Multi-column mapping API for normalizer estimators.

docs/samples/Microsoft.ML.Samples/Dynamic/Normalizer.cs

@@ -56,8 +56,8 @@ public static void Example()
 
             // Composing a different pipeline if we wanted to normalize more than one column at a time. 
             // Using log scale as the normalization mode. 
-            var multiColPipeline = ml.Transforms.NormalizeMinMax("LogInduced", "Induced")
-                .Append(ml.Transforms.NormalizeMinMax("LogSpontaneous", "Spontaneous"));
+            var multiColPipeline = ml.Transforms.NormalizeLogMeanVariance(new[] { new InputOutputColumnPair("LogInduced", "Induced"), new InputOutputColumnPair("LogSpontaneous", "Spontaneous") });
+
             // The transformed data.
             var multiColtransformer = multiColPipeline.Fit(trainData);
             var multiColtransformedData = multiColtransformer.Transform(trainData);

src/Microsoft.ML.Transforms/NormalizerCatalog.cs

@@ -1,4 +1,9 @@
-using Microsoft.ML.Data;
+// 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 System.Linq;
+using Microsoft.ML.Data;
 using Microsoft.ML.Runtime;
 using Microsoft.ML.Transforms;
 
@@ -56,6 +61,20 @@ public static NormalizingEstimator NormalizeMinMax(this TransformsCatalog catalo
             return new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog), columnOptions);
         }
 
+        /// <summary>
+        /// It normalizes the data based on the observed minimum and maximum values of the data.
+        /// </summary>
+        /// <param name="catalog">The transform catalog</param>
+        /// <param name="columns">List of Output and Input column pairs.</param>
+        /// <param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
+        /// <param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
+        public static NormalizingEstimator NormalizeMinMax(this TransformsCatalog catalog, InputOutputColumnPair[] columns,
+           long maximumExampleCount = NormalizingEstimator.Defaults.MaximumExampleCount,
+           bool fixZero = NormalizingEstimator.Defaults.EnsureZeroUntouched) =>
+            new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog),
+                columns.Select(column =>
+                    new NormalizingEstimator.MinMaxColumnOptions(column.OutputColumnName, column.InputColumnName, maximumExampleCount, fixZero)).ToArray());
+
         /// <summary>
         /// It normalizes the data based on the computed mean and variance of the data.
         /// </summary>
@@ -75,6 +94,22 @@ public static NormalizingEstimator NormalizeMeanVariance(this TransformsCatalog
             return new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog), columnOptions);
         }
 
+        /// <summary>
+        /// It normalizes the data based on the computed mean and variance of the data.
+        /// </summary>
+        /// <param name="catalog">The transform catalog</param>
+        /// <param name="columns">List of Output and Input column pairs.</param>
+        /// <param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
+        /// <param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
+        /// <param name="useCdf">Whether to use CDF as the output.</param>
+        public static NormalizingEstimator NormalizeMeanVariance(this TransformsCatalog catalog, InputOutputColumnPair[] columns,
+            long maximumExampleCount = NormalizingEstimator.Defaults.MaximumExampleCount,
+            bool fixZero = NormalizingEstimator.Defaults.EnsureZeroUntouched,
+            bool useCdf = NormalizingEstimator.Defaults.MeanVarCdf) =>
+                new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog),
+                    columns.Select(column =>
+                        new NormalizingEstimator.MeanVarianceColumnOptions(column.OutputColumnName, column.InputColumnName, maximumExampleCount, fixZero, useCdf)).ToArray());
+
         /// <summary>
         /// It normalizes the data based on the computed mean and variance of the logarithm of the data.
         /// </summary>
@@ -92,6 +127,27 @@ public static NormalizingEstimator NormalizeLogMeanVariance(this TransformsCatal
             return new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog), columnOptions);
         }
 
+        /// <summary>
+        /// It normalizes the data based on the computed mean and variance of the logarithm of the data.
+        /// </summary>
+        /// <param name="catalog">The transform catalog</param>
+        /// <param name="columns">List of Output and Input column pairs.</param>
+        /// <param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
+        /// <param name="useCdf">Whether to use CDF as the output.</param>
+        /// <example>
+        /// <format type="text/markdown">
+        /// <![CDATA[
+        /// [!code-csharp[Normalize](~/../docs/samples/docs/samples/Microsoft.ML.Samples/Dynamic/Normalizer.cs)]
+        /// ]]>
+        /// </format>
+        /// </example>
+        public static NormalizingEstimator NormalizeLogMeanVariance(this TransformsCatalog catalog, InputOutputColumnPair[] columns,
+            long maximumExampleCount = NormalizingEstimator.Defaults.MaximumExampleCount,
+            bool useCdf = NormalizingEstimator.Defaults.LogMeanVarCdf) =>
+            new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog),
+                columns.Select(column =>
+                    new NormalizingEstimator.LogMeanVarianceColumnOptions(column.OutputColumnName, column.InputColumnName, maximumExampleCount, useCdf)).ToArray());
+
         /// <summary>
         /// The values are assigned into bins with equal density.
         /// </summary>
@@ -111,6 +167,22 @@ public static NormalizingEstimator NormalizeBinning(this TransformsCatalog catal
             return new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog), columnOptions);
         }
 
+        /// <summary>
+        /// The values are assigned into bins with equal density.
+        /// </summary>
+        /// <param name="catalog">The transform catalog</param>
+        /// <param name="columns">List of Output and Input column pairs.</param>
+        /// <param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
+        /// <param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
+        /// <param name="maximumBinCount">Maximum number of bins (power of 2 recommended).</param>
+        public static NormalizingEstimator NormalizeBinning(this TransformsCatalog catalog, InputOutputColumnPair[] columns,
+            long maximumExampleCount = NormalizingEstimator.Defaults.MaximumExampleCount,
+            bool fixZero = NormalizingEstimator.Defaults.EnsureZeroUntouched,
+            int maximumBinCount = NormalizingEstimator.Defaults.MaximumBinCount) =>
+            new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog),
+                columns.Select(column =>
+                    new NormalizingEstimator.BinningColumnOptions(column.OutputColumnName, column.InputColumnName, maximumExampleCount, fixZero, maximumBinCount)).ToArray());
+
         /// <summary>
         /// The values are assigned into bins based on correlation with the <paramref name="labelColumnName"/> column.
         /// </summary>
@@ -134,6 +206,27 @@ public static NormalizingEstimator NormalizeSupervisedBinning(this TransformsCat
             return new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog), columnOptions);
         }
 
+        /// <summary>
+        /// The values are assigned into bins based on correlation with the <paramref name="labelColumnName"/> column.
+        /// </summary>
+        /// <param name="catalog">The transform catalog</param>
+        /// <param name="columns">List of Output and Input column pairs.</param>
+        /// <param name="labelColumnName">Name of the label column for supervised binning.</param>
+        /// <param name="maximumExampleCount">Maximum number of examples used to train the normalizer.</param>
+        /// <param name="fixZero">Whether to map zero to zero, preserving sparsity.</param>
+        /// <param name="maximumBinCount">Maximum number of bins (power of 2 recommended).</param>
+        /// <param name="mininimumExamplesPerBin">Minimum number of examples per bin.</param>
+        public static NormalizingEstimator NormalizeSupervisedBinning(this TransformsCatalog catalog, InputOutputColumnPair[] columns,
+            string labelColumnName = DefaultColumnNames.Label,
+            long maximumExampleCount = NormalizingEstimator.Defaults.MaximumExampleCount,
+            bool fixZero = NormalizingEstimator.Defaults.EnsureZeroUntouched,
+            int maximumBinCount = NormalizingEstimator.Defaults.MaximumBinCount,
+            int mininimumExamplesPerBin = NormalizingEstimator.Defaults.MininimumBinSize) =>
+                new NormalizingEstimator(CatalogUtils.GetEnvironment(catalog),
+                    columns.Select(column =>
+                        new NormalizingEstimator.SupervisedBinningColumOptions(
+                            column.OutputColumnName, column.InputColumnName, labelColumnName, maximumExampleCount, fixZero, maximumBinCount, mininimumExamplesPerBin)).ToArray());
+
         /// <summary>
         /// Normalize (rescale) columns according to specified custom parameters.
         /// </summary>