Lockdown Microsoft.ML.PCA public surface

src/Microsoft.ML.PCA/AssemblyInfo.cs

@@ -0,0 +1,8 @@
+// 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.Runtime.CompilerServices;
+using Microsoft.ML;
+
+[assembly: InternalsVisibleTo(assemblyName: "Microsoft.ML.Tests" + PublicKey.TestValue)]

src/Microsoft.ML.PCA/PcaTransformer.cs

@@ -17,7 +17,7 @@
 using Microsoft.ML.Numeric;
 using Microsoft.ML.Transforms.Projections;
 
-[assembly: LoadableClass(PcaTransformer.Summary, typeof(IDataTransform), typeof(PcaTransformer), typeof(PcaTransformer.Arguments), typeof(SignatureDataTransform),
+[assembly: LoadableClass(PcaTransformer.Summary, typeof(IDataTransform), typeof(PcaTransformer), typeof(PcaTransformer.Options), typeof(SignatureDataTransform),
     PcaTransformer.UserName, PcaTransformer.LoaderSignature, PcaTransformer.ShortName)]
 
 [assembly: LoadableClass(PcaTransformer.Summary, typeof(IDataTransform), typeof(PcaTransformer), null, typeof(SignatureLoadDataTransform),
@@ -36,10 +36,10 @@ namespace Microsoft.ML.Transforms.Projections
     /// <include file='doc.xml' path='doc/members/member[@name="PCA"]/*' />
     public sealed class PcaTransformer : OneToOneTransformerBase
     {
-        public sealed class Arguments : TransformInputBase
+        internal sealed class Options : TransformInputBase
         {
-            [Argument(ArgumentType.Multiple | ArgumentType.Required, HelpText = "New column definition(s) (optional form: name:src)", Name = "Column", ShortName = "col", SortOrder = 1)]
-            public Column[] Columns;
+            [Argument(ArgumentType.Multiple | ArgumentType.Required, HelpText = "New column definition(s) (optional form: name:src)", ShortName = "col", SortOrder = 1)]
+            public Column[] Column;
 
             [Argument(ArgumentType.Multiple, HelpText = "The name of the weight column", ShortName = "weight", Purpose = SpecialPurpose.ColumnName)]
             public string WeightColumn = PrincipalComponentAnalysisEstimator.Defaults.WeightColumn;
@@ -287,13 +287,13 @@ private static IRowMapper Create(IHostEnvironment env, ModelLoadContext ctx, Sch
             => Create(env, ctx).MakeRowMapper(inputSchema);
 
         // Factory method for SignatureDataTransform.
-        private static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
+        private static IDataTransform Create(IHostEnvironment env, Options args, IDataView input)
         {
             Contracts.CheckValue(env, nameof(env));
             env.CheckValue(args, nameof(args));
             env.CheckValue(input, nameof(input));
-            env.CheckValue(args.Columns, nameof(args.Columns));
-            var cols = args.Columns.Select(item => new ColumnInfo(
+            env.CheckValue(args.Column, nameof(args.Column));
+            var cols = args.Column.Select(item => new ColumnInfo(
                         item.Name,
                         item.Source,
                         item.WeightColumn,
@@ -645,7 +645,7 @@ private static void TransformFeatures(IExceptionContext ectx, in VBuffer<float>
             Desc = Summary,
             UserName = UserName,
             ShortName = ShortName)]
-        internal static CommonOutputs.TransformOutput Calculate(IHostEnvironment env, Arguments input)
+        internal static CommonOutputs.TransformOutput Calculate(IHostEnvironment env, Options input)
         {
             var h = EntryPointUtils.CheckArgsAndCreateHost(env, "Pca", input);
             var view = PcaTransformer.Create(h, input, input.Data);
@@ -683,7 +683,7 @@ internal static class Defaults
         /// <param name="overSampling">Oversampling parameter for randomized PCA 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 PrincipalComponentAnalysisEstimator(IHostEnvironment env,
+        internal PrincipalComponentAnalysisEstimator(IHostEnvironment env,
             string outputColumnName,
             string inputColumnName = null,
             string weightColumn = Defaults.WeightColumn, int rank = Defaults.Rank,
@@ -696,15 +696,21 @@ public PrincipalComponentAnalysisEstimator(IHostEnvironment env,
         /// <include file='doc.xml' path='doc/members/member[@name="PCA"]/*'/>
         /// <param name="env">The environment to use.</param>
         /// <param name="columns">The dataset columns to use, and their specific settings.</param>
-        public PrincipalComponentAnalysisEstimator(IHostEnvironment env, params PcaTransformer.ColumnInfo[] columns)
+        internal PrincipalComponentAnalysisEstimator(IHostEnvironment env, params PcaTransformer.ColumnInfo[] columns)
         {
             Contracts.CheckValue(env, nameof(env));
             _host = env.Register(nameof(PrincipalComponentAnalysisEstimator));
             _columns = columns;
         }
 
+        /// <summary>
+        /// Train and return a transformer.
+        /// </summary>
         public PcaTransformer Fit(IDataView input) => new PcaTransformer(_host, input, _columns);
 
+        /// <summary>
+        /// Returns the output schema shape of the estimator, if the input schema shape is like the one provided.
+        /// </summary>
         public SchemaShape GetOutputSchema(SchemaShape inputSchema)
         {
             _host.CheckValue(inputSchema, nameof(inputSchema));

test/BaselineOutput/Common/EntryPoints/core_ep-list.tsv

@@ -115,7 +115,7 @@ Transforms.ModelCombiner	Combines a sequence of TransformModels into a single mo
 Transforms.NGramTranslator	Produces a bag of counts of ngrams (sequences of consecutive values of length 1-n) in a given vector of keys. It does so by building a dictionary of ngrams and using the id in the dictionary as the index in the bag.	Microsoft.ML.Transforms.Text.TextAnalytics	NGramTransform	Microsoft.ML.Transforms.Text.NgramExtractingTransformer+Arguments	Microsoft.ML.EntryPoints.CommonOutputs+TransformOutput
 Transforms.NoOperation	Does nothing.	Microsoft.ML.Data.NopTransform	Nop	Microsoft.ML.Data.NopTransform+NopInput	Microsoft.ML.EntryPoints.CommonOutputs+TransformOutput
 Transforms.OptionalColumnCreator	If the source column does not exist after deserialization, create a column with the right type and default values.	Microsoft.ML.Transforms.OptionalColumnTransform	MakeOptional	Microsoft.ML.Transforms.OptionalColumnTransform+Arguments	Microsoft.ML.EntryPoints.CommonOutputs+TransformOutput
-Transforms.PcaCalculator	PCA is a dimensionality-reduction transform which computes the projection of a numeric vector onto a low-rank subspace.	Microsoft.ML.Transforms.Projections.PcaTransformer	Calculate	Microsoft.ML.Transforms.Projections.PcaTransformer+Arguments	Microsoft.ML.EntryPoints.CommonOutputs+TransformOutput
+Transforms.PcaCalculator	PCA is a dimensionality-reduction transform which computes the projection of a numeric vector onto a low-rank subspace.	Microsoft.ML.Transforms.Projections.PcaTransformer	Calculate	Microsoft.ML.Transforms.Projections.PcaTransformer+Options	Microsoft.ML.EntryPoints.CommonOutputs+TransformOutput
 Transforms.PredictedLabelColumnOriginalValueConverter	Transforms a predicted label column to its original values, unless it is of type bool.	Microsoft.ML.EntryPoints.FeatureCombiner	ConvertPredictedLabel	Microsoft.ML.EntryPoints.FeatureCombiner+PredictedLabelInput	Microsoft.ML.EntryPoints.CommonOutputs+TransformOutput
 Transforms.RandomNumberGenerator	Adds a column with a generated number sequence.	Microsoft.ML.Transforms.RandomNumberGenerator	Generate	Microsoft.ML.Transforms.GenerateNumberTransform+Arguments	Microsoft.ML.EntryPoints.CommonOutputs+TransformOutput
 Transforms.RowRangeFilter	Filters a dataview on a column of type Single, Double or Key (contiguous). Keeps the values that are in the specified min/max range. NaNs are always filtered out. If the input is a Key type, the min/max are considered percentages of the number of values.	Microsoft.ML.EntryPoints.SelectRows	FilterByRange	Microsoft.ML.Transforms.RangeFilter+Arguments	Microsoft.ML.EntryPoints.CommonOutputs+TransformOutput