of column 'GroupC'");
+            PrintDataColumn(data, "GroupC");
+            // NaN     8       9
+            // NaN     8       9
+            // NaN     8       9
+            // 7       8       9
+
+            // Second, we define the transformations that we apply on the data. Remember that an Estimator does not transform data
+            // directly, but it needs to be trained on data using .Fit(), and it will output a Transformer, which can transform data.
+
+            // We will use the SelectFeaturesBasedOnCount transform estimator, to retain only those slots which have 
+            // at least 'count' non-default values per slot.
+
+            // Multi column example : This pipeline uses two columns for transformation
+            var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
+                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupB"), new InputOutputColumnPair("GroupC") },
+                count: 3);
+
+            var transformedData = pipeline.Fit(data).Transform(data);
+
+            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
+            Console.WriteLine("Contents of two columns 'GroupB' and 'GroupC'.");
+            foreach (var item in convertedData)
+                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
+            // 4 6             8 9
+            // 4 6             8 9
+            // 4 6             8 9
+            // 4 NaN           8 9
+        }
+
+        private static void PrintDataColumn(IDataView transformedData, string columnName)
+        {
+            var countSelectColumn = transformedData.GetColumn<float[]>(transformedData.Schema[columnName]);
+
+            foreach (var row in countSelectColumn)
+            {
+                for (var i = 0; i < row.Length; i++)
+                    Console.Write($"{row[i]}\t");
+                Console.WriteLine();
+            }
+        }
+
+        private class TransformedData
+        {
+            public float[] GroupB { get; set; }
+
+            public float[] GroupC { get; set; }
+        }
+
+        public class NumericData
+        {
+            public bool Label;
+
+            [VectorType(3)]
+            public float[] GroupA { get; set; }
+
+            [VectorType(3)]
+            public float[] GroupB { get; set; }
+
+            [VectorType(3)]
+            public float[] GroupC { get; set; }
+        }
+
+        /// <summary>
+        /// Returns a few rows of numeric data.
+        /// </summary>
+        public static IEnumerable<NumericData> GetData()
+        {
+            var data = new List<NumericData>
+            {
+                new NumericData
+                {
+                    Label = true,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, float.NaN, 6 },
+                    GroupC = new float[] { float.NaN, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = false,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, 5, 6 },
+                    GroupC = new float[] { float.NaN, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = true,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, 5, 6 },
+                    GroupC = new float[] { float.NaN, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = false,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, float.NaN, float.NaN },
+                    GroupC = new float[] { 7, 8, 9 },
+                }
+            };
+            return data;
+        }
+    }
+}
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
index c0599b14b7..a4b1f4d6b4 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
@@ -1,129 +1,111 @@
 using System;
 using System.Collections.Generic;
-using System.Linq;
 using Microsoft.ML.Data;
 
 namespace Microsoft.ML.Samples.Dynamic
 {
     public static class SelectFeaturesBasedOnMutualInformation
     {
-        private static readonly int printRowCount = 4;
-
         public static void Example()
         {
-            // Downloading a classification dataset from github.com/dotnet/machinelearning.
-            // It will be stored in the same path as the executable
-            string dataFilePath = SamplesUtils.DatasetUtils.DownloadBreastCancerDataset();
-
-            // Data Preview
-            //    1. Label							0=benign, 1=malignant
-            //    2. Clump Thickness               1 - 10
-            //    3. Uniformity of Cell Size       1 - 10
-            //    4. Uniformity of Cell Shape      1 - 10
-            //    5. Marginal Adhesion             1 - 10
-            //    6. Single Epithelial Cell Size   1 - 10
-            //    7. Bare Nuclei                   1 - 10
-            //    8. Bland Chromatin               1 - 10
-            //    9. Normal Nucleoli               1 - 10
-            //   10. Mitoses                       1 - 10
-
             // 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();
 
-            // First, we define the loader: specify the data columns and where to find them in the text file. Notice that we combine entries from
-            // all the feature columns into entries of a vector of a single column named "Features".
-            var loader = mlContext.Data.CreateTextLoader(
-                columns: new[]
-                    {
-                        new TextLoader.Column("Label", DataKind.Boolean, 0),
-                        new TextLoader.Column("GroupA", DataKind.Single, new [] { new TextLoader.Range(1, 3) }),
-                        new TextLoader.Column("GroupB", DataKind.Single, new [] { new TextLoader.Range(4, 6) }),
-                        new TextLoader.Column("GroupC", DataKind.Single, new [] { new TextLoader.Range(7, 9) }),
-                    },
-                hasHeader: true
-            );
-
-            // Then, we use the loader to load the data as an IDataView.
-            var data = loader.Load(dataFilePath);
+            // Get a small dataset as an IEnumerable and convert it to an IDataView.
+            var rawData = GetData();
 
-            Console.WriteLine("Contents of column 'GroupB'");
-            PrintDataColumn(data, "GroupB");
-            // 5 7 10
-            // 1 2 2
-            // 1 3 4
-            // 3 2 1
+            Console.WriteLine("Contents of two columns 'Label' and 'GroupB'.");
+            foreach (var item in rawData)
+                Console.WriteLine("{0}\t\t{1}", item.Label, string.Join(" ", item.GroupB));
+            // True            4 0 6
+            // False           0 5 7
+            // True            4 0 6
+            // False           0 5 7
 
-            Console.WriteLine("Contents of column 'GroupC'");
-            PrintDataColumn(data, "GroupC");
-            // 3 2 1
-            // 3 1 1
-            // 3 7 1
-            // 3 1 1
-
-            // Second, we define the transformations that we apply on the data. Remember that an Estimator does not transform data
-            // directly, but it needs to be trained on data using .Fit(), and it will output a Transformer, which can transform data.
+            var data = mlContext.Data.LoadFromEnumerable(rawData);
 
             // We define a MutualInformationFeatureSelectingEstimator that selects the top k slots in a feature 
-            // vector based on highest mutual information between that slot and a specified label. Notice that it is possible to 
-            // specify the parameter `numBins', which controls the number of bins used in the approximation of the mutual information
-            // between features and label.
+            // vector based on highest mutual information between that slot and a specified label. 
 
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
-                outputColumnName: "FeaturesSelectedGroupB", inputColumnName: "GroupB", labelColumnName: "Label", slotsInOutput: 2);
+                outputColumnName: "FeaturesSelectedGroupB", inputColumnName: "GroupB", labelColumnName: "Label",
+                slotsInOutput:2);
 
             // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
             var transformedData = pipeline.Fit(data).Transform(data);
 
             Console.WriteLine("Contents of column 'FeaturesSelectedGroupB'");
             PrintDataColumn(transformedData, "FeaturesSelectedGroupB");
-            // Note, SelectFeaturesBasedOnMutualInformation retained 2 slots (out of 3).  
-            // 7 10
-            // 2 2
-            // 3 4
-            // 2 1
-
-            // Multi column example : This pipeline uses two columns for transformation
-            pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
-                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupB"), new InputOutputColumnPair("GroupC") },
-                labelColumnName: "Label",
-                slotsInOutput:4);
-
-            transformedData = pipeline.Fit(data).Transform(data);
-
-            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true).Take(printRowCount);
-            Console.WriteLine("Contents of two columns 'GroupB' and 'GroupC'.");
-            foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
-
-            // 7 10            3 2
-            // 2 2             3 1
-            // 3 4             3 7
-            // 2 1             3 1
+            // 4 0
+            // 0 5
+            // 4 0
+            // 0 5
         }
 
         private static void PrintDataColumn(IDataView transformedData, string columnName)
         {
             var countSelectColumn = transformedData.GetColumn<float[]>(transformedData.Schema[columnName]);
 
-            int count = 0;
             foreach (var row in countSelectColumn)
             {
                 for (var i = 0; i < row.Length; i++)
                     Console.Write($"{row[i]} ");
                 Console.WriteLine();
-
-                count += 1;
-                if (count >= printRowCount)
-                    break;
             }
         }
 
-        private class TransformedData
+        public class NumericData
         {
+            public bool Label;
+
+            [VectorType(3)]
+            public float[] GroupA { get; set; }
+
+            [VectorType(3)]
             public float[] GroupB { get; set; }
 
+            [VectorType(3)]
             public float[] GroupC { get; set; }
         }
+
+        /// <summary>
+        /// Returns a few rows of numeric data.
+        /// </summary>
+        public static IEnumerable<NumericData> GetData()
+        {
+            var data = new List<NumericData>
+            {
+                new NumericData
+                {
+                    Label = true,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, 0, 6 },
+                    GroupC = new float[] { 7, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = false,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 0, 5, 7 },
+                    GroupC = new float[] { 7, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = true,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, 0, 6 },
+                    GroupC = new float[] { 7, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = false,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 0, 5, 7 },
+                    GroupC = new float[] { 7, 8, 9 },
+                }
+            };
+            return data;
+        }
     }
 }
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
new file mode 100644
index 0000000000..c33d406d18
--- /dev/null
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
@@ -0,0 +1,111 @@
+using System;
+using System.Collections.Generic;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+    public static class SelectFeaturesBasedOnMutualInformationMultiColumn
+    {
+        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();
+
+            // Get a small dataset as an IEnumerable and convert it to an IDataView.
+            var rawData = GetData();
+
+            Console.WriteLine("Contents of columns 'Label', 'GroupB' and 'GroupC'.");
+            foreach (var item in rawData)
+                Console.WriteLine("{0}\t\t{1}\t\t{2}", item.Label, string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
+            // True            4 0 6           7 8 9
+            // False           0 5 7           7 9 0
+            // True            4 0 6           7 8 9
+            // False           0 5 7           7 8 0
+
+            var data = mlContext.Data.LoadFromEnumerable(rawData);
+
+            // We define a MutualInformationFeatureSelectingEstimator that selects the top k slots in a feature 
+            // vector based on highest mutual information between that slot and a specified label. 
+
+            // Multi column example : This pipeline uses two columns for transformation.
+            var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
+                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupB"), new InputOutputColumnPair("GroupC") },
+                labelColumnName: "Label",
+                slotsInOutput: 4);
+
+            var transformedData = pipeline.Fit(data).Transform(data);
+
+            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
+            Console.WriteLine("Contents of two columns 'GroupB' and 'GroupC'.");
+            foreach (var item in convertedData)
+                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
+
+            // Here, we see SelectFeaturesBasedOnMutualInformation selected 4 slots. (3 slots from the 'GroupB' column and 1 slot from the 'GroupC' column.)
+            // 4 0 6           9
+            // 0 5 7           0
+            // 4 0 6           9
+            // 0 5 7           0
+        }
+
+        private class TransformedData
+        {
+            public float[] GroupB { get; set; }
+
+            public float[] GroupC { get; set; }
+        }
+
+        public class NumericData
+        {
+            public bool Label;
+
+            [VectorType(3)]
+            public float[] GroupA { get; set; }
+
+            [VectorType(3)]
+            public float[] GroupB { get; set; }
+
+            [VectorType(3)]
+            public float[] GroupC { get; set; }
+        }
+
+        /// <summary>
+        /// Returns a few rows of numeric data.
+        /// </summary>
+        public static IEnumerable<NumericData> GetData()
+        {
+            var data = new List<NumericData>
+            {
+                new NumericData
+                {
+                    Label = true,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, 0, 6 },
+                    GroupC = new float[] { 7, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = false,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 0, 5, 7 },
+                    GroupC = new float[] { 7, 9, 0 },
+                },
+                new NumericData
+                {
+                    Label = true,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 4, 0, 6 },
+                    GroupC = new float[] { 7, 8, 9 },
+                },
+                new NumericData
+                {
+                    Label = false,
+                    GroupA = new float[] { 1, 2, 3 },
+                    GroupB = new float[] { 0, 5, 7 },
+                    GroupC = new float[] { 7, 8, 0 },
+                }
+            };
+            return data;
+        }
+    }
+}
diff --git a/src/Microsoft.ML.Transforms/FeatureSelectionCatalog.cs b/src/Microsoft.ML.Transforms/FeatureSelectionCatalog.cs
index 0cdea6b269..c115836f22 100644
--- a/src/Microsoft.ML.Transforms/FeatureSelectionCatalog.cs
+++ b/src/Microsoft.ML.Transforms/FeatureSelectionCatalog.cs
@@ -24,7 +24,7 @@ public static class FeatureSelectionCatalog
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        /// [!code-csharp[SelectFeaturesBasedOnMutualInformation](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/SelectFeaturesBasedOnMutualInformation.cs)]
+        /// [!code-csharp[SelectFeaturesBasedOnMutualInformation](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs)]
         /// ]]>
         /// </format>
         /// </example>
@@ -44,7 +44,7 @@ public static MutualInformationFeatureSelectingEstimator SelectFeaturesBasedOnMu
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        /// [!code-csharp[SelectFeaturesBasedOnMutualInformation](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/SelectFeaturesBasedOnMutualInformation.cs)]
+        /// [!code-csharp[SelectFeaturesBasedOnMutualInformation](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs)]
         /// ]]>
         /// </format>
         /// </example>
@@ -76,7 +76,7 @@ internal static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this T
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        /// [!code-csharp[SelectFeaturesBasedOnCount](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/SelectFeaturesBasedOnCount.cs)]
+        /// [!code-csharp[SelectFeaturesBasedOnCount](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs)]
         /// ]]>
         /// </format>
         /// </example>
@@ -93,7 +93,7 @@ public static CountFeatureSelectingEstimator SelectFeaturesBasedOnCount(this Tra
         /// <example>
         /// <format type="text/markdown">
         /// <![CDATA[
-        /// [!code-csharp[SelectFeaturesBasedOnCount](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/SelectFeaturesBasedOnCount.cs)]
+        /// [!code-csharp[SelectFeaturesBasedOnCount](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs)]
         /// ]]>
         /// </format>
         /// </example>

From c4533bca2f7955a90b5fe15925a1c3e37bc47844 Mon Sep 17 00:00:00 2001
From: Abhishek Goswami <abgoswam@gmail.com>
Date: Thu, 4 Apr 2019 18:44:14 +0000
Subject: [PATCH 3/6] fix review comments

---
 .../SelectFeaturesBasedOnCount.cs             | 100 +++++++++--------
 .../SelectFeaturesBasedOnCountMultiColumn.cs  | 106 ++++++------------
 .../SelectFeaturesBasedOnMutualInformation.cs |  35 ++----
 ...uresBasedOnMutualInformationMultiColumn.cs |  42 +++----
 4 files changed, 117 insertions(+), 166 deletions(-)

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
index a1cad6af94..43db2df365 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
@@ -1,8 +1,9 @@
 using System;
 using System.Collections.Generic;
+using Microsoft.ML;
 using Microsoft.ML.Data;
 
-namespace Microsoft.ML.Samples.Dynamic
+namespace Samples.Dynamic
 {
     public static class SelectFeaturesBasedOnCount
     {
@@ -16,92 +17,93 @@ public static void Example()
             var rawData = GetData();
             var data = mlContext.Data.LoadFromEnumerable(rawData);
 
-            Console.WriteLine("Contents of column 'GroupB'");
-            PrintDataColumn(data, "GroupB");
-            // 4       NaN     6
-            // 4       5       6
-            // 4       5       6
-            // 4       NaN     NaN
+            var convertedData = mlContext.Data.CreateEnumerable<InputData>(data, true);
 
-            // Second, we define the transformations that we apply on the data. Remember that an Estimator does not transform data
-            // directly, but it needs to be trained on data using .Fit(), and it will output a Transformer, which can transform data.
+            Console.WriteLine("Contents of two columns 'GroupA' and 'Info'.");
+            foreach (var item in convertedData)
+                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.GroupA), string.Join("\t", item.Info));
+            // 4       NaN     6                       A       WA   Male
+            // 4       5       6                       A            Female
+            // 4       5       6                       A       NY
+            // 4       NaN     NaN                     A            Male
 
-            // We will use the SelectFeaturesBasedOnCount transform estimator, to retain only those slots which have 
-            // at least 'count' non-default values per slot.
+            // We will use the SelectFeaturesBasedOnCount to retain only those slots which have at least 'count' non-default values per slot.
+
+            // Usage on numeric column.
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                outputColumnName: "FeaturesSelectedGroupB", inputColumnName: "GroupB", count: 3);
+                outputColumnName: "FeaturesSelectedGroupA", inputColumnName: "GroupA", count: 3);
 
             // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
             var transformedData = pipeline.Fit(data).Transform(data);
 
-            Console.WriteLine("Contents of column 'FeaturesSelectedGroupB'");
-            PrintDataColumn(transformedData, "FeaturesSelectedGroupB");
+            Console.WriteLine("Contents of column 'FeaturesSelectedGroupA'");
+            var featuresSelectedGroupA = transformedData.GetColumn<float[]>(transformedData.Schema["FeaturesSelectedGroupA"]);
+            foreach (var row in featuresSelectedGroupA)
+            {
+                for (var i = 0; i < row.Length; i++)
+                    Console.Write($"{row[i]}\t");
+                Console.WriteLine();
+            }
             // 4       6
             // 4       6
             // 4       6
             // 4       NaN
-        }
 
-        private static void PrintDataColumn(IDataView transformedData, string columnName)
-        {
-            var countSelectColumn = transformedData.GetColumn<float[]>(transformedData.Schema[columnName]);
+            // Usage on text column.
+            pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
+                outputColumnName: "FeaturesSelectedInfo", inputColumnName: "Info", count: 3);
+
+            transformedData = pipeline.Fit(data).Transform(data);
 
-            foreach (var row in countSelectColumn)
+            Console.WriteLine("Contents of column 'FeaturesSelectedInfo'");
+            var featuresSelectedInfo = transformedData.GetColumn<string[]>(transformedData.Schema["FeaturesSelectedInfo"]);
+            foreach (var row in featuresSelectedInfo)
             {
                 for (var i = 0; i < row.Length; i++)
                     Console.Write($"{row[i]}\t");
                 Console.WriteLine();
             }
+            // A       Male
+            // A       Female
+            // A
+            // A       Male
         }
 
-        public class NumericData
+        public class InputData
         {
-            public bool Label;
-
             [VectorType(3)]
             public float[] GroupA { get; set; }
 
             [VectorType(3)]
-            public float[] GroupB { get; set; }
-
-            [VectorType(3)]
-            public float[] GroupC { get; set; }
+            public string[] Info { get; set; }
         }
 
         /// <summary>
-        /// Returns a few rows of numeric data.
+        /// Return a few rows of data.
         /// </summary>
-        public static IEnumerable<NumericData> GetData()
+        public static IEnumerable<InputData> GetData()
         {
-            var data = new List<NumericData>
+            var data = new List<InputData>
             {
-                new NumericData
+                new InputData
                 {
-                    Label = true,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, float.NaN, 6 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, float.NaN, 6 },
+                    Info = new string[] { "A", "WA", "Male"}
                 },
-                new NumericData
+                new InputData
                 {
-                    Label = false,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, 5, 6 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, 5, 6 },
+                    Info = new string[] { "A", "", "Female"}
                 },
-                new NumericData
+                new InputData
                 {
-                    Label = true,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, 5, 6 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, 5, 6 },
+                    Info = new string[] { "A", "NY", null}
                 },
-                new NumericData
+                new InputData
                 {
-                    Label = false,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, float.NaN, float.NaN },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, float.NaN, float.NaN },
+                    Info = new string[] { "A", null, "Male"}
                 }
             };
             return data;
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
index 0b73a6d0fd..871fe9531e 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
@@ -1,8 +1,9 @@
 using System;
 using System.Collections.Generic;
+using Microsoft.ML;
 using Microsoft.ML.Data;
 
-namespace Microsoft.ML.Samples.Dynamic
+namespace Samples.Dynamic
 {
     public static class SelectFeaturesBasedOnCountMultiColumn
     {
@@ -14,112 +15,79 @@ public static void Example()
 
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
-            var data = mlContext.Data.LoadFromEnumerable(rawData);
-
-            Console.WriteLine("Contents of column 'GroupB'");
-            PrintDataColumn(data, "GroupB");
-            // 4       NaN     6
-            // 4       5       6
-            // 4       5       6
-            // 4       NaN     NaN
 
-            Console.WriteLine("Contents of column 'GroupC'");
-            PrintDataColumn(data, "GroupC");
-            // NaN     8       9
-            // NaN     8       9
-            // NaN     8       9
-            // 7       8       9
+            Console.WriteLine("Contents of two columns 'GroupA' and 'Info'.");
+            foreach (var item in rawData)
+                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.GroupA), string.Join("\t", item.Info));
+            // 4       NaN     6                       A   WA      Male
+            // 4       5       6                       A           Female
+            // 4       5       6                       A   NY
+            // 4       NaN     NaN                     A           Male
 
-            // Second, we define the transformations that we apply on the data. Remember that an Estimator does not transform data
-            // directly, but it needs to be trained on data using .Fit(), and it will output a Transformer, which can transform data.
+            var data = mlContext.Data.LoadFromEnumerable(rawData);
 
             // We will use the SelectFeaturesBasedOnCount transform estimator, to retain only those slots which have 
             // at least 'count' non-default values per slot.
 
-            // Multi column example : This pipeline uses two columns for transformation
+            // Multi column example. This pipeline transform two columns using the provided parameters.
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupB"), new InputOutputColumnPair("GroupC") },
+                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupA"), new InputOutputColumnPair("Info") },
                 count: 3);
 
             var transformedData = pipeline.Fit(data).Transform(data);
 
             var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
-            Console.WriteLine("Contents of two columns 'GroupB' and 'GroupC'.");
+            Console.WriteLine("Contents of two columns 'GroupA' and 'Info'.");
             foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
-            // 4 6             8 9
-            // 4 6             8 9
-            // 4 6             8 9
-            // 4 NaN           8 9
-        }
-
-        private static void PrintDataColumn(IDataView transformedData, string columnName)
-        {
-            var countSelectColumn = transformedData.GetColumn<float[]>(transformedData.Schema[columnName]);
-
-            foreach (var row in countSelectColumn)
-            {
-                for (var i = 0; i < row.Length; i++)
-                    Console.Write($"{row[i]}\t");
-                Console.WriteLine();
-            }
+                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.GroupA), string.Join("\t", item.Info));
+            // 4       6                       A   Male
+            // 4       6                       A   Female
+            // 4       6                       A
+            // 4       NaN                     A   Male
         }
 
         private class TransformedData
         {
-            public float[] GroupB { get; set; }
+            public float[] GroupA { get; set; }
 
-            public float[] GroupC { get; set; }
+            public string[] Info { get; set; }
         }
 
-        public class NumericData
+        public class InputData
         {
-            public bool Label;
-
             [VectorType(3)]
             public float[] GroupA { get; set; }
 
             [VectorType(3)]
-            public float[] GroupB { get; set; }
-
-            [VectorType(3)]
-            public float[] GroupC { get; set; }
+            public string[] Info { get; set; }
         }
 
         /// <summary>
-        /// Returns a few rows of numeric data.
+        /// Returns a few rows of data.
         /// </summary>
-        public static IEnumerable<NumericData> GetData()
+        public static IEnumerable<InputData> GetData()
         {
-            var data = new List<NumericData>
+            var data = new List<InputData>
             {
-                new NumericData
+                new InputData
                 {
-                    Label = true,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, float.NaN, 6 },
-                    GroupC = new float[] { float.NaN, 8, 9 },
+                    GroupA = new float[] { 4, float.NaN, 6 },
+                    Info = new string[] { "A", "WA", "Male"}
                 },
-                new NumericData
+                new InputData
                 {
-                    Label = false,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, 5, 6 },
-                    GroupC = new float[] { float.NaN, 8, 9 },
+                    GroupA = new float[] { 4, 5, 6 },
+                    Info = new string[] { "A", "", "Female"}
                 },
-                new NumericData
+                new InputData
                 {
-                    Label = true,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, 5, 6 },
-                    GroupC = new float[] { float.NaN, 8, 9 },
+                    GroupA = new float[] { 4, 5, 6 },
+                    Info = new string[] { "A", "NY", null}
                 },
-                new NumericData
+                new InputData
                 {
-                    Label = false,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, float.NaN, float.NaN },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, float.NaN, float.NaN },
+                    Info = new string[] { "A", null, "Male"}
                 }
             };
             return data;
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
index a4b1f4d6b4..9967c94142 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
@@ -1,8 +1,9 @@
 using System;
 using System.Collections.Generic;
+using Microsoft.ML;
 using Microsoft.ML.Data;
 
-namespace Microsoft.ML.Samples.Dynamic
+namespace Samples.Dynamic
 {
     public static class SelectFeaturesBasedOnMutualInformation
     {
@@ -15,9 +16,9 @@ public static void Example()
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
 
-            Console.WriteLine("Contents of two columns 'Label' and 'GroupB'.");
+            Console.WriteLine("Contents of two columns 'Label' and 'GroupA'.");
             foreach (var item in rawData)
-                Console.WriteLine("{0}\t\t{1}", item.Label, string.Join(" ", item.GroupB));
+                Console.WriteLine("{0}\t\t{1}", item.Label, string.Join(" ", item.GroupA));
             // True            4 0 6
             // False           0 5 7
             // True            4 0 6
@@ -29,14 +30,14 @@ public static void Example()
             // vector based on highest mutual information between that slot and a specified label. 
 
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
-                outputColumnName: "FeaturesSelectedGroupB", inputColumnName: "GroupB", labelColumnName: "Label",
+                outputColumnName: "FeaturesSelectedGroupA", inputColumnName: "GroupA", labelColumnName: "Label",
                 slotsInOutput:2);
 
             // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
             var transformedData = pipeline.Fit(data).Transform(data);
 
-            Console.WriteLine("Contents of column 'FeaturesSelectedGroupB'");
-            PrintDataColumn(transformedData, "FeaturesSelectedGroupB");
+            Console.WriteLine("Contents of column 'FeaturesSelectedGroupA'");
+            PrintDataColumn(transformedData, "FeaturesSelectedGroupA");
             // 4 0
             // 0 5
             // 4 0
@@ -61,12 +62,6 @@ public class NumericData
 
             [VectorType(3)]
             public float[] GroupA { get; set; }
-
-            [VectorType(3)]
-            public float[] GroupB { get; set; }
-
-            [VectorType(3)]
-            public float[] GroupC { get; set; }
         }
 
         /// <summary>
@@ -79,30 +74,22 @@ public static IEnumerable<NumericData> GetData()
                 new NumericData
                 {
                     Label = true,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, 0, 6 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, 0, 6 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 0, 5, 7 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 0, 5, 7 },
                 },
                 new NumericData
                 {
                     Label = true,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, 0, 6 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, 0, 6 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 0, 5, 7 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 0, 5, 7 },
                 }
             };
             return data;
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
index c33d406d18..71ac19b207 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
@@ -1,8 +1,9 @@
 using System;
 using System.Collections.Generic;
+using Microsoft.ML;
 using Microsoft.ML.Data;
 
-namespace Microsoft.ML.Samples.Dynamic
+namespace Samples.Dynamic
 {
     public static class SelectFeaturesBasedOnMutualInformationMultiColumn
     {
@@ -15,9 +16,9 @@ public static void Example()
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
 
-            Console.WriteLine("Contents of columns 'Label', 'GroupB' and 'GroupC'.");
+            Console.WriteLine("Contents of columns 'Label', 'GroupA' and 'GroupB'.");
             foreach (var item in rawData)
-                Console.WriteLine("{0}\t\t{1}\t\t{2}", item.Label, string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
+                Console.WriteLine("{0}\t\t{1}\t\t{2}", item.Label, string.Join(" ", item.GroupA), string.Join(" ", item.GroupB));
             // True            4 0 6           7 8 9
             // False           0 5 7           7 9 0
             // True            4 0 6           7 8 9
@@ -28,18 +29,18 @@ public static void Example()
             // We define a MutualInformationFeatureSelectingEstimator that selects the top k slots in a feature 
             // vector based on highest mutual information between that slot and a specified label. 
 
-            // Multi column example : This pipeline uses two columns for transformation.
+            // Multi column example : This pipeline transform two columns using the provided parameters.
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
-                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupB"), new InputOutputColumnPair("GroupC") },
+                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupA"), new InputOutputColumnPair("GroupB") },
                 labelColumnName: "Label",
                 slotsInOutput: 4);
 
             var transformedData = pipeline.Fit(data).Transform(data);
 
             var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
-            Console.WriteLine("Contents of two columns 'GroupB' and 'GroupC'.");
+            Console.WriteLine("Contents of two columns 'GroupA' and 'GroupB'.");
             foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupB), string.Join(" ", item.GroupC));
+                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupA), string.Join(" ", item.GroupB));
 
             // Here, we see SelectFeaturesBasedOnMutualInformation selected 4 slots. (3 slots from the 'GroupB' column and 1 slot from the 'GroupC' column.)
             // 4 0 6           9
@@ -50,9 +51,9 @@ public static void Example()
 
         private class TransformedData
         {
-            public float[] GroupB { get; set; }
+            public float[] GroupA { get; set; }
 
-            public float[] GroupC { get; set; }
+            public float[] GroupB { get; set; }
         }
 
         public class NumericData
@@ -64,9 +65,6 @@ public class NumericData
 
             [VectorType(3)]
             public float[] GroupB { get; set; }
-
-            [VectorType(3)]
-            public float[] GroupC { get; set; }
         }
 
         /// <summary>
@@ -79,30 +77,26 @@ public static IEnumerable<NumericData> GetData()
                 new NumericData
                 {
                     Label = true,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, 0, 6 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, 0, 6 },
+                    GroupB = new float[] { 7, 8, 9 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 0, 5, 7 },
-                    GroupC = new float[] { 7, 9, 0 },
+                    GroupA = new float[] { 0, 5, 7 },
+                    GroupB = new float[] { 7, 9, 0 },
                 },
                 new NumericData
                 {
                     Label = true,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 4, 0, 6 },
-                    GroupC = new float[] { 7, 8, 9 },
+                    GroupA = new float[] { 4, 0, 6 },
+                    GroupB = new float[] { 7, 8, 9 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    GroupA = new float[] { 1, 2, 3 },
-                    GroupB = new float[] { 0, 5, 7 },
-                    GroupC = new float[] { 7, 8, 0 },
+                    GroupA = new float[] { 0, 5, 7 },
+                    GroupB = new float[] { 7, 8, 0 },
                 }
             };
             return data;

From d44c6a2833c1c030185ff2ffd4196926f8e08d2c Mon Sep 17 00:00:00 2001
From: Abhishek Goswami <abgoswam@gmail.com>
Date: Thu, 4 Apr 2019 20:51:38 +0000
Subject: [PATCH 4/6] review comments

---
 .../SelectFeaturesBasedOnCount.cs             | 36 +++++++++----------
 .../SelectFeaturesBasedOnCountMultiColumn.cs  | 34 +++++++++---------
 .../SelectFeaturesBasedOnMutualInformation.cs | 20 +++++------
 ...uresBasedOnMutualInformationMultiColumn.cs | 36 +++++++++----------
 4 files changed, 63 insertions(+), 63 deletions(-)

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
index 43db2df365..ea40853c54 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
@@ -19,9 +19,9 @@ public static void Example()
 
             var convertedData = mlContext.Data.CreateEnumerable<InputData>(data, true);
 
-            Console.WriteLine("Contents of two columns 'GroupA' and 'Info'.");
+            Console.WriteLine("Contents of two columns 'NumericVector' and 'StringVector'.");
             foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.GroupA), string.Join("\t", item.Info));
+                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.NumericVector), string.Join("\t", item.StringVector));
             // 4       NaN     6                       A       WA   Male
             // 4       5       6                       A            Female
             // 4       5       6                       A       NY
@@ -31,13 +31,13 @@ public static void Example()
 
             // Usage on numeric column.
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                outputColumnName: "FeaturesSelectedGroupA", inputColumnName: "GroupA", count: 3);
+                outputColumnName: "NumericVector", count: 3);
 
             // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
             var transformedData = pipeline.Fit(data).Transform(data);
 
-            Console.WriteLine("Contents of column 'FeaturesSelectedGroupA'");
-            var featuresSelectedGroupA = transformedData.GetColumn<float[]>(transformedData.Schema["FeaturesSelectedGroupA"]);
+            Console.WriteLine("Contents of column 'NumericVector'");
+            var featuresSelectedGroupA = transformedData.GetColumn<float[]>(transformedData.Schema["NumericVector"]);
             foreach (var row in featuresSelectedGroupA)
             {
                 for (var i = 0; i < row.Length; i++)
@@ -51,12 +51,12 @@ public static void Example()
 
             // Usage on text column.
             pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                outputColumnName: "FeaturesSelectedInfo", inputColumnName: "Info", count: 3);
+                outputColumnName: "StringVector", count: 3);
 
             transformedData = pipeline.Fit(data).Transform(data);
 
-            Console.WriteLine("Contents of column 'FeaturesSelectedInfo'");
-            var featuresSelectedInfo = transformedData.GetColumn<string[]>(transformedData.Schema["FeaturesSelectedInfo"]);
+            Console.WriteLine("Contents of column 'StringVector'");
+            var featuresSelectedInfo = transformedData.GetColumn<string[]>(transformedData.Schema["StringVector"]);
             foreach (var row in featuresSelectedInfo)
             {
                 for (var i = 0; i < row.Length; i++)
@@ -72,10 +72,10 @@ public static void Example()
         public class InputData
         {
             [VectorType(3)]
-            public float[] GroupA { get; set; }
+            public float[] NumericVector { get; set; }
 
             [VectorType(3)]
-            public string[] Info { get; set; }
+            public string[] StringVector { get; set; }
         }
 
         /// <summary>
@@ -87,23 +87,23 @@ public static IEnumerable<InputData> GetData()
             {
                 new InputData
                 {
-                    GroupA = new float[] { 4, float.NaN, 6 },
-                    Info = new string[] { "A", "WA", "Male"}
+                    NumericVector = new float[] { 4, float.NaN, 6 },
+                    StringVector = new string[] { "A", "WA", "Male"}
                 },
                 new InputData
                 {
-                    GroupA = new float[] { 4, 5, 6 },
-                    Info = new string[] { "A", "", "Female"}
+                    NumericVector = new float[] { 4, 5, 6 },
+                    StringVector = new string[] { "A", "", "Female"}
                 },
                 new InputData
                 {
-                    GroupA = new float[] { 4, 5, 6 },
-                    Info = new string[] { "A", "NY", null}
+                    NumericVector = new float[] { 4, 5, 6 },
+                    StringVector = new string[] { "A", "NY", null}
                 },
                 new InputData
                 {
-                    GroupA = new float[] { 4, float.NaN, float.NaN },
-                    Info = new string[] { "A", null, "Male"}
+                    NumericVector = new float[] { 4, float.NaN, float.NaN },
+                    StringVector = new string[] { "A", null, "Male"}
                 }
             };
             return data;
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
index 871fe9531e..a1e217b089 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
@@ -16,9 +16,9 @@ public static void Example()
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
 
-            Console.WriteLine("Contents of two columns 'GroupA' and 'Info'.");
+            Console.WriteLine("Contents of two columns 'NumericVector' and 'StringVector'.");
             foreach (var item in rawData)
-                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.GroupA), string.Join("\t", item.Info));
+                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.NumericVector), string.Join("\t", item.StringVector));
             // 4       NaN     6                       A   WA      Male
             // 4       5       6                       A           Female
             // 4       5       6                       A   NY
@@ -31,15 +31,15 @@ public static void Example()
 
             // Multi column example. This pipeline transform two columns using the provided parameters.
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupA"), new InputOutputColumnPair("Info") },
+                new InputOutputColumnPair[] { new InputOutputColumnPair("NumericVector"), new InputOutputColumnPair("StringVector") },
                 count: 3);
 
             var transformedData = pipeline.Fit(data).Transform(data);
 
             var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
-            Console.WriteLine("Contents of two columns 'GroupA' and 'Info'.");
+            Console.WriteLine("Contents of two columns 'NumericVector' and 'StringVector'.");
             foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.GroupA), string.Join("\t", item.Info));
+                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.NumericVector), string.Join("\t", item.StringVector));
             // 4       6                       A   Male
             // 4       6                       A   Female
             // 4       6                       A
@@ -48,18 +48,18 @@ public static void Example()
 
         private class TransformedData
         {
-            public float[] GroupA { get; set; }
+            public float[] NumericVector { get; set; }
 
-            public string[] Info { get; set; }
+            public string[] StringVector { get; set; }
         }
 
         public class InputData
         {
             [VectorType(3)]
-            public float[] GroupA { get; set; }
+            public float[] NumericVector { get; set; }
 
             [VectorType(3)]
-            public string[] Info { get; set; }
+            public string[] StringVector { get; set; }
         }
 
         /// <summary>
@@ -71,23 +71,23 @@ public static IEnumerable<InputData> GetData()
             {
                 new InputData
                 {
-                    GroupA = new float[] { 4, float.NaN, 6 },
-                    Info = new string[] { "A", "WA", "Male"}
+                    NumericVector = new float[] { 4, float.NaN, 6 },
+                    StringVector = new string[] { "A", "WA", "Male"}
                 },
                 new InputData
                 {
-                    GroupA = new float[] { 4, 5, 6 },
-                    Info = new string[] { "A", "", "Female"}
+                    NumericVector = new float[] { 4, 5, 6 },
+                    StringVector = new string[] { "A", "", "Female"}
                 },
                 new InputData
                 {
-                    GroupA = new float[] { 4, 5, 6 },
-                    Info = new string[] { "A", "NY", null}
+                    NumericVector = new float[] { 4, 5, 6 },
+                    StringVector = new string[] { "A", "NY", null}
                 },
                 new InputData
                 {
-                    GroupA = new float[] { 4, float.NaN, float.NaN },
-                    Info = new string[] { "A", null, "Male"}
+                    NumericVector = new float[] { 4, float.NaN, float.NaN },
+                    StringVector = new string[] { "A", null, "Male"}
                 }
             };
             return data;
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
index 9967c94142..7937eed0a5 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
@@ -16,9 +16,9 @@ public static void Example()
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
 
-            Console.WriteLine("Contents of two columns 'Label' and 'GroupA'.");
+            Console.WriteLine("Contents of two columns 'Label' and 'NumericVector'.");
             foreach (var item in rawData)
-                Console.WriteLine("{0}\t\t{1}", item.Label, string.Join(" ", item.GroupA));
+                Console.WriteLine("{0}\t\t{1}", item.Label, string.Join(" ", item.NumericVector));
             // True            4 0 6
             // False           0 5 7
             // True            4 0 6
@@ -30,14 +30,14 @@ public static void Example()
             // vector based on highest mutual information between that slot and a specified label. 
 
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
-                outputColumnName: "FeaturesSelectedGroupA", inputColumnName: "GroupA", labelColumnName: "Label",
+                outputColumnName: "NumericVector", labelColumnName: "Label",
                 slotsInOutput:2);
 
             // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
             var transformedData = pipeline.Fit(data).Transform(data);
 
-            Console.WriteLine("Contents of column 'FeaturesSelectedGroupA'");
-            PrintDataColumn(transformedData, "FeaturesSelectedGroupA");
+            Console.WriteLine("Contents of column 'NumericVector'");
+            PrintDataColumn(transformedData, "NumericVector");
             // 4 0
             // 0 5
             // 4 0
@@ -61,7 +61,7 @@ public class NumericData
             public bool Label;
 
             [VectorType(3)]
-            public float[] GroupA { get; set; }
+            public float[] NumericVector { get; set; }
         }
 
         /// <summary>
@@ -74,22 +74,22 @@ public static IEnumerable<NumericData> GetData()
                 new NumericData
                 {
                     Label = true,
-                    GroupA = new float[] { 4, 0, 6 },
+                    NumericVector = new float[] { 4, 6, 0 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    GroupA = new float[] { 0, 5, 7 },
+                    NumericVector = new float[] { 0, 7, 5 },
                 },
                 new NumericData
                 {
                     Label = true,
-                    GroupA = new float[] { 4, 0, 6 },
+                    NumericVector = new float[] { 4, 6, 0 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    GroupA = new float[] { 0, 5, 7 },
+                    NumericVector = new float[] { 0, 7, 5 },
                 }
             };
             return data;
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
index 71ac19b207..0679cec9b7 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
@@ -16,9 +16,9 @@ public static void Example()
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
 
-            Console.WriteLine("Contents of columns 'Label', 'GroupA' and 'GroupB'.");
+            Console.WriteLine("Contents of columns 'Label', 'NumericVectorA' and 'NumericVectorB'.");
             foreach (var item in rawData)
-                Console.WriteLine("{0}\t\t{1}\t\t{2}", item.Label, string.Join(" ", item.GroupA), string.Join(" ", item.GroupB));
+                Console.WriteLine("{0}\t\t{1}\t\t{2}", item.Label, string.Join(" ", item.NumericVectorA), string.Join(" ", item.NumericVectorB));
             // True            4 0 6           7 8 9
             // False           0 5 7           7 9 0
             // True            4 0 6           7 8 9
@@ -31,18 +31,18 @@ public static void Example()
 
             // Multi column example : This pipeline transform two columns using the provided parameters.
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
-                new InputOutputColumnPair[] { new InputOutputColumnPair("GroupA"), new InputOutputColumnPair("GroupB") },
+                new InputOutputColumnPair[] { new InputOutputColumnPair("NumericVectorA"), new InputOutputColumnPair("NumericVectorB") },
                 labelColumnName: "Label",
                 slotsInOutput: 4);
 
             var transformedData = pipeline.Fit(data).Transform(data);
 
             var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
-            Console.WriteLine("Contents of two columns 'GroupA' and 'GroupB'.");
+            Console.WriteLine("Contents of two columns 'NumericVectorA' and 'NumericVectorB'.");
             foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.GroupA), string.Join(" ", item.GroupB));
+                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.NumericVectorA), string.Join(" ", item.NumericVectorB));
 
-            // Here, we see SelectFeaturesBasedOnMutualInformation selected 4 slots. (3 slots from the 'GroupB' column and 1 slot from the 'GroupC' column.)
+            // Here, we see SelectFeaturesBasedOnMutualInformation selected 4 slots.
             // 4 0 6           9
             // 0 5 7           0
             // 4 0 6           9
@@ -51,9 +51,9 @@ public static void Example()
 
         private class TransformedData
         {
-            public float[] GroupA { get; set; }
+            public float[] NumericVectorA { get; set; }
 
-            public float[] GroupB { get; set; }
+            public float[] NumericVectorB { get; set; }
         }
 
         public class NumericData
@@ -61,10 +61,10 @@ public class NumericData
             public bool Label;
 
             [VectorType(3)]
-            public float[] GroupA { get; set; }
+            public float[] NumericVectorA { get; set; }
 
             [VectorType(3)]
-            public float[] GroupB { get; set; }
+            public float[] NumericVectorB { get; set; }
         }
 
         /// <summary>
@@ -77,26 +77,26 @@ public static IEnumerable<NumericData> GetData()
                 new NumericData
                 {
                     Label = true,
-                    GroupA = new float[] { 4, 0, 6 },
-                    GroupB = new float[] { 7, 8, 9 },
+                    NumericVectorA = new float[] { 4, 0, 6 },
+                    NumericVectorB = new float[] { 7, 8, 9 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    GroupA = new float[] { 0, 5, 7 },
-                    GroupB = new float[] { 7, 9, 0 },
+                    NumericVectorA = new float[] { 0, 5, 7 },
+                    NumericVectorB = new float[] { 7, 9, 0 },
                 },
                 new NumericData
                 {
                     Label = true,
-                    GroupA = new float[] { 4, 0, 6 },
-                    GroupB = new float[] { 7, 8, 9 },
+                    NumericVectorA = new float[] { 4, 0, 6 },
+                    NumericVectorB = new float[] { 7, 8, 9 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    GroupA = new float[] { 0, 5, 7 },
-                    GroupB = new float[] { 7, 8, 0 },
+                    NumericVectorA = new float[] { 0, 5, 7 },
+                    NumericVectorB = new float[] { 7, 8, 0 },
                 }
             };
             return data;

From 51b85078e23932da8b953057486249dcd5e704e9 Mon Sep 17 00:00:00 2001
From: Abhishek Goswami <abgoswam@gmail.com>
Date: Thu, 4 Apr 2019 23:32:39 +0000
Subject: [PATCH 5/6] take care of review comments

---
 .../SelectFeaturesBasedOnCount.cs             | 72 ++++++++-----------
 .../SelectFeaturesBasedOnCountMultiColumn.cs  | 31 ++++----
 .../SelectFeaturesBasedOnMutualInformation.cs | 44 ++++++------
 ...uresBasedOnMutualInformationMultiColumn.cs | 31 ++++----
 4 files changed, 89 insertions(+), 89 deletions(-)

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
index ea40853c54..8b27d23e0d 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCount.cs
@@ -15,58 +15,46 @@ public static void Example()
 
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
-            var data = mlContext.Data.LoadFromEnumerable(rawData);
 
-            var convertedData = mlContext.Data.CreateEnumerable<InputData>(data, true);
+            // Printing the columns of the input data. 
+            Console.WriteLine($"NumericVector             StringVector");
+            foreach (var item in rawData)
+                Console.WriteLine("{0,-25} {1,-25}", string.Join(",", item.NumericVector), string.Join(",", item.StringVector));
+            
+            // NumericVector             StringVector
+            // 4,NaN,6                   A,WA,Male
+            // 4,5,6                     A,,Female
+            // 4,5,6                     A,NY,
+            // 4,NaN,NaN                 A,,Male
 
-            Console.WriteLine("Contents of two columns 'NumericVector' and 'StringVector'.");
-            foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.NumericVector), string.Join("\t", item.StringVector));
-            // 4       NaN     6                       A       WA   Male
-            // 4       5       6                       A            Female
-            // 4       5       6                       A       NY
-            // 4       NaN     NaN                     A            Male
+            var data = mlContext.Data.LoadFromEnumerable(rawData);
 
             // We will use the SelectFeaturesBasedOnCount to retain only those slots which have at least 'count' non-default values per slot.
+            var pipeline = 
+                mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(outputColumnName: "NumericVector", count: 3) // Usage on numeric column.
+                .Append(mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(outputColumnName: "StringVector", count: 3)); // Usage on text column.
 
-            // Usage on numeric column.
-            var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                outputColumnName: "NumericVector", count: 3);
-
-            // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
             var transformedData = pipeline.Fit(data).Transform(data);
 
-            Console.WriteLine("Contents of column 'NumericVector'");
-            var featuresSelectedGroupA = transformedData.GetColumn<float[]>(transformedData.Schema["NumericVector"]);
-            foreach (var row in featuresSelectedGroupA)
-            {
-                for (var i = 0; i < row.Length; i++)
-                    Console.Write($"{row[i]}\t");
-                Console.WriteLine();
-            }
-            // 4       6
-            // 4       6
-            // 4       6
-            // 4       NaN
+            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
+
+            // Printing the columns of the transformed data. 
+            Console.WriteLine($"NumericVector             StringVector");
+            foreach (var item in convertedData)
+                Console.WriteLine("{0,-25} {1,-25}", string.Join(",", item.NumericVector), string.Join(",", item.StringVector));
 
-            // Usage on text column.
-            pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnCount(
-                outputColumnName: "StringVector", count: 3);
+            // NumericVector             StringVector
+            // 4,6                       A,Male
+            // 4,6                       A,Female
+            // 4,6                       A,
+            // 4,NaN                     A,Male
+        }
 
-            transformedData = pipeline.Fit(data).Transform(data);
+        public class TransformedData
+        {
+            public float[] NumericVector { get; set; }
 
-            Console.WriteLine("Contents of column 'StringVector'");
-            var featuresSelectedInfo = transformedData.GetColumn<string[]>(transformedData.Schema["StringVector"]);
-            foreach (var row in featuresSelectedInfo)
-            {
-                for (var i = 0; i < row.Length; i++)
-                    Console.Write($"{row[i]}\t");
-                Console.WriteLine();
-            }
-            // A       Male
-            // A       Female
-            // A
-            // A       Male
+            public string[] StringVector { get; set; }
         }
 
         public class InputData
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
index a1e217b089..ae45fa375e 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnCountMultiColumn.cs
@@ -16,13 +16,16 @@ public static void Example()
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
 
-            Console.WriteLine("Contents of two columns 'NumericVector' and 'StringVector'.");
+            // Printing the columns of the input data. 
+            Console.WriteLine($"NumericVector             StringVector");
             foreach (var item in rawData)
-                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.NumericVector), string.Join("\t", item.StringVector));
-            // 4       NaN     6                       A   WA      Male
-            // 4       5       6                       A           Female
-            // 4       5       6                       A   NY
-            // 4       NaN     NaN                     A           Male
+                Console.WriteLine("{0,-25} {1,-25}", string.Join(",", item.NumericVector), string.Join(",", item.StringVector));
+
+            // NumericVector             StringVector
+            // 4,NaN,6                   A,WA,Male
+            // 4,5,6                     A,,Female
+            // 4,5,6                     A,NY,
+            // 4,NaN,NaN                 A,,Male
 
             var data = mlContext.Data.LoadFromEnumerable(rawData);
 
@@ -37,13 +40,17 @@ public static void Example()
             var transformedData = pipeline.Fit(data).Transform(data);
 
             var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
-            Console.WriteLine("Contents of two columns 'NumericVector' and 'StringVector'.");
+
+            // Printing the columns of the transformed data. 
+            Console.WriteLine($"NumericVector             StringVector");
             foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t\t{1}", string.Join("\t", item.NumericVector), string.Join("\t", item.StringVector));
-            // 4       6                       A   Male
-            // 4       6                       A   Female
-            // 4       6                       A
-            // 4       NaN                     A   Male
+                Console.WriteLine("{0,-25} {1,-25}", string.Join(",", item.NumericVector), string.Join(",", item.StringVector));
+
+            // NumericVector             StringVector
+            // 4,6                       A,Male
+            // 4,6                       A,Female
+            // 4,6                       A,
+            // 4,NaN                     A,Male
         }
 
         private class TransformedData
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
index 7937eed0a5..0b9232e5e6 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
@@ -16,9 +16,11 @@ public static void Example()
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
 
-            Console.WriteLine("Contents of two columns 'Label' and 'NumericVector'.");
+            // Printing the columns of the input data. 
+            Console.WriteLine($"Label             NumericVector");
             foreach (var item in rawData)
-                Console.WriteLine("{0}\t\t{1}", item.Label, string.Join(" ", item.NumericVector));
+                Console.WriteLine("{0,-25} {1,-25}", item.Label, string.Join(",", item.NumericVector));
+
             // True            4 0 6
             // False           0 5 7
             // True            4 0 6
@@ -28,7 +30,6 @@ public static void Example()
 
             // We define a MutualInformationFeatureSelectingEstimator that selects the top k slots in a feature 
             // vector based on highest mutual information between that slot and a specified label. 
-
             var pipeline = mlContext.Transforms.FeatureSelection.SelectFeaturesBasedOnMutualInformation(
                 outputColumnName: "NumericVector", labelColumnName: "Label",
                 slotsInOutput:2);
@@ -36,24 +37,23 @@ public static void Example()
             // The pipeline can then be trained, using .Fit(), and the resulting transformer can be used to transform data. 
             var transformedData = pipeline.Fit(data).Transform(data);
 
-            Console.WriteLine("Contents of column 'NumericVector'");
-            PrintDataColumn(transformedData, "NumericVector");
-            // 4 0
-            // 0 5
-            // 4 0
-            // 0 5
+            var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
+
+            // Printing the columns of the transformed data. 
+            Console.WriteLine($"NumericVector");
+            foreach (var item in convertedData)
+                Console.WriteLine("{0,-25}", string.Join(",", item.NumericVector));
+            
+            // NumericVector
+            // 4,0
+            // 0,5
+            // 4,0
+            // 0,5
         }
 
-        private static void PrintDataColumn(IDataView transformedData, string columnName)
+        public class TransformedData
         {
-            var countSelectColumn = transformedData.GetColumn<float[]>(transformedData.Schema[columnName]);
-
-            foreach (var row in countSelectColumn)
-            {
-                for (var i = 0; i < row.Length; i++)
-                    Console.Write($"{row[i]} ");
-                Console.WriteLine();
-            }
+            public float[] NumericVector { get; set; }
         }
 
         public class NumericData
@@ -74,22 +74,22 @@ public static IEnumerable<NumericData> GetData()
                 new NumericData
                 {
                     Label = true,
-                    NumericVector = new float[] { 4, 6, 0 },
+                    NumericVector = new float[] { 4, 0, 6 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    NumericVector = new float[] { 0, 7, 5 },
+                    NumericVector = new float[] { 0, 5, 7 },
                 },
                 new NumericData
                 {
                     Label = true,
-                    NumericVector = new float[] { 4, 6, 0 },
+                    NumericVector = new float[] { 4, 0, 6 },
                 },
                 new NumericData
                 {
                     Label = false,
-                    NumericVector = new float[] { 0, 7, 5 },
+                    NumericVector = new float[] { 0, 5, 7 },
                 }
             };
             return data;
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
index 0679cec9b7..d9543cee7e 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformationMultiColumn.cs
@@ -16,13 +16,16 @@ public static void Example()
             // Get a small dataset as an IEnumerable and convert it to an IDataView.
             var rawData = GetData();
 
-            Console.WriteLine("Contents of columns 'Label', 'NumericVectorA' and 'NumericVectorB'.");
+            // Printing the columns of the input data. 
+            Console.WriteLine($"NumericVectorA            NumericVectorB");
             foreach (var item in rawData)
-                Console.WriteLine("{0}\t\t{1}\t\t{2}", item.Label, string.Join(" ", item.NumericVectorA), string.Join(" ", item.NumericVectorB));
-            // True            4 0 6           7 8 9
-            // False           0 5 7           7 9 0
-            // True            4 0 6           7 8 9
-            // False           0 5 7           7 8 0
+                Console.WriteLine("{0,-25} {1,-25}", string.Join(",", item.NumericVectorA), string.Join(",", item.NumericVectorB));
+
+            // NumericVectorA              NumericVectorB
+            // 4,0,6                       7,8,9
+            // 0,5,7                       7,9,0
+            // 4,0,6                       7,8,9
+            // 0,5,7                       7,8,0
 
             var data = mlContext.Data.LoadFromEnumerable(rawData);
 
@@ -38,15 +41,17 @@ public static void Example()
             var transformedData = pipeline.Fit(data).Transform(data);
 
             var convertedData = mlContext.Data.CreateEnumerable<TransformedData>(transformedData, true);
-            Console.WriteLine("Contents of two columns 'NumericVectorA' and 'NumericVectorB'.");
+
+            // Printing the columns of the transformed data. 
+            Console.WriteLine($"NumericVectorA            NumericVectorB");
             foreach (var item in convertedData)
-                Console.WriteLine("{0}\t\t{1}", string.Join(" ", item.NumericVectorA), string.Join(" ", item.NumericVectorB));
+                Console.WriteLine("{0,-25} {1,-25}", string.Join(",", item.NumericVectorA), string.Join(",", item.NumericVectorB));
 
-            // Here, we see SelectFeaturesBasedOnMutualInformation selected 4 slots.
-            // 4 0 6           9
-            // 0 5 7           0
-            // 4 0 6           9
-            // 0 5 7           0
+            // NumericVectorA              NumericVectorB
+            // 4,0,6                       9
+            // 0,5,7                       0
+            // 4,0,6                       9
+            // 0,5,7                       0
         }
 
         private class TransformedData

From cb09d87a86e83f03369e058668cba581d8a9b249 Mon Sep 17 00:00:00 2001
From: Abhishek Goswami <abgoswam@gmail.com>
Date: Thu, 4 Apr 2019 23:40:04 +0000
Subject: [PATCH 6/6] fix copy paste output error

---
 .../SelectFeaturesBasedOnMutualInformation.cs            | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
index 0b9232e5e6..d7aa805ceb 100644
--- a/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
+++ b/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/FeatureSelection/SelectFeaturesBasedOnMutualInformation.cs
@@ -21,10 +21,11 @@ public static void Example()
             foreach (var item in rawData)
                 Console.WriteLine("{0,-25} {1,-25}", item.Label, string.Join(",", item.NumericVector));
 
-            // True            4 0 6
-            // False           0 5 7
-            // True            4 0 6
-            // False           0 5 7
+            // Label                       NumericVector
+            // True                        4,0,6
+            // False                       0,5,7
+            // True                        4,0,6
+            // False                       0,5,7
 
             var data = mlContext.Data.LoadFromEnumerable(rawData);