From d9c4a297c790e6423fdd8077e8eaab44eaf04b8e Mon Sep 17 00:00:00 2001
From: Zeeshan Ahmed <zeahmed@microsoft.com>
Date: Tue, 10 Jul 2018 12:59:08 -0700
Subject: [PATCH 1/6] [Part 3] Added convenience constructors for set of
 transforms.

---
 src/Microsoft.ML.Transforms/GroupTransform.cs | 12 ++++++
 .../HashJoinTransform.cs                      | 35 +++++++++++++++--
 .../KeyToBinaryVectorTransform.cs             | 12 ++++++
 src/Microsoft.ML.Transforms/LoadTransform.cs  | 19 +++++++++
 .../MissingValueIndicatorTransform.cs         | 12 ++++++
 .../MutualInformationFeatureSelection.cs      | 39 +++++++++++++++++--
 .../NADropTransform.cs                        | 12 ++++++
 .../NAHandleTransform.cs                      | 21 ++++++++++
 .../NAIndicatorTransform.cs                   | 12 ++++++
 .../NAReplaceTransform.cs                     | 13 +++++++
 .../OptionalColumnTransform.cs                | 11 ++++++
 .../ProduceIdTransform.cs                     | 18 ++++++++-
 src/Microsoft.ML.Transforms/RffTransform.cs   | 29 +++++++++++++-
 .../UngroupTransform.cs                       | 12 ++++++
 .../WhiteningTransform.cs                     | 36 ++++++++++++++---
 15 files changed, 278 insertions(+), 15 deletions(-)

diff --git a/src/Microsoft.ML.Transforms/GroupTransform.cs b/src/Microsoft.ML.Transforms/GroupTransform.cs
index 1d5b823278..55720e19b9 100644
--- a/src/Microsoft.ML.Transforms/GroupTransform.cs
+++ b/src/Microsoft.ML.Transforms/GroupTransform.cs
@@ -88,6 +88,18 @@ public sealed class Arguments : TransformInputBase
 
         private readonly GroupSchema _schema;
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="groupKey">Columns to group by</param>
+        /// <param name="columns">Columns to group together</param>
+        public GroupTransform(IHostEnvironment env, IDataView input, string[] groupKey, params string[] columns)
+            : this(env, new Arguments() { GroupKey = groupKey, Column = columns }, input)
+        {
+        }
+
         public GroupTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, RegistrationName, input)
         {
diff --git a/src/Microsoft.ML.Transforms/HashJoinTransform.cs b/src/Microsoft.ML.Transforms/HashJoinTransform.cs
index 098564bef3..f7c2259a3a 100644
--- a/src/Microsoft.ML.Transforms/HashJoinTransform.cs
+++ b/src/Microsoft.ML.Transforms/HashJoinTransform.cs
@@ -37,6 +37,14 @@ public sealed class HashJoinTransform : OneToOneTransformBase
         public const int NumBitsMin = 1;
         public const int NumBitsLim = 32;
 
+        private static class Defaults
+        {
+            public const bool Join = true;
+            public const int HashBits = NumBitsLim - 1;
+            public const uint Seed = 314489979;
+            public const bool Ordered = true;
+        }
+
         public sealed class Arguments : TransformInputBase
         {
             [Argument(ArgumentType.Multiple | ArgumentType.Required, HelpText = "New column definition(s) (optional form: name:src)",
@@ -45,17 +53,17 @@ public sealed class Arguments : TransformInputBase
             public Column[] Column;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Whether the values need to be combined for a single hash")]
-            public bool Join = true;
+            public bool Join = Defaults.Join;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Number of bits to hash into. Must be between 1 and 31, inclusive.",
                 ShortName = "bits", SortOrder = 2)]
-            public int HashBits = NumBitsLim - 1;
+            public int HashBits = Defaults.HashBits;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Hashing seed")]
-            public uint Seed = 314489979;
+            public uint Seed = Defaults.Seed;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Whether the position of each term should be included in the hash", ShortName = "ord")]
-            public bool Ordered = true;
+            public bool Ordered = Defaults.Ordered;
         }
 
         public sealed class Column : OneToOneColumn
@@ -166,6 +174,25 @@ private static VersionInfo GetVersionInfo()
 
         private readonly ColumnInfoEx[] _exes;
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        /// <param name="join">Whether the values need to be combined for a single hash.</param>
+        /// <param name="hashBits">Number of bits to hash into. Must be between 1 and 31, inclusive.</param>
+        public HashJoinTransform(IHostEnvironment env,
+            IDataView input,
+            string name,
+            string source = null,
+             bool join = Defaults.Join,
+            int hashBits = Defaults.HashBits)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } }, Join = join, HashBits = hashBits }, input)
+        {
+        }
+
         public HashJoinTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, RegistrationName, Contracts.CheckRef(args, nameof(args)).Column, input, TestColumnType)
         {
diff --git a/src/Microsoft.ML.Transforms/KeyToBinaryVectorTransform.cs b/src/Microsoft.ML.Transforms/KeyToBinaryVectorTransform.cs
index 5983efb244..0cfaf75500 100644
--- a/src/Microsoft.ML.Transforms/KeyToBinaryVectorTransform.cs
+++ b/src/Microsoft.ML.Transforms/KeyToBinaryVectorTransform.cs
@@ -54,6 +54,18 @@ private static VersionInfo GetVersionInfo()
 
         private readonly VectorType[] _types;
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        public KeyToBinaryVectorTransform(IHostEnvironment env, IDataView input, string name, string source = null)
+            : this(env, new Arguments() { Column = new[] { new KeyToVectorTransform.Column() { Source = source ?? name, Name = name } } }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/LoadTransform.cs b/src/Microsoft.ML.Transforms/LoadTransform.cs
index 83ff43274d..64a494702d 100644
--- a/src/Microsoft.ML.Transforms/LoadTransform.cs
+++ b/src/Microsoft.ML.Transforms/LoadTransform.cs
@@ -39,6 +39,25 @@ public class Arguments
 
         internal const string Summary = "Loads specified transforms from the model file and applies them to current data.";
 
+        /// <summary>
+        /// A helper method to create <see cref="LoadTransform"/> for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="modelFile">Model file to load the transforms from.</param>
+        /// <param name="tag">The tags (comma-separated) to be loaded (or omitted, if complement is true).</param>
+        /// <param name="complement">Whether to load all transforms except those marked by tags.</param>
+        public static IDataTransform Create(IHostEnvironment env, IDataView input, string modelFile, string[] tag, bool complement = false)
+        {
+            var args = new Arguments()
+            {
+                ModelFile = modelFile,
+                Tag = tag,
+                Complement = complement
+            };
+            return Create(env, args, input);
+        }
+
         public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
         {
             Contracts.CheckValue(env, nameof(env));
diff --git a/src/Microsoft.ML.Transforms/MissingValueIndicatorTransform.cs b/src/Microsoft.ML.Transforms/MissingValueIndicatorTransform.cs
index 7020bc0830..5c757a2593 100644
--- a/src/Microsoft.ML.Transforms/MissingValueIndicatorTransform.cs
+++ b/src/Microsoft.ML.Transforms/MissingValueIndicatorTransform.cs
@@ -69,6 +69,18 @@ private static VersionInfo GetVersionInfo()
         // The output column types, parallel to Infos.
         private readonly VectorType[] _types;
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        public MissingValueIndicatorTransform(IHostEnvironment env, IDataView input, string name, string source = null)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } } }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/MutualInformationFeatureSelection.cs b/src/Microsoft.ML.Transforms/MutualInformationFeatureSelection.cs
index d8c20f03ca..41ff9930a2 100644
--- a/src/Microsoft.ML.Transforms/MutualInformationFeatureSelection.cs
+++ b/src/Microsoft.ML.Transforms/MutualInformationFeatureSelection.cs
@@ -33,6 +33,13 @@ public static class MutualInformationFeatureSelectionTransform
         public const string UserName = "Mutual Information Feature Selection Transform";
         public const string ShortName = "MIFeatureSelection";
 
+        private static class Defaults
+        {
+            public const string LabelColumn = DefaultColumnNames.Label;
+            public const int SlotsInOutput = 1000;
+            public const int NumBins = 256;
+        }
+
         public sealed class Arguments : TransformInputBase
         {
             [Argument(ArgumentType.Multiple | ArgumentType.Required, HelpText = "Columns to use for feature selection", ShortName = "col",
@@ -41,19 +48,45 @@ public sealed class Arguments : TransformInputBase
 
             [Argument(ArgumentType.LastOccurenceWins, HelpText = "Column to use for labels", ShortName = "lab",
                 SortOrder = 4, Purpose = SpecialPurpose.ColumnName)]
-            public string LabelColumn = DefaultColumnNames.Label;
+            public string LabelColumn = Defaults.LabelColumn;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "The maximum number of slots to preserve in output", ShortName = "topk,numSlotsToKeep",
                 SortOrder = 1)]
-            public int SlotsInOutput = 1000;
+            public int SlotsInOutput = Defaults.SlotsInOutput;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Max number of bins for R4/R8 columns, power of 2 recommended",
                 ShortName = "bins")]
-            public int NumBins = 256;
+            public int NumBins = Defaults.NumBins;
         }
 
         internal static string RegistrationName = "MutualInformationFeatureSelectionTransform";
 
+        /// <summary>
+        /// A helper method to create <see cref="MutualInformationFeatureSelectionTransform"/> for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="labelColumn">Column to use for labels.</param>
+        /// <param name="slotsInOutput">The maximum number of slots to preserve in output.</param>
+        /// <param name="numBins">Max number of bins for R4/R8 columns, power of 2 recommended.</param>
+        /// <param name="columns">Columns to use for feature selection.</param>
+        public static IDataTransform Create(IHostEnvironment env,
+            IDataView input,
+            string labelColumn = Defaults.LabelColumn,
+            int slotsInOutput = Defaults.SlotsInOutput,
+            int numBins = Defaults.NumBins,
+            params string[] columns)
+        {
+            var args = new Arguments()
+            {
+                Column = columns,
+                LabelColumn = labelColumn,
+                SlotsInOutput = slotsInOutput,
+                NumBins = numBins
+            };
+            return Create(env, args, input);
+        }
+
         /// <summary>
         /// Create method corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/NADropTransform.cs b/src/Microsoft.ML.Transforms/NADropTransform.cs
index 347e889a5b..ded5add732 100644
--- a/src/Microsoft.ML.Transforms/NADropTransform.cs
+++ b/src/Microsoft.ML.Transforms/NADropTransform.cs
@@ -69,6 +69,18 @@ private static VersionInfo GetVersionInfo()
         // The isNA delegates, parallel to Infos.
         private readonly Delegate[] _isNAs;
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        public NADropTransform(IHostEnvironment env, IDataView input, string name, string source = null)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } } }, input)
+        {
+        }
+
         public NADropTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(Contracts.CheckRef(env, nameof(env)), RegistrationName, env.CheckRef(args, nameof(args)).Column, input, TestType)
         {
diff --git a/src/Microsoft.ML.Transforms/NAHandleTransform.cs b/src/Microsoft.ML.Transforms/NAHandleTransform.cs
index 1b82fe3e1e..ceff4869a6 100644
--- a/src/Microsoft.ML.Transforms/NAHandleTransform.cs
+++ b/src/Microsoft.ML.Transforms/NAHandleTransform.cs
@@ -105,6 +105,27 @@ public bool TryUnparse(StringBuilder sb)
         internal const string FriendlyName = "NA Handle Transform";
         internal const string ShortName = "NAHandle";
 
+        /// <summary>
+        /// A helper method to create <see cref="NAHandleTransform"/> for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        /// <param name="replaceWith">The replacement method to utilize.</param>
+        public static IDataTransform Create(IHostEnvironment env, IDataView input, string name, string source = null, ReplacementKind replaceWith = ReplacementKind.DefaultValue)
+        {
+            var args = new Arguments()
+            {
+                Column = new[] 
+                {
+                    new Column() { Source = source ?? name, Name = name }
+                },
+                ReplaceWith = replaceWith
+            };
+            return Create(env, args, input);
+        }
+
         public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
         {
             Contracts.CheckValue(env, nameof(env));
diff --git a/src/Microsoft.ML.Transforms/NAIndicatorTransform.cs b/src/Microsoft.ML.Transforms/NAIndicatorTransform.cs
index 38ecc2c817..c35a90d748 100644
--- a/src/Microsoft.ML.Transforms/NAIndicatorTransform.cs
+++ b/src/Microsoft.ML.Transforms/NAIndicatorTransform.cs
@@ -85,6 +85,18 @@ private static string TestType(ColumnType type)
         // The output column types, parallel to Infos.
         private readonly ColumnType[] _types;
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        public NAIndicatorTransform(IHostEnvironment env, IDataView input, string name, string source = null)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } } }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/NAReplaceTransform.cs b/src/Microsoft.ML.Transforms/NAReplaceTransform.cs
index 44832ee517..30384780e9 100644
--- a/src/Microsoft.ML.Transforms/NAReplaceTransform.cs
+++ b/src/Microsoft.ML.Transforms/NAReplaceTransform.cs
@@ -186,6 +186,19 @@ private static string TestType<T>(ColumnType type)
 
         public override bool CanSaveOnnx => true;
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        /// <param name="replacementKind">The replacement method to utilize.</param>
+        public NAReplaceTransform(IHostEnvironment env, IDataView input, string name, string source = null, ReplacementKind replacementKind = ReplacementKind.DefaultValue)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } }, ReplacementKind = replacementKind }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
index 5d3ab591b2..8a3fa6f7ae 100644
--- a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
+++ b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
@@ -232,6 +232,17 @@ private static VersionInfo GetVersionInfo()
 
         private const string RegistrationName = "OptionalColumn";
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="columns">Columns to transform.</param>
+        public OptionalColumnTransform(IHostEnvironment env, IDataView input, params string[] columns)
+            : this(env, new Arguments() { Column = columns }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/ProduceIdTransform.cs b/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
index c66489d386..f437d6319b 100644
--- a/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
+++ b/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
@@ -25,10 +25,15 @@ namespace Microsoft.ML.Runtime.Data
     /// </summary>
     public sealed class ProduceIdTransform : RowToRowTransformBase
     {
+        private static class Defaults
+        {
+            public const string Column = "Id";
+        }
+
         public sealed class Arguments
         {
             [Argument(ArgumentType.AtMostOnce, HelpText = "Name of the column to produce", ShortName = "col", SortOrder = 1)]
-            public string Column = "Id";
+            public string Column = Defaults.Column;
         }
 
         private sealed class Bindings : ColumnBindingsBase
@@ -93,6 +98,17 @@ private static VersionInfo GetVersionInfo()
 
         public override bool CanShuffle { get { return Source.CanShuffle; } }
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="column">Name of the column to produce.</param>
+        public ProduceIdTransform(IHostEnvironment env, IDataView input, string column = Defaults.Column)
+            : this(env, new Arguments() { Column = column }, input)
+        {
+        }
+
         public ProduceIdTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, LoaderSignature, input)
         {
diff --git a/src/Microsoft.ML.Transforms/RffTransform.cs b/src/Microsoft.ML.Transforms/RffTransform.cs
index b8f49b4dce..25ff320ec5 100644
--- a/src/Microsoft.ML.Transforms/RffTransform.cs
+++ b/src/Microsoft.ML.Transforms/RffTransform.cs
@@ -27,20 +27,26 @@ namespace Microsoft.ML.Runtime.Data
 
     public sealed class RffTransform : OneToOneTransformBase
     {
+        private static class Defaults
+        {
+            public const int NewDim = 1000;
+            public const bool UseSin = false;
+        }
+
         public sealed class Arguments
         {
             [Argument(ArgumentType.Multiple | ArgumentType.Required, HelpText = "New column definition(s) (optional form: name:src)", ShortName = "col", SortOrder = 1)]
             public Column[] Column;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "The number of random Fourier features to create", ShortName = "dim")]
-            public int NewDim = 1000;
+            public int NewDim = Defaults.NewDim;
 
             [Argument(ArgumentType.Multiple, HelpText = "which kernel to use?", ShortName = "kernel")]
             public SubComponent<IFourierDistributionSampler, SignatureFourierDistributionSampler> MatrixGenerator =
                 new SubComponent<IFourierDistributionSampler, SignatureFourierDistributionSampler>(GaussianFourierSampler.LoadName);
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "create two features for every random Fourier frequency? (one for cos and one for sin)")]
-            public bool UseSin = false;
+            public bool UseSin = Defaults.UseSin;
 
             [Argument(ArgumentType.LastOccurenceWins,
                 HelpText = "The seed of the random number generator for generating the new features (if unspecified, " +
@@ -232,6 +238,25 @@ private static string TestColumnType(ColumnType type)
             return "Expected R4 or vector of R4 with known size";
         }
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        /// <param name="newDim">The number of random Fourier features to create.</param>
+        /// <param name="useSin">create two features for every random Fourier frequency? (one for cos and one for sin).</param>
+        public RffTransform(IHostEnvironment env,
+            IDataView input,
+            string name,
+            string source = null,
+            int newDim = Defaults.NewDim,
+            bool useSin = Defaults.UseSin)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } }, NewDim = newDim, UseSin = useSin }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to <see cref="SignatureDataTransform"/>.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/UngroupTransform.cs b/src/Microsoft.ML.Transforms/UngroupTransform.cs
index cb97e1c3b3..89c17f22d1 100644
--- a/src/Microsoft.ML.Transforms/UngroupTransform.cs
+++ b/src/Microsoft.ML.Transforms/UngroupTransform.cs
@@ -79,6 +79,18 @@ public sealed class Arguments : TransformInputBase
 
         private readonly SchemaImpl _schemaImpl;
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="mode">Specifies how to unroll multiple pivot columns of different size.</param>
+        /// <param name="columns">Columns to unroll, or 'pivot'</param>
+        public UngroupTransform(IHostEnvironment env, IDataView input, UngroupMode mode, params string[] columns)
+            : this(env, new Arguments() { Column = columns, Mode = mode }, input)
+        {
+        }
+
         public UngroupTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, LoaderSignature, input)
         {
diff --git a/src/Microsoft.ML.Transforms/WhiteningTransform.cs b/src/Microsoft.ML.Transforms/WhiteningTransform.cs
index 2ae3824ba8..8b36078a04 100644
--- a/src/Microsoft.ML.Transforms/WhiteningTransform.cs
+++ b/src/Microsoft.ML.Transforms/WhiteningTransform.cs
@@ -46,25 +46,34 @@ public enum WhiteningKind
     /// </summary>
     public sealed class WhiteningTransform : OneToOneTransformBase
     {
+        private static class Defaults
+        {
+            public const WhiteningKind Kind = WhiteningKind.Zca;
+            public const Float Eps = (Float)1e-5;
+            public const int MaxRows = 100 * 1000;
+            public const bool SaveInverse = false;
+            public const int PcaNum = 0;
+        }
+
         public sealed class Arguments
         {
             [Argument(ArgumentType.Multiple | ArgumentType.Required, HelpText = "New column definition(s) (optional form: name:src)", ShortName = "col", SortOrder = 1)]
             public Column[] Column;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Whitening kind (PCA/ZCA)")]
-            public WhiteningKind Kind = WhiteningKind.Zca;
+            public WhiteningKind Kind = Defaults.Kind;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Scaling regularizer")]
-            public Float Eps = (Float)1e-5;
+            public Float Eps = Defaults.Eps;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Max number of rows", ShortName = "rows")]
-            public int MaxRows = 100 * 1000;
+            public int MaxRows = Defaults.MaxRows;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Whether to save inverse (recovery) matrix", ShortName = "saveInv")]
-            public bool SaveInverse = false;
+            public bool SaveInverse = Defaults.SaveInverse;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "PCA components to retain")]
-            public int PcaNum = 0;
+            public int PcaNum = Defaults.PcaNum;
 
             // REVIEW: add the following options:
             // 1. Currently there is no way to apply an inverse transform AFTER the the transform is trained.
@@ -209,6 +218,23 @@ private static VersionInfo GetVersionInfo()
 
         private const string RegistrationName = "Whitening";
 
+        /// <summary>
+        /// Convenience constructor for public facing API.
+        /// </summary>
+        /// <param name="env">Host Environment.</param>
+        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="name">Name of the output column.</param>
+        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
+        /// <param name="kind">Whitening kind (PCA/ZCA).</param>
+        public WhiteningTransform(IHostEnvironment env,
+            IDataView input,
+            string name,
+            string source = null,
+            WhiteningKind kind = Defaults.Kind)
+                : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } }, Kind = kind }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>

From 6cd77eb96fa37276f147572af0ed90d7f86b2b96 Mon Sep 17 00:00:00 2001
From: Zeeshan Ahmed <zeahmed@microsoft.com>
Date: Thu, 12 Jul 2018 11:57:17 -0700
Subject: [PATCH 2/6] Addressed reviewers' comments.

---
 src/Microsoft.ML.Transforms/GroupTransform.cs  |  4 ++--
 .../MissingValueIndicatorTransform.cs          | 12 ------------
 .../MutualInformationFeatureSelection.cs       |  2 +-
 .../NAHandleTransform.cs                       | 18 ++++++++++++++++++
 .../ProduceIdTransform.cs                      | 11 -----------
 src/Microsoft.ML.Transforms/RffTransform.cs    | 10 ++++------
 .../UngroupTransform.cs                        | 14 ++++++++++++++
 7 files changed, 39 insertions(+), 32 deletions(-)

diff --git a/src/Microsoft.ML.Transforms/GroupTransform.cs b/src/Microsoft.ML.Transforms/GroupTransform.cs
index 55720e19b9..2170c3b373 100644
--- a/src/Microsoft.ML.Transforms/GroupTransform.cs
+++ b/src/Microsoft.ML.Transforms/GroupTransform.cs
@@ -95,8 +95,8 @@ public sealed class Arguments : TransformInputBase
         /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
         /// <param name="groupKey">Columns to group by</param>
         /// <param name="columns">Columns to group together</param>
-        public GroupTransform(IHostEnvironment env, IDataView input, string[] groupKey, params string[] columns)
-            : this(env, new Arguments() { GroupKey = groupKey, Column = columns }, input)
+        public GroupTransform(IHostEnvironment env, IDataView input, string groupKey, params string[] columns)
+            : this(env, new Arguments() { GroupKey = new[] { groupKey }, Column = columns }, input)
         {
         }
 
diff --git a/src/Microsoft.ML.Transforms/MissingValueIndicatorTransform.cs b/src/Microsoft.ML.Transforms/MissingValueIndicatorTransform.cs
index 5c757a2593..7020bc0830 100644
--- a/src/Microsoft.ML.Transforms/MissingValueIndicatorTransform.cs
+++ b/src/Microsoft.ML.Transforms/MissingValueIndicatorTransform.cs
@@ -69,18 +69,6 @@ private static VersionInfo GetVersionInfo()
         // The output column types, parallel to Infos.
         private readonly VectorType[] _types;
 
-        /// <summary>
-        /// Convenience constructor for public facing API.
-        /// </summary>
-        /// <param name="env">Host Environment.</param>
-        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
-        /// <param name="name">Name of the output column.</param>
-        /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
-        public MissingValueIndicatorTransform(IHostEnvironment env, IDataView input, string name, string source = null)
-            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } } }, input)
-        {
-        }
-
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/MutualInformationFeatureSelection.cs b/src/Microsoft.ML.Transforms/MutualInformationFeatureSelection.cs
index 41ff9930a2..39fec2b208 100644
--- a/src/Microsoft.ML.Transforms/MutualInformationFeatureSelection.cs
+++ b/src/Microsoft.ML.Transforms/MutualInformationFeatureSelection.cs
@@ -62,7 +62,7 @@ public sealed class Arguments : TransformInputBase
         internal static string RegistrationName = "MutualInformationFeatureSelectionTransform";
 
         /// <summary>
-        /// A helper method to create <see cref="MutualInformationFeatureSelectionTransform"/> for public facing API.
+        /// A helper method to create <see cref="IDataTransform"/> for selecting the top k slots ordered by their mutual information.
         /// </summary>
         /// <param name="env">Host Environment.</param>
         /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
diff --git a/src/Microsoft.ML.Transforms/NAHandleTransform.cs b/src/Microsoft.ML.Transforms/NAHandleTransform.cs
index ceff4869a6..3b8956f2a2 100644
--- a/src/Microsoft.ML.Transforms/NAHandleTransform.cs
+++ b/src/Microsoft.ML.Transforms/NAHandleTransform.cs
@@ -34,12 +34,30 @@ namespace Microsoft.ML.Runtime.Data
     /// </summary>
     public static class NAHandleTransform
     {
+        /// <summary>
+        /// 
+        /// </summary>
         public enum ReplacementKind
         {
+            /// <summary>
+            /// Replace with the default value of the column based on it's type. For example, 'zero' for numeric and 'empty' for string/text columns.
+            /// </summary>
             [EnumValueDisplay("Zero/empty")]
             DefaultValue,
+
+            /// <summary>
+            /// Replace with the mean value of the column. Supports only numeric/time span/ DateTime columns.
+            /// </summary>
             Mean,
+
+            /// <summary>
+            /// Replace with the minimum value of the column. Supports only numeric/time span/ DateTime columns.
+            /// </summary>
             Minimum,
+
+            /// <summary>
+            /// Replace with the maximum value of the column. Supports only numeric/time span/ DateTime columns.
+            /// </summary>
             Maximum,
 
             [HideEnumValue]
diff --git a/src/Microsoft.ML.Transforms/ProduceIdTransform.cs b/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
index f437d6319b..fedaf3cb25 100644
--- a/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
+++ b/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
@@ -98,17 +98,6 @@ private static VersionInfo GetVersionInfo()
 
         public override bool CanShuffle { get { return Source.CanShuffle; } }
 
-        /// <summary>
-        /// Convenience constructor for public facing API.
-        /// </summary>
-        /// <param name="env">Host Environment.</param>
-        /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
-        /// <param name="column">Name of the column to produce.</param>
-        public ProduceIdTransform(IHostEnvironment env, IDataView input, string column = Defaults.Column)
-            : this(env, new Arguments() { Column = column }, input)
-        {
-        }
-
         public ProduceIdTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, LoaderSignature, input)
         {
diff --git a/src/Microsoft.ML.Transforms/RffTransform.cs b/src/Microsoft.ML.Transforms/RffTransform.cs
index 25ff320ec5..85c4203512 100644
--- a/src/Microsoft.ML.Transforms/RffTransform.cs
+++ b/src/Microsoft.ML.Transforms/RffTransform.cs
@@ -243,17 +243,15 @@ private static string TestColumnType(ColumnType type)
         /// </summary>
         /// <param name="env">Host Environment.</param>
         /// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
+        /// <param name="newDim">The number of random Fourier features to create.</param>
         /// <param name="name">Name of the output column.</param>
         /// <param name="source">Name of the column to be transformed. If this is null '<paramref name="name"/>' will be used.</param>
-        /// <param name="newDim">The number of random Fourier features to create.</param>
-        /// <param name="useSin">create two features for every random Fourier frequency? (one for cos and one for sin).</param>
         public RffTransform(IHostEnvironment env,
             IDataView input,
+            int newDim,
             string name,
-            string source = null,
-            int newDim = Defaults.NewDim,
-            bool useSin = Defaults.UseSin)
-            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } }, NewDim = newDim, UseSin = useSin }, input)
+            string source = null)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } }, NewDim = newDim }, input)
         {
         }
 
diff --git a/src/Microsoft.ML.Transforms/UngroupTransform.cs b/src/Microsoft.ML.Transforms/UngroupTransform.cs
index 89c17f22d1..0b6aeea1b5 100644
--- a/src/Microsoft.ML.Transforms/UngroupTransform.cs
+++ b/src/Microsoft.ML.Transforms/UngroupTransform.cs
@@ -61,10 +61,24 @@ private static VersionInfo GetVersionInfo()
                 loaderSignature: LoaderSignature);
         }
 
+        /// <summary>
+        /// Controls the number of output rows produced by the <see cref="UngroupTransform"/> transform
+        /// </summary>
         public enum UngroupMode
         {
+            /// <summary>
+            /// A number of output rows are equal to the minimum length of pivot columns
+            /// </summary>
             Inner,
+
+            /// <summary>
+            /// A number of output rows are equal to the maximum length of pivot columns
+            /// </summary>
             Outer,
+
+            /// <summary>
+            /// A number of output rows are equal to the length of the first pivot column.
+            /// </summary>
             First
         }
 

From 75a8b6dc31b1d7e78980e3b179dd011e597400f2 Mon Sep 17 00:00:00 2001
From: Zeeshan Ahmed <zeahmed@microsoft.com>
Date: Fri, 13 Jul 2018 11:32:43 -0700
Subject: [PATCH 3/6] Addressed reviewers' comments.

---
 src/Microsoft.ML.Transforms/NAHandleTransform.cs       | 3 ---
 src/Microsoft.ML.Transforms/OptionalColumnTransform.cs | 4 ++++
 src/Microsoft.ML.Transforms/ProduceIdTransform.cs      | 7 +------
 src/Microsoft.ML.Transforms/UngroupTransform.cs        | 6 +++---
 4 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/src/Microsoft.ML.Transforms/NAHandleTransform.cs b/src/Microsoft.ML.Transforms/NAHandleTransform.cs
index 3b8956f2a2..840a080ae6 100644
--- a/src/Microsoft.ML.Transforms/NAHandleTransform.cs
+++ b/src/Microsoft.ML.Transforms/NAHandleTransform.cs
@@ -34,9 +34,6 @@ namespace Microsoft.ML.Runtime.Data
     /// </summary>
     public static class NAHandleTransform
     {
-        /// <summary>
-        /// 
-        /// </summary>
         public enum ReplacementKind
         {
             /// <summary>
diff --git a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
index 8a3fa6f7ae..e294ea5066 100644
--- a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
+++ b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
@@ -26,6 +26,10 @@
 
 namespace Microsoft.ML.Runtime.DataPipe
 {
+    /// <summary>
+    /// This transform is used to mark some of the columns (e.g. Label) optional during training So that the columns is not required during scoring..
+    /// At scoring time, it is checked if the data schema for scoring matches the data used for training except for the optional columns.
+    /// </summary>
     public class OptionalColumnTransform : RowToRowMapperTransformBase
     {
         public sealed class Arguments : TransformInputBase
diff --git a/src/Microsoft.ML.Transforms/ProduceIdTransform.cs b/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
index fedaf3cb25..c66489d386 100644
--- a/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
+++ b/src/Microsoft.ML.Transforms/ProduceIdTransform.cs
@@ -25,15 +25,10 @@ namespace Microsoft.ML.Runtime.Data
     /// </summary>
     public sealed class ProduceIdTransform : RowToRowTransformBase
     {
-        private static class Defaults
-        {
-            public const string Column = "Id";
-        }
-
         public sealed class Arguments
         {
             [Argument(ArgumentType.AtMostOnce, HelpText = "Name of the column to produce", ShortName = "col", SortOrder = 1)]
-            public string Column = Defaults.Column;
+            public string Column = "Id";
         }
 
         private sealed class Bindings : ColumnBindingsBase
diff --git a/src/Microsoft.ML.Transforms/UngroupTransform.cs b/src/Microsoft.ML.Transforms/UngroupTransform.cs
index 0b6aeea1b5..4781492076 100644
--- a/src/Microsoft.ML.Transforms/UngroupTransform.cs
+++ b/src/Microsoft.ML.Transforms/UngroupTransform.cs
@@ -67,17 +67,17 @@ private static VersionInfo GetVersionInfo()
         public enum UngroupMode
         {
             /// <summary>
-            /// A number of output rows are equal to the minimum length of pivot columns
+            /// The number of output rows are equal to the minimum length of pivot columns
             /// </summary>
             Inner,
 
             /// <summary>
-            /// A number of output rows are equal to the maximum length of pivot columns
+            /// The number of output rows are equal to the maximum length of pivot columns
             /// </summary>
             Outer,
 
             /// <summary>
-            /// A number of output rows are equal to the length of the first pivot column.
+            /// The number of output rows are equal to the length of the first pivot column.
             /// </summary>
             First
         }

From d72a4acaf5b56d55823ab94d4cb8783d5c6b52ea Mon Sep 17 00:00:00 2001
From: Zeeshan Ahmed <zeahmed@microsoft.com>
Date: Fri, 13 Jul 2018 15:35:47 -0700
Subject: [PATCH 4/6] Addressed reviewers' comments.

---
 src/Microsoft.ML.Transforms/OptionalColumnTransform.cs | 10 +++++++---
 src/Microsoft.ML.Transforms/UngroupTransform.cs        |  6 +++---
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
index e294ea5066..d900715d30 100644
--- a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
+++ b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
@@ -27,10 +27,14 @@
 namespace Microsoft.ML.Runtime.DataPipe
 {
     /// <summary>
-    /// This transform is used to mark some of the columns (e.g. Label) optional during training So that the columns is not required during scoring..
-    /// At scoring time, it is checked if the data schema for scoring matches the data used for training except for the optional columns.
+    /// This transform is used to mark some of the columns (e.g. Label) optional during training so that the columns are not required during scoring.
+    /// When applied to new data, if optional columns are not present a meta column is created having the same properties (e.g. 'name', 'type' etc.) as used during training.
+    /// The columns are filled with default values. The value is
+    ///     - scalar for scalar column
+    ///     - totally sparse vector for vector column. 
+    /// If value of the column is requested the default value will be returned.
     /// </summary>
-    public class OptionalColumnTransform : RowToRowMapperTransformBase
+    public sealed class OptionalColumnTransform : RowToRowMapperTransformBase
     {
         public sealed class Arguments : TransformInputBase
         {
diff --git a/src/Microsoft.ML.Transforms/UngroupTransform.cs b/src/Microsoft.ML.Transforms/UngroupTransform.cs
index 4781492076..49cae8ae6e 100644
--- a/src/Microsoft.ML.Transforms/UngroupTransform.cs
+++ b/src/Microsoft.ML.Transforms/UngroupTransform.cs
@@ -67,17 +67,17 @@ private static VersionInfo GetVersionInfo()
         public enum UngroupMode
         {
             /// <summary>
-            /// The number of output rows are equal to the minimum length of pivot columns
+            /// The number of output rows is equal to the minimum length of pivot columns
             /// </summary>
             Inner,
 
             /// <summary>
-            /// The number of output rows are equal to the maximum length of pivot columns
+            /// The number of output rows is equal to the maximum length of pivot columns
             /// </summary>
             Outer,
 
             /// <summary>
-            /// The number of output rows are equal to the length of the first pivot column.
+            /// The number of output rows is equal to the length of the first pivot column.
             /// </summary>
             First
         }

From 3dd984782d43fc34d8718e32b7c34928e060047f Mon Sep 17 00:00:00 2001
From: Zeeshan Ahmed <zeahmed@microsoft.com>
Date: Fri, 13 Jul 2018 16:09:41 -0700
Subject: [PATCH 5/6] Updated OptionalColumnTransform comments.

---
 src/Microsoft.ML.Transforms/OptionalColumnTransform.cs | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
index d900715d30..ff0ff03c93 100644
--- a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
+++ b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
@@ -28,11 +28,10 @@ namespace Microsoft.ML.Runtime.DataPipe
 {
     /// <summary>
     /// This transform is used to mark some of the columns (e.g. Label) optional during training so that the columns are not required during scoring.
-    /// When applied to new data, if optional columns are not present a meta column is created having the same properties (e.g. 'name', 'type' etc.) as used during training.
+    /// When applied to new data, if optional columns are not present dummy columns are created having the same properties (e.g. 'name', 'type' etc.) as used during training.
     /// The columns are filled with default values. The value is
     ///     - scalar for scalar column
     ///     - totally sparse vector for vector column. 
-    /// If value of the column is requested the default value will be returned.
     /// </summary>
     public sealed class OptionalColumnTransform : RowToRowMapperTransformBase
     {

From 730fe9312520c21585d086f90fbbbe3155555f00 Mon Sep 17 00:00:00 2001
From: Zeeshan Ahmed <zeahmed@microsoft.com>
Date: Fri, 13 Jul 2018 16:15:42 -0700
Subject: [PATCH 6/6] Updated comments.

---
 src/Microsoft.ML.Transforms/OptionalColumnTransform.cs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
index ff0ff03c93..9e1bad374e 100644
--- a/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
+++ b/src/Microsoft.ML.Transforms/OptionalColumnTransform.cs
@@ -28,7 +28,7 @@ namespace Microsoft.ML.Runtime.DataPipe
 {
     /// <summary>
     /// This transform is used to mark some of the columns (e.g. Label) optional during training so that the columns are not required during scoring.
-    /// When applied to new data, if optional columns are not present dummy columns are created having the same properties (e.g. 'name', 'type' etc.) as used during training.
+    /// When applied to new data, if any of the optional columns is not present a dummy columns is created having the same properties (e.g. 'name', 'type' etc.) as used during training.
     /// The columns are filled with default values. The value is
     ///     - scalar for scalar column
     ///     - totally sparse vector for vector column.