Adding another handful transform's extensions

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

@@ -0,0 +1,47 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
+
+using Microsoft.ML.Runtime;
+using Microsoft.ML.Runtime.Data;
+using Microsoft.ML.Transforms.Categorical;
+
+namespace Microsoft.ML
+{
+    /// <summary>
+    /// Extensions for the ValueToKeyMappingEstimator
+    /// </summary>
+   public static class ValueToKeyCatalog
+    {
+        /// <summary>
+        /// Initializes a new instance of <see cref="ValueToKeyMappingEstimator"/>.
+        /// </summary>
+        /// <param name="catalog">The categorical transform's catalog.</param>
+        /// <param name="inputColumn">Name of the column to be transformed.</param>
+        /// <param name="outputColumn">Name of the output column. If this is null '<paramref name="inputColumn"/>' will be used.</param>
+        /// <param name="maxNumTerms">Maximum number of keys to keep per column when auto-training.</param>
+        /// <param name="sort">How items should be ordered when vectorized. By default, they will be in the order encountered.
+        /// If by value items are sorted according to their default comparison, for example, text sorting will be case sensitive (for example, 'A' then 'Z' then 'a').</param>
+        public static ValueToKeyMappingEstimator MapValueToKey(this TransformsCatalog.CategoricalTransforms catalog,
+            string inputColumn,
+            string outputColumn = null,
+            int maxNumTerms = ValueToKeyMappingEstimator.Defaults.MaxNumTerms,
+            TermTransform.SortOrder sort = ValueToKeyMappingEstimator.Defaults.Sort)
+           => new ValueToKeyMappingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, maxNumTerms, sort);
+
+        /// <summary>
+        /// Initializes a new instance of <see cref="ValueToKeyMappingEstimator"/> loading the terms to use from <paramref name="file"/>.
+        /// </summary>
+        /// <param name="catalog">The categorical transform's catalog.</param>
+        /// <param name="columns">The data columns to map to keys.</param>
+        /// <param name="file">The path of the file containing the terms.</param>
+        /// <param name="termsColumn"></param>
+        /// <param name="loaderFactory"></param>
+        public static ValueToKeyMappingEstimator MapValueToKey(this TransformsCatalog.CategoricalTransforms catalog,
+            TermTransform.ColumnInfo[] columns,
+            string file = null,
+            string termsColumn = null,
+            IComponentFactory<IMultiStreamSource, IDataLoader> loaderFactory = null)
+            => new ValueToKeyMappingEstimator(CatalogUtils.GetEnvironment(catalog), columns, file, termsColumn, loaderFactory);
+    }
+}

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

@@ -24,7 +24,7 @@ public static class HashingEstimatorCatalog
         /// <param name="outputColumn">Name of the column to be transformed. If this is null '<paramref name="inputColumn"/>' 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 static HashingEstimator Hash(this TransformsCatalog.Conversions catalog, string inputColumn, string outputColumn = null,
+        public static HashingEstimator Hash(this TransformsCatalog.ConversionTransforms catalog, string inputColumn, string outputColumn = null,
             int hashBits = HashDefaults.HashBits, int invertHash = HashDefaults.InvertHash)
             => new HashingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, hashBits, invertHash);
 
@@ -33,7 +33,7 @@ public static HashingEstimator Hash(this TransformsCatalog.Conversions catalog,
         /// </summary>
         /// <param name="catalog">The transform's catalog.</param>
         /// <param name="columns">Description of dataset columns and how to process them.</param>
-        public static HashingEstimator Hash(this TransformsCatalog.Conversions catalog, params HashTransformer.ColumnInfo[] columns)
+        public static HashingEstimator Hash(this TransformsCatalog.ConversionTransforms catalog, params HashTransformer.ColumnInfo[] columns)
             => new HashingEstimator(CatalogUtils.GetEnvironment(catalog), columns);
 
         /// <summary>
@@ -43,7 +43,7 @@ public static HashingEstimator Hash(this TransformsCatalog.Conversions catalog,
         /// <param name="inputColumn">Name of the input column.</param>
         /// <param name="outputColumn">Name of the column to be transformed. If this is null '<paramref name="inputColumn"/>' will be used.</param>
         /// <param name="outputKind">Number of bits to hash into. Must be between 1 and 31, inclusive.</param>
-        public static ConvertingEstimator ConvertTo(this TransformsCatalog.Conversions catalog, string inputColumn, string outputColumn = null,
+        public static ConvertingEstimator ConvertTo(this TransformsCatalog.ConversionTransforms catalog, string inputColumn, string outputColumn = null,
             DataKind outputKind = ConvertDefaults.DefaultOutputKind)
             => new ConvertingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, outputKind);
 
@@ -52,7 +52,7 @@ public static ConvertingEstimator ConvertTo(this TransformsCatalog.Conversions c
         /// </summary>
         /// <param name="catalog">The transform's catalog.</param>
         /// <param name="columns">Description of dataset columns and how to process them.</param>
-        public static ConvertingEstimator ConvertTo(this TransformsCatalog.Conversions catalog, params ConvertingTransform.ColumnInfo[] columns)
+        public static ConvertingEstimator ConvertTo(this TransformsCatalog.ConversionTransforms catalog, params ConvertingTransform.ColumnInfo[] columns)
             => new ConvertingEstimator(CatalogUtils.GetEnvironment(catalog), columns);
     }
 
@@ -63,7 +63,7 @@ public static class ToValueCatalog
         /// </summary>
         /// <param name="catalog">The categorical transform's catalog.</param>
         /// <param name="inputColumn">Name of the input column.</param>
-        public static KeyToValueEstimator MapKeyToValue(this TransformsCatalog.Conversions catalog, string inputColumn)
+        public static KeyToValueEstimator MapKeyToValue(this TransformsCatalog.ConversionTransforms catalog, string inputColumn)
             => new KeyToValueEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn);
 
         /// <summary>
@@ -72,7 +72,7 @@ public static KeyToValueEstimator MapKeyToValue(this TransformsCatalog.Conversio
         /// </summary>
         /// <param name="catalog">The categorical transform's catalog</param>
         /// <param name="columns">The pairs of input and output columns.</param>
-        public static KeyToValueEstimator MapKeyToValue(this TransformsCatalog.Conversions catalog, params (string input, string output)[] columns)
+        public static KeyToValueEstimator MapKeyToValue(this TransformsCatalog.ConversionTransforms catalog, params (string input, string output)[] columns)
              => new KeyToValueEstimator(CatalogUtils.GetEnvironment(catalog), columns);
     }
 
@@ -86,7 +86,7 @@ public static class ToVectorCatalog
         /// </summary>
         /// <param name="catalog">The categorical transform's catalog.</param>
         /// <param name="columns">The input column to map back to vectors.</param>
-        public static KeyToVectorMappingEstimator MapKeyToVector(this TransformsCatalog.Conversions catalog,
+        public static KeyToVectorMappingEstimator MapKeyToVector(this TransformsCatalog.ConversionTransforms catalog,
             params KeyToVectorTransform.ColumnInfo[] columns)
             => new KeyToVectorMappingEstimator(CatalogUtils.GetEnvironment(catalog), columns);
 
@@ -97,7 +97,7 @@ public static KeyToVectorMappingEstimator MapKeyToVector(this TransformsCatalog.
         /// <param name="inputColumn">The name of the input column.</param>
         /// <param name="outputColumn">The name of the output column.</param>
         /// <param name="bag">Whether bagging is used for the conversion. </param>
-        public static KeyToVectorMappingEstimator MapKeyToVector(this TransformsCatalog.Conversions catalog,
+        public static KeyToVectorMappingEstimator MapKeyToVector(this TransformsCatalog.ConversionTransforms catalog,
             string inputColumn, string outputColumn = null, bool bag = KeyToVectorMappingEstimator.Defaults.Bag)
             => new KeyToVectorMappingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, bag);
     }

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

@@ -13,19 +13,19 @@ public sealed class TransformsCatalog
         internal IHostEnvironment Environment { get; }
 
         public CategoricalTransforms Categorical { get; }
-        public Conversions Conversion { get; }
+        public ConversionTransforms Conversion { get; }
         public TextTransforms Text { get; }
-        public ProjectionTransforms Projections { get; }
+        public ProjectionTransforms Projection { get; }
 
         internal TransformsCatalog(IHostEnvironment env)
         {
             Contracts.AssertValue(env);
             Environment = env;
 
             Categorical = new CategoricalTransforms(this);
-            Conversion = new Conversions(this);
+            Conversion = new ConversionTransforms(this);
             Text = new TextTransforms(this);
-            Projections = new ProjectionTransforms(this);
+            Projection = new ProjectionTransforms(this);
         }
 
         public abstract class SubCatalogBase
@@ -52,9 +52,9 @@ internal CategoricalTransforms(TransformsCatalog owner) : base(owner)
         /// <summary>
         /// The catalog of rescaling operations.
         /// </summary>
-        public sealed class Conversions : SubCatalogBase
+        public sealed class ConversionTransforms : SubCatalogBase
         {
-            public Conversions(TransformsCatalog owner) : base(owner)
+            public ConversionTransforms(TransformsCatalog owner) : base(owner)
             {
             }
         }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -0,0 +1,34 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
+
+using Microsoft.ML.Runtime;
+using Microsoft.ML.Runtime.Data;
+using Microsoft.ML.Transforms;
+
+namespace Microsoft.ML
+{
+    public static class OnnxCatalog
+    {
+        /// <summary>
+        /// Initializes a new instance of <see cref="OnnxScoringEstimator"/>.
+        /// </summary>
+        /// <param name="catalog">The transform's catalog.</param>
+        /// <param name="modelFile">The path of the file containing the ONNX model.</param>
+        /// <param name="inputColumn">The input column.</param>
+        /// <param name="outputColumn">The output column resulting from the transformation.</param>
+        public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog,
+            string modelFile,
+            string inputColumn,
+            string outputColumn)
+        => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), modelFile, inputColumn, outputColumn);
+
+        /// <summary>
+        /// Initializes a new instance of <see cref="OnnxScoringEstimator"/>.
+        /// </summary>
+        /// <param name="catalog">The transform's catalog.</param>
+        /// <param name="transformer">The ONNX transformer.</param>
+        public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog, OnnxTransform transformer)
+            => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), transformer);
+    }
+}

src/Microsoft.ML.PCA/PCACatalog.cs

@@ -0,0 +1,40 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
+
+using Microsoft.ML.Runtime;
+using Microsoft.ML.Runtime.Data;
+using Microsoft.ML.Transforms.Projections;
+
+namespace Microsoft.ML
+{
+    public static class PcaCatalog
+    {
+
+        /// <summary>Initializes a new instance of <see cref="PrincipalComponentAnalysisEstimator"/>.</summary>
+        /// <param name="catalog">The transform's catalog.</param>
+        /// <param name="inputColumn">Input column to apply PrincipalComponentAnalysis on.</param>
+        /// <param name="outputColumn">Optional output column. Null means <paramref name="inputColumn"/> is replaced.</param>
+        /// <param name="weightColumn">The name of the weight column.</param>
+        /// <param name="rank">The number of principal components.</param>
+        /// <param name="overSampling">Oversampling parameter for randomized PrincipalComponentAnalysis training.</param>
+        /// <param name="center">If enabled, data is centered to be zero mean.</param>
+        /// <param name="seed">The seed for random number generation.</param>
+        public static PrincipalComponentAnalysisEstimator ProjectToPrincipalComponents(this TransformsCatalog.ProjectionTransforms catalog,
+            string inputColumn,
+            string outputColumn = null,
+            string weightColumn = PrincipalComponentAnalysisEstimator.Defaults.WeightColumn,
+            int rank = PrincipalComponentAnalysisEstimator.Defaults.Rank,
+            int overSampling = PrincipalComponentAnalysisEstimator.Defaults.Oversampling,
+            bool center = PrincipalComponentAnalysisEstimator.Defaults.Center,
+            int? seed = null)
+            => new PrincipalComponentAnalysisEstimator(CatalogUtils.GetEnvironment(catalog),
+                inputColumn, outputColumn, weightColumn, rank, overSampling, center, seed);
+
+        /// <summary>Initializes a new instance of <see cref="PrincipalComponentAnalysisEstimator"/>.</summary>
+        /// <param name="catalog">The transform's catalog.</param>
+        /// <param name="columns">Input columns to apply PrincipalComponentAnalysis on.</param>
+        public static PrincipalComponentAnalysisEstimator ProjectToPrincipalComponents(this TransformsCatalog.ProjectionTransforms catalog, params PcaTransform.ColumnInfo[] columns)
+            => new PrincipalComponentAnalysisEstimator(CatalogUtils.GetEnvironment(catalog), columns);
+    }
+}

src/Microsoft.ML.Transforms/ExtensionsCatalog.cs

@@ -32,6 +32,31 @@ public static MissingValueIndicatorEstimator IndicateMissingValues(this Transfor
             => new MissingValueIndicatorEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn);
     }
 
+    public static class MissingValueReplacerCatalog
+    {
+        /// <summary>
+        /// Initializes a new instance of <see cref="MissingValueReplacingEstimator"/>
+        /// </summary>
+        /// <param name="catalog">The transform's catalog.</param>
+        /// <param name="inputColumn">The name of the input column.</param>
+        /// <param name="outputColumn">The optional name of the output column,
+        /// If not provided, the <paramref name="inputColumn"/> will be replaced with the results of the transforms.</param>
+        /// <param name="replacementKind">The type of replacement to use as specified in <see cref="NAReplaceTransform.ColumnInfo.ReplacementMode"/></param>
+        public static MissingValueReplacingEstimator ReplaceMissingValues(this TransformsCatalog catalog,
+            string inputColumn,
+            string outputColumn = null,
+            NAReplaceTransform.ColumnInfo.ReplacementMode replacementKind = MissingValueReplacingEstimator.Defaults.ReplacementMode)
+        => new MissingValueReplacingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, replacementKind);
+
+        /// <summary>
+        /// Initializes a new instance of <see cref="MissingValueReplacingEstimator"/>
+        /// </summary>
+        /// <param name="catalog">The transform's catalog.</param>
+        /// <param name="columns">The name of the columns to use, and per-column transformation configuraiton.</param>
+        public static MissingValueReplacingEstimator ReplaceMissingValues(this TransformsCatalog catalog, params NAReplaceTransform.ColumnInfo[] columns)
+            => new MissingValueReplacingEstimator(CatalogUtils.GetEnvironment(catalog), columns);
+    }
+
     /// <summary>
     /// Extensions for KeyToVectorMappingEstimator.
     /// </summary>

src/Microsoft.ML.Transforms/ProjectionCatalog.cs

@@ -0,0 +1,36 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+// See the LICENSE file in the project root for more information.
+
+using Microsoft.ML.Runtime;
+using Microsoft.ML.Runtime.Data;
+using Microsoft.ML.Transforms.Projections;
+
+namespace Microsoft.ML
+{
+    public static class ProjectionCatalog
+    {
+        /// <summary>
+        /// Initializes a new instance of <see cref="RandomFourierFeaturizingEstimator"/>.
+        /// </summary>
+        /// <param name="catalog">The transform's catalog.</param>
+        /// <param name="inputColumn">Name of the column to be transformed.</param>
+        /// <param name="outputColumn">Name of the output column. If this is null '<paramref name="inputColumn"/>' 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 static RandomFourierFeaturizingEstimator CreateRandomFourierFeatures(this TransformsCatalog.ProjectionTransforms catalog,
+            string inputColumn,
+            string outputColumn = null,
+            int newDim = RandomFourierFeaturizingEstimator.Defaults.NewDim,
+            bool useSin = RandomFourierFeaturizingEstimator.Defaults.UseSin)
+            => new RandomFourierFeaturizingEstimator(CatalogUtils.GetEnvironment(catalog), inputColumn, outputColumn, newDim, useSin);
+
+        /// <summary>
+        /// Initializes a new instance of <see cref="RandomFourierFeaturizingEstimator"/>.
+        /// </summary>
+        /// <param name="catalog">The transform's catalog.</param>
+        /// <param name="columns">The input columns to use for the transformation.</param>
+        public static RandomFourierFeaturizingEstimator CreateRandomFourierFeatures(this TransformsCatalog.ProjectionTransforms catalog, params RffTransform.ColumnInfo[] columns)
+            => new RandomFourierFeaturizingEstimator(CatalogUtils.GetEnvironment(catalog), columns);
+    }
+}