Added convenience constructor for set of transforms (dotnet#371).

zeahmed · zeahmed · commit bfac765e12e8 · 2018-06-25T11:45:19.000-07:00
diff --git a/src/Microsoft.ML.Data/Transforms/ConcatTransform.cs b/src/Microsoft.ML.Data/Transforms/ConcatTransform.cs
@@ -527,6 +527,28 @@ private static VersionInfo GetVersionInfo()
 
         public override ISchema Schema => _bindings;
 
+        public ConcatTransform(IHostEnvironment env, IDataView input, string outputColumn, params string[] inputColumns)
+            : base(env, RegistrationName, input)
+        {
+            var cols = new Column[1];
+            cols[0] = new Column()
+            {
+                Name = outputColumn,
+                Source = inputColumns
+            };
+
+            var args = new Arguments()
+            {
+                Column = cols
+            };
+            Host.CheckValue(args, nameof(args));
+            Host.CheckUserArg(Utils.Size(args.Column) > 0, nameof(args.Column));
+            for (int i = 0; i < args.Column.Length; i++)
+                Host.CheckUserArg(Utils.Size(args.Column[i].Source) > 0, nameof(args.Column));
+
+            _bindings = new Bindings(args.Column, null, Source.Schema);
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Data/Transforms/CopyColumnsTransform.cs b/src/Microsoft.ML.Data/Transforms/CopyColumnsTransform.cs
@@ -64,6 +64,32 @@ private static VersionInfo GetVersionInfo()
 
         private const string RegistrationName = "CopyColumns";
 
+        public static CopyColumnsTransform Create(IHostEnvironment env, IDataView input, params string[] inputColumns)
+        {
+            var inputOutputColumns = new(string inputColumn, string outputColumn)[inputColumns.Length];
+            for (int i = 0; i < inputColumns.Length; i++)
+            {
+                inputOutputColumns[i].inputColumn = inputOutputColumns[i].outputColumn = inputColumns[i];
+            }
+            return Create(env, input, inputOutputColumns);
+        }
+
+        public static CopyColumnsTransform Create(IHostEnvironment env, IDataView input, params (string inputColumn, string outputColumn)[] inputOutputColumns)
+        {
+            Column[] cols = new Column[inputOutputColumns.Length];
+            for (int i = 0; i < inputOutputColumns.Length; i++)
+            {
+                cols[i] = new Column();
+                cols[i].Source = inputOutputColumns[i].inputColumn;
+                cols[i].Name = inputOutputColumns[i].outputColumn;
+            }
+            var args = new Arguments()
+            {
+                Column = cols
+            };
+            return new CopyColumnsTransform(env,args,input);
+        }
+
         public CopyColumnsTransform(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, RegistrationName, env.CheckRef(args, nameof(args)).Column, input, null)
         {
diff --git a/src/Microsoft.ML.Data/Transforms/DropColumnsTransform.cs b/src/Microsoft.ML.Data/Transforms/DropColumnsTransform.cs
@@ -237,6 +237,16 @@ private static VersionInfo GetVersionInfo()
         private const string DropRegistrationName = "DropColumns";
         private const string KeepRegistrationName = "KeepColumns";
 
+        public DropColumnsTransform CreateColumnDroper(IHostEnvironment env, IDataView input, params string[] columnsToDrop)
+        {
+            return new DropColumnsTransform(env, new Arguments() { Column = columnsToDrop }, input);
+        }
+
+        public static DropColumnsTransform CreateColumnSelector(IHostEnvironment env, IDataView input, params string[] columnsToKeep)
+        {
+            return new DropColumnsTransform(env, new KeepArguments() { Column = columnsToKeep }, input);
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Data/Transforms/NAFilter.cs b/src/Microsoft.ML.Data/Transforms/NAFilter.cs
@@ -72,6 +72,12 @@ private static VersionInfo GetVersionInfo()
         private readonly bool _complement;
         private const string RegistrationName = "MissingValueFilter";
 
+        public NAFilter(IHostEnvironment env, IDataView input, params string[] inputColumns)
+            : this(env, new Arguments() { Column = inputColumns}, input)
+        {
+
+        }
+
         public NAFilter(IHostEnvironment env, Arguments args, IDataView input)
             : base(env, RegistrationName, input)
         {
diff --git a/src/Microsoft.ML.Transforms/BootstrapSampleTransform.cs b/src/Microsoft.ML.Transforms/BootstrapSampleTransform.cs
@@ -76,6 +76,12 @@ public BootstrapSampleTransform(IHostEnvironment env, Arguments args, IDataView
             _poolSize = args.PoolSize;
         }
 
+        public BootstrapSampleTransform(IHostEnvironment env, IDataView input, bool complement = false, uint? seed = null, bool shuffleInput = true, int poolSize = 1000)
+            : this(env, new Arguments() { Complement = complement, Seed = seed, ShuffleInput = shuffleInput, PoolSize = poolSize }, input)
+        {
+            
+        }
+
         private BootstrapSampleTransform(IHost host, ModelLoadContext ctx, IDataView input)
             : base(host, input)
         {
diff --git a/src/Microsoft.ML.Transforms/CategoricalHashTransform.cs b/src/Microsoft.ML.Transforms/CategoricalHashTransform.cs
@@ -120,6 +120,32 @@ public sealed class Arguments : TransformInputBase
 
         public const string UserName = "Categorical Hash Transform";
 
+        public static IDataTransform Create(IHostEnvironment env, IDataView input, params string[] inputColumns)
+        {
+            var inputOutputColumns = new(string inputColumn, string outputColumn)[inputColumns.Length];
+            for (int i = 0; i < inputColumns.Length; i++)
+            {
+                inputOutputColumns[i].inputColumn = inputOutputColumns[i].outputColumn = inputColumns[i];
+            }
+            return Create(env, input, inputOutputColumns);
+        }
+
+        public static IDataTransform Create(IHostEnvironment env, IDataView input, params (string inputColumn, string outputColumn)[] inputOutputColumns)
+        {
+            Column[] cols = new Column[inputOutputColumns.Length];
+            for (int i = 0; i < inputOutputColumns.Length; i++)
+            {
+                cols[i] = new Column();
+                cols[i].Source = inputOutputColumns[i].inputColumn;
+                cols[i].Name = inputOutputColumns[i].outputColumn;
+            }
+            var args = new Arguments()
+            {
+                Column = cols
+            };
+            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/CategoricalTransform.cs b/src/Microsoft.ML.Transforms/CategoricalTransform.cs
@@ -118,6 +118,32 @@ public Arguments()
 
         public const string UserName = "Categorical Transform";
 
+        public static IDataTransform Create(IHostEnvironment env, IDataView input, params string[] inputColumns)
+        {
+            var inputOutputColumns = new (string inputColumn, string outputColumn)[inputColumns.Length];
+            for (int i = 0; i < inputColumns.Length; i++)
+            {
+                inputOutputColumns[i].inputColumn = inputOutputColumns[i].outputColumn = inputColumns[i];
+            }
+            return Create(env, input, inputOutputColumns);
+        }
+
+        public static IDataTransform Create(IHostEnvironment env, IDataView input, params (string inputColumn, string outputColumn)[] inputOutputColumns)
+        {
+            Column[] cols = new Column[inputOutputColumns.Length];
+            for (int i = 0; i < inputOutputColumns.Length; i++)
+            {
+                cols[i] = new Column();
+                cols[i].Source = inputOutputColumns[i].inputColumn;
+                cols[i].Name = inputOutputColumns[i].outputColumn;
+            }
+            var args = new Arguments()
+            {
+                Column = cols
+            };
+            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/CountFeatureSelection.cs b/src/Microsoft.ML.Transforms/CountFeatureSelection.cs
@@ -39,6 +39,16 @@ public sealed class Arguments : TransformInputBase
 
         internal static string RegistrationName = "CountFeatureSelectionTransform";
 
+        public static IDataTransform Create(IHostEnvironment env, IDataView input, long count = 1, params string[] columns)
+        {
+            var args = new Arguments()
+            {
+                Column = columns,
+                Count = count
+            };
+            return Create(env, args, input);
+        }
+
         /// <summary>
         /// Create method corresponding to SignatureDataTransform.
         /// </summary>
diff --git a/src/Microsoft.ML.Transforms/GcnTransform.cs b/src/Microsoft.ML.Transforms/GcnTransform.cs
@@ -237,6 +237,37 @@ private static VersionInfo GetVersionInfo()
 
         private readonly ColInfoEx[] _exes;
 
+        public static IDataTransform CreateGlobalContrastNormalizer(IHostEnvironment env, IDataView input, params string[] inputColumns)
+        {
+            var inputOutputColumns = new(string inputColumn, string outputColumn)[inputColumns.Length];
+            for (int i = 0; i < inputColumns.Length; i++)
+            {
+                inputOutputColumns[i].inputColumn = inputOutputColumns[i].outputColumn = inputColumns[i];
+            }
+            return CreateGlobalContrastNormalizer(env, input, inputOutputColumns);
+        }
+
+        public static IDataTransform CreateGlobalContrastNormalizer(IHostEnvironment env, IDataView input, params (string inputColumn, string outputColumn)[] inputOutputColumns)
+        {
+            GcnColumn[] cols = new GcnColumn[inputOutputColumns.Length];
+            for (int i = 0; i < inputOutputColumns.Length; i++)
+            {
+                cols[i] = new GcnColumn();
+                cols[i].Source = inputOutputColumns[i].inputColumn;
+                cols[i].Name = inputOutputColumns[i].outputColumn;
+            }
+            var args = new GcnArguments()
+            {
+                Column = cols
+            };
+            return new LpNormNormalizerTransform(env, args, input);
+        }
+
+        public static IDataTransform CreateGlobalContrastNormalizer(IHostEnvironment env, IDataView input, GcnArguments args)
+        {
+            return new LpNormNormalizerTransform(env, args, input);
+        }
+
         /// <summary>
         /// Public constructor corresponding to SignatureDataTransform.
         /// </summary>
@@ -263,9 +294,40 @@ public LpNormNormalizerTransform(IHostEnvironment env, GcnArguments args, IDataV
             SetMetadata();
         }
 
+        public static IDataTransform CreateLpNormNormalizer(IHostEnvironment env, IDataView input, params string[] inputColumns)
+        {
+            var inputOutputColumns = new(string inputColumn, string outputColumn)[inputColumns.Length];
+            for (int i = 0; i < inputColumns.Length; i++)
+            {
+                inputOutputColumns[i].inputColumn = inputOutputColumns[i].outputColumn = inputColumns[i];
+            }
+            return CreateLpNormNormalizer(env, input, inputOutputColumns);
+        }
+
+        public static IDataTransform CreateLpNormNormalizer(IHostEnvironment env, IDataView input, params (string inputColumn, string outputColumn)[] inputOutputColumns)
+        {
+            Column[] cols = new Column[inputOutputColumns.Length];
+            for (int i = 0; i < inputOutputColumns.Length; i++)
+            {
+                cols[i] = new Column();
+                cols[i].Source = inputOutputColumns[i].inputColumn;
+                cols[i].Name = inputOutputColumns[i].outputColumn;
+            }
+            var args = new Arguments()
+            {
+                Column = cols
+            };
+            return new LpNormNormalizerTransform(env, args, input);
+        }
+
+        public static IDataTransform CreateLpNormNormalizer(IHostEnvironment env, IDataView input, Arguments args)
+        {
+            return new LpNormNormalizerTransform(env, args, input);
+        }
+
         public LpNormNormalizerTransform(IHostEnvironment env, Arguments args, IDataView input)
-            : base(env, RegistrationName, env.CheckRef(args, nameof(args)).Column,
-                input, TestIsFloatVector)
+        : base(env, RegistrationName, env.CheckRef(args, nameof(args)).Column,
+            input, TestIsFloatVector)
         {
             Host.AssertNonEmpty(Infos);
             Host.Assert(Infos.Length == Utils.Size(args.Column));
diff --git a/src/Microsoft.ML.Transforms/NormalizeColumn.cs b/src/Microsoft.ML.Transforms/NormalizeColumn.cs

Original file line number	Diff line number	Diff line change
`@@ -76,6 +76,12 @@ public BootstrapSampleTransform(IHostEnvironment env, Arguments args, IDataView`
`76`	`76`	`_poolSize = args.PoolSize;`
`77`	`77`	`}`
`78`	`78`
	`79`	`+ public BootstrapSampleTransform(IHostEnvironment env, IDataView input, bool complement = false, uint? seed = null, bool shuffleInput = true, int poolSize = 1000)`
	`80`	`+ : this(env, new Arguments() { Complement = complement, Seed = seed, ShuffleInput = shuffleInput, PoolSize = poolSize }, input)`
	`81`	`+ {`
	`82`	`+`
	`83`	`+ }`
	`84`	`+`
`79`	`85`	`private BootstrapSampleTransform(IHost host, ModelLoadContext ctx, IDataView input)`
`80`	`86`	`: base(host, input)`
`81`	`87`	`{`