Added convenience constructors for set of transforms (Part 2).

Author: zeahmed

src/Microsoft.ML.Data/Transforms/ChooseColumnsTransform.cs

@@ -442,6 +442,18 @@ private static VersionInfo GetVersionInfo()
 
         private const string RegistrationName = "ChooseColumns";
 
+        /// <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 selected column.  If this is null '<paramref name="name"/>' will be used.</param>
+        public ChooseColumnsTransform(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>

src/Microsoft.ML.Data/Transforms/ConvertTransform.cs

@@ -108,6 +108,16 @@ public bool TryUnparse(StringBuilder sb)
 
         public class Arguments : TransformInputBase
         {
+            public Arguments()
+            {
+
+            }
+
+            public Arguments(string name, string source)
+            {
+                Column = new[] { new Column() { Source = source ?? name, Name = name } };
+            }
+
             [Argument(ArgumentType.Multiple | ArgumentType.Required, HelpText = "New column definition(s) (optional form: name:type:src)", ShortName = "col", SortOrder = 1)]
             public Column[] Column;
 
@@ -169,6 +179,25 @@ private static VersionInfo GetVersionInfo()
         // This is parallel to Infos.
         private readonly ColInfoEx[] _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 converted.  If this is null '<paramref name="name"/>' will be used.</param>
+        /// <param name="resultType">The expected type of the converted column.</param>
+        /// <param name="keyRange">For a key column, this defines the range of values.</param>
+        public ConvertTransform(IHostEnvironment env,
+            IDataView input,
+            string name,
+            string source = null,
+            DataKind? resultType = null,
+            KeyRange keyRange = null)
+            : this(env, new Arguments(name, source) { ResultType = resultType, KeyRange = keyRange }, input)
+        {
+        }
+
         public ConvertTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, RegistrationName, env.CheckRef(args, nameof(args)).Column,
                 input, null)

src/Microsoft.ML.Data/Transforms/DropSlotsTransform.cs

@@ -216,6 +216,18 @@ public ColInfoEx(SlotDropper slotDropper, bool suppressed, ColumnType typeDst, i
 
         private readonly ColInfoEx[] _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 input column.  If this is null '<paramref name="name"/>' will be used.</param>
+        public DropSlotsTransform(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>

src/Microsoft.ML.Data/Transforms/GenerateNumberTransform.cs

@@ -77,16 +77,22 @@ private bool TryParse(string str)
             }
         }
 
+        private static class Defaults
+        {
+            public const bool UseCounter = false;
+            public const uint Seed = 42;
+        }
+
         public sealed class Arguments : TransformInputBase
         {
             [Argument(ArgumentType.Multiple | ArgumentType.Required, HelpText = "New column definition(s) (optional form: name:seed)", ShortName = "col", SortOrder = 1)]
             public Column[] Column;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Use an auto-incremented integer starting at zero instead of a random number", ShortName = "cnt")]
-            public bool UseCounter;
+            public bool UseCounter = Defaults.UseCounter;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "The random seed")]
-            public uint Seed = 42;
+            public uint Seed = Defaults.Seed;
         }
 
         private sealed class Bindings : ColumnBindingsBase
@@ -250,6 +256,18 @@ private static VersionInfo GetVersionInfo()
 
         private const string RegistrationName = "GenerateNumber";
 
+        /// <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="useCounter">Use an auto-incremented integer starting at zero instead of a random number.</param>
+        public GenerateNumberTransform(IHostEnvironment env, IDataView input, string name, bool useCounter = Defaults.UseCounter)
+            : this(env, new Arguments() { Column = new[] { new Column() { Name = name } }, UseCounter = useCounter }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>

src/Microsoft.ML.Data/Transforms/HashTransform.cs

@@ -33,26 +33,48 @@ public sealed class HashTransform : OneToOneTransformBase, ITransformTemplate
         public const int NumBitsMin = 1;
         public const int NumBitsLim = 32;
 
+        private static class Defaults
+        {
+            public const int HashBits = NumBitsLim - 1;
+            public const uint Seed = 314489979;
+            public const bool Ordered = false;
+            public const int InvertHash = 0;
+        }
+
         public sealed class Arguments
         {
+            public Arguments()
+            {
+
+            }
+
+            public Arguments(string name, string source)
+            {
+                Column = new[] { new Column(){
+                    Source = source ?? name,
+                    Name = name
+                    }
+                };
+            }
+
             [Argument(ArgumentType.Multiple, HelpText = "New column definition(s) (optional form: name:src)", ShortName = "col",
                 SortOrder = 1)]
             public Column[] Column;
 
             [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;
+            public bool Ordered = Defaults.Ordered;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Limit the number of keys used to generate the slot name to this many. 0 means no invert hashing, -1 means no limit.",
                 ShortName = "ih")]
-            public int InvertHash;
+            public int InvertHash = Defaults.InvertHash;
         }
 
         public sealed class Column : OneToOneColumn
@@ -234,6 +256,25 @@ public override void Save(ModelSaveContext ctx)
             TextModelHelper.SaveAll(Host, ctx, Infos.Length, _keyValues);
         }
 
+        /// <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="hashBits">Number of bits to hash into. Must be between 1 and 31, inclusive.</param>
+        /// <param name="invertHash">Limit the number of keys used to generate the slot name to this many. 0 means no invert hashing, -1 means no limit.</param>
+        public HashTransform(IHostEnvironment env,
+            IDataView input,
+            string name,
+            string source = null,
+            int hashBits = Defaults.HashBits,
+            int invertHash = Defaults.InvertHash)
+            : this(env, new Arguments(name, source) { HashBits = hashBits, InvertHash = invertHash }, input)
+        {
+        }
+
         public HashTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(Contracts.CheckRef(env, nameof(env)), RegistrationName, env.CheckRef(args, nameof(args)).Column,
                 input, TestType)

src/Microsoft.ML.Data/Transforms/KeyToValueTransform.cs

@@ -73,6 +73,19 @@ private static VersionInfo GetVersionInfo()
         private readonly ColumnType[] _types;
         private KeyToValueMap[] _kvMaps;
 
+        /// <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 input column.  If this is null '<paramref name="name"/>' will be used.</param>
+        public KeyToValueTransform(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>

src/Microsoft.ML.Data/Transforms/KeyToVectorTransform.cs

@@ -70,14 +70,19 @@ public bool TryUnparse(StringBuilder sb)
             }
         }
 
+        private static class Defaults
+        {
+            public const bool Bag = false;
+        }
+
         public sealed class Arguments
         {
             [Argument(ArgumentType.Multiple, HelpText = "New column definition(s) (optional form: name:src)", ShortName = "col", SortOrder = 1)]
             public Column[] Column;
 
             [Argument(ArgumentType.AtMostOnce,
                 HelpText = "Whether to combine multiple indicator vectors into a single bag vector instead of concatenating them. This is only relevant when the input is a vector.")]
-            public bool Bag;
+            public bool Bag = Defaults.Bag;
         }
 
         internal const string Summary = "Converts a key column to an indicator vector.";
@@ -112,6 +117,23 @@ private static VersionInfo GetVersionInfo()
         private readonly bool[] _concat;
         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 input column.  If this is null '<paramref name="name"/>' will be used.</param>
+        /// <param name="bag">Whether to combine multiple indicator vectors into a single bag vector instead of concatenating them. This is only relevant when the input is a vector.</param>
+        public KeyToVectorTransform(IHostEnvironment env,
+            IDataView input,
+            string name,
+            string source = null,
+            bool bag = Defaults.Bag)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } }, Bag = bag }, input)
+        {
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>

src/Microsoft.ML.Data/Transforms/LabelConvertTransform.cs

@@ -64,6 +64,18 @@ private static VersionInfo GetVersionInfo()
         private const string RegistrationName = "LabelConvert";
         private VectorType _slotType;
 
+        /// <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 input column.  If this is null '<paramref name="name"/>' will be used.</param>
+        public LabelConvertTransform(IHostEnvironment env, IDataView input, string name, string source = null)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } } }, input)
+        {
+        }
+
         public LabelConvertTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, RegistrationName, Contracts.CheckRef(args, nameof(args)).Column, input, RowCursorUtils.TestGetLabelGetter)
         {

src/Microsoft.ML.Data/Transforms/LabelIndicatorTransform.cs

@@ -64,13 +64,18 @@ public bool TryUnparse(StringBuilder sb)
             }
         }
 
+        private static class Defaults
+        {
+            public const int ClassIndex = 0;
+        }
+
         public sealed class Arguments : TransformInputBase
         {
             [Argument(ArgumentType.Multiple, HelpText = "New column definition(s) (optional form: name:src)", ShortName = "col", SortOrder = 1)]
             public Column[] Column;
 
             [Argument(ArgumentType.AtMostOnce, HelpText = "Label of the positive class.", ShortName = "index")]
-            public int ClassIndex;
+            public int ClassIndex = Defaults.ClassIndex;
         }
 
         public static LabelIndicatorTransform Create(IHostEnvironment env,
@@ -111,6 +116,23 @@ private static string TestIsMulticlassLabel(ColumnType type)
             return $"Label column type is not supported for binary remapping: {type}. Supported types: key, float, double.";
         }
 
+        /// <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 input column.  If this is null '<paramref name="name"/>' will be used.</param>
+        /// <param name="classIndex">Label of the positive class.</param>
+        public LabelIndicatorTransform(IHostEnvironment env,
+            IDataView input,
+            string name,
+            string source = null,
+            int classIndex = Defaults.ClassIndex)
+            : this(env, new Arguments() { Column = new[] { new Column() { Source = source ?? name, Name = name } }, ClassIndex = classIndex }, input)
+        {
+        }
+
         public LabelIndicatorTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, LoadName, Contracts.CheckRef(args, nameof(args)).Column,
                 input, TestIsMulticlassLabel)

src/Microsoft.ML.Data/Transforms/RangeFilter.cs

@@ -77,6 +77,19 @@ private static VersionInfo GetVersionInfo()
         private readonly bool _includeMin;
         private readonly bool _includeMax;
 
+        /// <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 input column.</param>
+        /// <param name="minimum">Minimum value (0 to 1 for key types).</param>
+        /// <param name="maximum">Maximum value (0 to 1 for key types).</param>
+        public RangeFilter(IHostEnvironment env, IDataView input, string column, Double? minimum = null, Double? maximum = null)
+            : this(env, new Arguments() { Column = column, Min = minimum, Max = maximum }, input)
+        {
+        }
+
         public RangeFilter(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, RegistrationName, input)
         {