Clean static part for previous projection catalog

Scrubbing normalization again

Author: wschin

docs/code/MlNetCookBook.md

@@ -595,7 +595,7 @@ As a general rule, *if you use a parametric learner, you need to make sure your
 
 ML.NET offers several built-in scaling algorithms, or 'normalizers':
 - MinMax normalizer: for each feature, we learn the minimum and maximum value of it, and then linearly rescale it so that the values fit between -1 and 1.
-- MeanVar normalizer: for each feature, compute the mean and variance, and then linearly rescale it to zero-mean, unit-variance.
+- MeanVariance normalizer: for each feature, compute the mean and variance, and then linearly rescale it to zero-mean, unit-variance.
 - CDF normalizer: for each feature, compute the mean and variance, and then replace each value `x` with `Cdf(x)`, where `Cdf` is the cumulative density function of normal distribution with these mean and variance. 
 - Binning normalizer: discretize the feature value into `N` 'buckets', and then replace each value with the index of the bucket, divided by `N-1`.
 
@@ -630,8 +630,8 @@ var trainData = mlContext.Data.LoadFromTextFile<IrisInputAllFeatures>(dataPath,
 var pipeline =
     mlContext.Transforms.Normalize(
         new NormalizingEstimator.MinMaxColumnOptions("MinMaxNormalized", "Features", fixZero: true),
-        new NormalizingEstimator.MeanVarColumnOptions("MeanVarNormalized", "Features", fixZero: true),
-        new NormalizingEstimator.BinningColumnOptions("BinNormalized", "Features", numBins: 256));
+        new NormalizingEstimator.MeanVarianceColumnOptions("MeanVarNormalized", "Features", fixZero: true),
+        new NormalizingEstimator.BinningColumnOptions("BinNormalized", "Features", binCount: 256));
 
 // Let's train our pipeline of normalizers, and then apply it to the same data.
 var normalizedData = pipeline.Fit(trainData).Transform(trainData);

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

@@ -55,7 +55,7 @@ public static void Example()
             //0.165 0.117 -0.547  0.014
 
             // A pipeline to project Features column into L-p normalized vector.
-            var lpNormalizePipeline = ml.Transforms.LpNormalize(nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features), normKind: Transforms.LpNormalizingEstimatorBase.NormFunction.L1);
+            var lpNormalizePipeline = ml.Transforms.LpNormalize(nameof(SamplesUtils.DatasetUtils.SampleVectorOfNumbersData.Features), norm: Transforms.LpNormalizingEstimatorBase.NormFunction.L1);
             // The transformed (projected) data.
             transformedData = lpNormalizePipeline.Fit(trainData).Transform(trainData);
             // Getting the data of the newly created column, so we can preview it.

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

@@ -11,7 +11,6 @@
 using Microsoft.ML;
 using Microsoft.ML.CommandLine;
 using Microsoft.ML.Data;
-using Microsoft.ML.EntryPoints;
 using Microsoft.ML.Internal.Internallearn;
 using Microsoft.ML.Model.OnnxConverter;
 using Microsoft.ML.Model.Pfa;
@@ -51,7 +50,7 @@ internal sealed partial class NormalizeTransform
         public abstract class ColumnBase : OneToOneColumn
         {
             [Argument(ArgumentType.AtMostOnce, HelpText = "Max number of examples used to train the normalizer", ShortName = "maxtrain")]
-            public long? MaxTrainingExamples;
+            public long? MaximumExampleCount;
 
             private protected ColumnBase()
             {
@@ -60,7 +59,7 @@ private protected ColumnBase()
             private protected override bool TryUnparseCore(StringBuilder sb)
             {
                 Contracts.AssertValue(sb);
-                if (MaxTrainingExamples != null)
+                if (MaximumExampleCount != null)
                     return false;
                 return base.TryUnparseCore(sb);
             }
@@ -291,7 +290,7 @@ internal static IDataTransform Create(IHostEnvironment env, MinMaxArguments args
                 .Select(col => new NormalizingEstimator.MinMaxColumnOptions(
                     col.Name,
                     col.Source ?? col.Name,
-                    col.MaxTrainingExamples ?? args.MaxTrainingExamples,
+                    col.MaximumExampleCount ?? args.MaxTrainingExamples,
                     col.FixZero ?? args.FixZero))
                 .ToArray();
             var normalizer = new NormalizingEstimator(env, columns);
@@ -306,10 +305,10 @@ internal static IDataTransform Create(IHostEnvironment env, MeanVarArguments arg
             env.CheckValue(args.Columns, nameof(args.Columns));
 
             var columns = args.Columns
-                .Select(col => new NormalizingEstimator.MeanVarColumnOptions(
+                .Select(col => new NormalizingEstimator.MeanVarianceColumnOptions(
                     col.Name,
                     col.Source ?? col.Name,
-                    col.MaxTrainingExamples ?? args.MaxTrainingExamples,
+                    col.MaximumExampleCount ?? args.MaxTrainingExamples,
                     col.FixZero ?? args.FixZero))
                 .ToArray();
             var normalizer = new NormalizingEstimator(env, columns);
@@ -326,10 +325,10 @@ internal static IDataTransform Create(IHostEnvironment env, LogMeanVarArguments
             env.CheckValue(args.Columns, nameof(args.Columns));
 
             var columns = args.Columns
-                .Select(col => new NormalizingEstimator.LogMeanVarColumnOptions(
+                .Select(col => new NormalizingEstimator.LogMeanVarianceColumnOptions(
                     col.Name,
                     col.Source ?? col.Name,
-                    col.MaxTrainingExamples ?? args.MaxTrainingExamples,
+                    col.MaximumExampleCount ?? args.MaxTrainingExamples,
                     args.UseCdf))
                 .ToArray();
             var normalizer = new NormalizingEstimator(env, columns);
@@ -349,7 +348,7 @@ internal static IDataTransform Create(IHostEnvironment env, BinArguments args, I
                 .Select(col => new NormalizingEstimator.BinningColumnOptions(
                     col.Name,
                     col.Source ?? col.Name,
-                    col.MaxTrainingExamples ?? args.MaxTrainingExamples,
+                    col.MaximumExampleCount ?? args.MaxTrainingExamples,
                     col.FixZero ?? args.FixZero,
                     col.NumBins ?? args.NumBins))
                 .ToArray();
@@ -926,7 +925,7 @@ public static IColumnFunctionBuilder CreateBuilder(MinMaxArguments args, IHost h
                 return CreateBuilder(new NormalizingEstimator.MinMaxColumnOptions(
                     args.Columns[icol].Name,
                     args.Columns[icol].Source ?? args.Columns[icol].Name,
-                    args.Columns[icol].MaxTrainingExamples ?? args.MaxTrainingExamples,
+                    args.Columns[icol].MaximumExampleCount ?? args.MaxTrainingExamples,
                     args.Columns[icol].FixZero ?? args.FixZero), host, srcIndex, srcType, cursor);
             }
 
@@ -959,15 +958,15 @@ public static IColumnFunctionBuilder CreateBuilder(MeanVarArguments args, IHost
                 Contracts.AssertValue(host);
                 host.AssertValue(args);
 
-                return CreateBuilder(new NormalizingEstimator.MeanVarColumnOptions(
+                return CreateBuilder(new NormalizingEstimator.MeanVarianceColumnOptions(
                     args.Columns[icol].Name,
                     args.Columns[icol].Source ?? args.Columns[icol].Name,
-                    args.Columns[icol].MaxTrainingExamples ?? args.MaxTrainingExamples,
+                    args.Columns[icol].MaximumExampleCount ?? args.MaxTrainingExamples,
                     args.Columns[icol].FixZero ?? args.FixZero,
                     args.UseCdf), host, srcIndex, srcType, cursor);
             }
 
-            public static IColumnFunctionBuilder CreateBuilder(NormalizingEstimator.MeanVarColumnOptions column, IHost host,
+            public static IColumnFunctionBuilder CreateBuilder(NormalizingEstimator.MeanVarianceColumnOptions column, IHost host,
                 int srcIndex, DataViewType srcType, DataViewRowCursor cursor)
             {
                 Contracts.AssertValue(host);
@@ -999,14 +998,14 @@ public static IColumnFunctionBuilder CreateBuilder(LogMeanVarArguments args, IHo
                 Contracts.AssertValue(host);
                 host.AssertValue(args);
 
-                return CreateBuilder(new NormalizingEstimator.LogMeanVarColumnOptions(
+                return CreateBuilder(new NormalizingEstimator.LogMeanVarianceColumnOptions(
                     args.Columns[icol].Name,
                     args.Columns[icol].Source ?? args.Columns[icol].Name,
-                    args.Columns[icol].MaxTrainingExamples ?? args.MaxTrainingExamples,
+                    args.Columns[icol].MaximumExampleCount ?? args.MaxTrainingExamples,
                     args.UseCdf), host, srcIndex, srcType, cursor);
             }
 
-            public static IColumnFunctionBuilder CreateBuilder(NormalizingEstimator.LogMeanVarColumnOptions column, IHost host,
+            public static IColumnFunctionBuilder CreateBuilder(NormalizingEstimator.LogMeanVarianceColumnOptions column, IHost host,
                 int srcIndex, DataViewType srcType, DataViewRowCursor cursor)
             {
                 Contracts.AssertValue(host);
@@ -1041,7 +1040,7 @@ public static IColumnFunctionBuilder CreateBuilder(BinArguments args, IHost host
                 return CreateBuilder(new NormalizingEstimator.BinningColumnOptions(
                     args.Columns[icol].Name,
                     args.Columns[icol].Source ?? args.Columns[icol].Name,
-                    args.Columns[icol].MaxTrainingExamples ?? args.MaxTrainingExamples,
+                    args.Columns[icol].MaximumExampleCount ?? args.MaxTrainingExamples,
                     args.Columns[icol].FixZero ?? args.FixZero,
                     args.Columns[icol].NumBins ?? args.NumBins), host, srcIndex, srcType, cursor);
             }
@@ -1091,7 +1090,7 @@ public static IColumnFunctionBuilder CreateBuilder(SupervisedBinArguments args,
                         args.Columns[icol].Name,
                         args.Columns[icol].Source ?? args.Columns[icol].Name,
                         args.LabelColumn ?? DefaultColumnNames.Label,
-                        args.Columns[icol].MaxTrainingExamples ?? args.MaxTrainingExamples,
+                        args.Columns[icol].MaximumExampleCount ?? args.MaxTrainingExamples,
                         args.Columns[icol].FixZero ?? args.FixZero,
                         args.Columns[icol].NumBins ?? args.NumBins,
                         args.MinBinSize),