Creation of components through MLContext, internalization, and renaming

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/PriorTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class PriorTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Prior(labelColumn: "Sentiment"));
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // The Prior trainer outputs the proportion of a label in the dataset as the probability of that label.
+ // In this case it means that there is a split of around 64%-36% of positive and negative labels in the dataset.
+ // Expected output:
+ // Accuracy: 0.647058823529412
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/RandomTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class RandomTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext(seed: 1);
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Random());
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // We expect an output probability closet to 0.5 as the Random trainer outputs a random prediction.
+ // Regardless of the input features, the trainer will predict either positive or negative label with equal probability.
+ // Expected output (close to 0.5):
+ // Accuracy: 0.588235294117647
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSample.cs

@@ -0,0 +1,70 @@
+using System;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class CustomMappingSample
+ {
+ public static void Example()
+ {
+ // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+ // as well as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Get a small dataset as an IEnumerable and convert it to an IDataView.
+ var data = SamplesUtils.DatasetUtils.GetInfertData();
+ var trainData = mlContext.Data.ReadFromEnumerable(data);
+
+ // Preview of the data.
+ //
+ // Age Case Education Induced Parity PooledStratum RowNum ...
+ // 26 1 0-5yrs 1 6 3 1 ...
+ // 42 1 0-5yrs 1 1 1 2 ...
+ // 39 1 0-5yrs 2 6 4 3 ...
+ // 34 1 0-5yrs 2 4 2 4 ...
+ // 35 1 6-11yrs 1 3 32 5 ...
+
+ // We define the custom mapping between input and output rows that will be applied by the transformation.
+ Action<SamplesUtils.DatasetUtils.SampleInfertData, SampleInfertDataTransformed> mapping = 
+ (input, output) => output.IsUnderThirty = input.Age < 30;
+
+ // Custom transformations can be used to transform data directly, or as part of a pipeline. Below we transform data directly.
+ var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
+ var transformedData = transformer.Transform(trainData);
+
+ // Preview of the data.
+ //
+ // IsUnderThirty Age Case Education Induced Parity PooledStratum RowNum ...
+ // true 26 1 0-5yrs 1 6 3 1 ...
+ // false 42 1 0-5yrs 1 1 1 2 ...
+ // false 39 1 0-5yrs 2 6 4 3 ...
+ // false 34 1 0-5yrs 2 4 2 4 ...
+ // false 35 1 6-11yrs 1 3 32 5 ...
+
+ // Here instead we use it as part of a pipeline of estimators.
+ var pipeline = mlContext.Transforms.CustomMapping(mapping, null)
+ .Append(mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: new[] { "Parity", "Induced" }))
+ // It is useful to add a caching checkpoint before a trainer that does several passes over the data.
+ .AppendCacheCheckpoint(mlContext)
+ // We use binary FastTree to predict the label column that was generated by the custom mapping at the first step of the pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumn: "IsUnderThirty"));
+
+ // We can train the pipeline and use it to transform data.
+ transformedData = pipeline.Fit(trainData).Transform(trainData);
+ }
+
+ // Represents the transformed infertility dataset.
+ public class SampleInfertDataTransformed
+ {
+ public int RowNum { get; set; }
+ public string Education { get; set; }
+ public bool IsUnderThirty { get; set; }
+ public float Parity { get; set; }
+ public float Induced { get; set; }
+ public float Case { get; set; }
+ public float Spontaneous { get; set; }
+ public float Stratum { get; set; }
+ public float PooledStratum { get; set; }
+ }
+ }
+}

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoader.cs

@@ -905,7 +905,7 @@ private Schema ComputeOutputSchema()
 
  internal const string Summary = "Loads text data file.";
 
-public const string LoaderSignature = "TextLoader";
+internal const string LoaderSignature = "TextLoader";
 
  private const uint VerForceVectorSupported = 0x0001000A;
  private const uint VersionNoMinCount = 0x0001000C;

src/Microsoft.ML.Data/DataLoadSave/TransformWrapper.cs

@@ -20,7 +20,7 @@ namespace Microsoft.ML.Data
  // It needs to become internal.
  public sealed class TransformWrapper : ITransformer
  {
-public const string LoaderSignature = "TransformWrapper";
+internal const string LoaderSignature = "TransformWrapper";
  private const string TransformDirTemplate = "Step_{0:000}";
 
  private readonly IHost _host;

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -54,6 +54,10 @@ public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer
  private protected ISchemaBindableMapper BindableMapper;
  protected Schema TrainSchema;
 
+ /// <summary>
+ /// Whether a call to <see cref="GetRowToRowMapper(Schema)"/> should succeed, on an
+ /// appropriate schema.
+ /// </summary>
  public bool IsRowToRowMapper => true;
 
  /// <summary>
@@ -257,8 +261,8 @@ private protected GenericScorer GetGenericScorer()
  public sealed class AnomalyPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal AnomalyPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,
@@ -326,8 +330,8 @@ private static VersionInfo GetVersionInfo()
  public sealed class BinaryPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal BinaryPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -36,7 +36,7 @@ namespace Microsoft.ML.Trainers.FastTree
  public sealed partial class FastTreeRegressionTrainer
  : BoostingFastTreeTrainerBase<FastTreeRegressionTrainer.Options, RegressionPredictionTransformer<FastTreeRegressionModelParameters>, FastTreeRegressionModelParameters>
  {
-public const string LoadNameValue = "FastTreeRegression";
+internal const string LoadNameValue = "FastTreeRegression";
  internal const string UserNameValue = "FastTree (Boosted Trees) Regression";
  internal const string Summary = "Trains gradient boosted decision trees to fit target values using least-squares.";
  internal const string ShortName = "ftr";
@@ -142,7 +142,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -149,7 +149,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.LightGBM/LightGbmRankingTrainer.cs

@@ -75,9 +75,9 @@ private static LightGbmRankingModelParameters Create(IHostEnvironment env, Model
  /// <include file='doc.xml' path='doc/members/member[@name="LightGBM"]/*' />
  public sealed class LightGbmRankingTrainer : LightGbmTrainerBase<float, RankingPredictionTransformer<LightGbmRankingModelParameters>, LightGbmRankingModelParameters>
  {
-public const string UserName = "LightGBM Ranking";
-public const string LoadNameValue = "LightGBMRanking";
-public const string ShortName = "LightGBMRank";
+internal const string UserName = "LightGBM Ranking";
+internal const string LoadNameValue = "LightGBMRanking";
+internal const string ShortName = "LightGBMRank";
 
  public override PredictionKind PredictionKind => PredictionKind.Ranking;
 

src/Microsoft.ML.OnnxTransform/DnnImageFeaturizerTransform.cs

@@ -61,7 +61,7 @@ public sealed class DnnImageFeaturizerEstimator : IEstimator<TransformerChain<Co
  /// For an example, see Microsoft.ML.DnnImageFeaturizer.ResNet18 </param>
  /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
  /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
-public DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
+internal DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
  {
  _modelChain = modelFactory(new DnnImageFeaturizerInput(outputColumnName, inputColumnName ?? outputColumnName, env, new DnnImageModelSelector()));
  }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -2,6 +2,7 @@
 // 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;
 using Microsoft.ML.Data;
 using Microsoft.ML.Transforms;
 
@@ -61,5 +62,19 @@ public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog
  bool fallbackToCpu = false)
  => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnNames, inputColumnNames, modelFile, gpuDeviceId, fallbackToCpu);
 
+ /// <summary>
+ /// Creates a new instance of <see cref="DnnImageFeaturizerEstimator"/> which applies a pre-trained DNN model to featurize an image.
+ /// </summary>
+ /// <param name="catalog">The transform's catalog.</param>
+ /// <param name="outputColumnName">The name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
+ /// <param name="modelFactory">An extension method on the <see cref="DnnImageModelSelector"/> that creates a chain of two
+ /// <see cref="OnnxScoringEstimator"/> (one for preprocessing and one with a pretrained image DNN) with specific models
+ /// included in a package together with that extension method.</param>
+ /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
+ public static DnnImageFeaturizerEstimator DnnFeaturizeImage(this TransformsCatalog catalog,
+ string outputColumnName,
+ Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory,
+ string inputColumnName = null)
+ => new DnnImageFeaturizerEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, modelFactory, inputColumnName);
  }
 }

src/Microsoft.ML.StandardLearners/FactorizationMachine/FieldAwareFactorizationMachineModelParameters.cs

@@ -285,17 +285,17 @@ public float[] GetLatentWeights()
 
  public sealed class FieldAwareFactorizationMachinePredictionTransformer : PredictionTransformerBase<FieldAwareFactorizationMachineModelParameters>
  {
-public const string LoaderSignature = "FAFMPredXfer";
+internal const string LoaderSignature = "FAFMPredXfer";
 
  /// <summary>
  /// The name of the feature column used by the prediction transformer.
  /// </summary>
-public IReadOnlyList<string> FeatureColumns { get; }
+internal IReadOnlyList<string> FeatureColumns { get; }
 
  /// <summary>
  /// The type of the feature columns.
  /// </summary>
-public IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
+internal IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
 
  private readonly string _thresholdColumn;
  private readonly float _threshold;

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -35,7 +35,7 @@ public sealed partial class LogisticRegression : LbfgsTrainerBase<LogisticRegres
  BinaryPredictionTransformer<CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>,
  CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>
  {
-public const string LoadNameValue = "LogisticRegression";
+internal const string LoadNameValue = "LogisticRegression";
  internal const string UserNameValue = "Logistic Regression";
  internal const string ShortName = "lr";
  internal const string Summary = "Logistic Regression is a method in statistics used to predict the probability of occurrence of an event and can "

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/MulticlassLogisticRegression.cs

@@ -41,7 +41,7 @@ namespace Microsoft.ML.Trainers
  public sealed class MulticlassLogisticRegression : LbfgsTrainerBase<MulticlassLogisticRegression.Options,
  MulticlassPredictionTransformer<MulticlassLogisticRegressionModelParameters>, MulticlassLogisticRegressionModelParameters>
  {
-public const string LoadNameValue = "MultiClassLogisticRegression";
+internal const string LoadNameValue = "MultiClassLogisticRegression";
  internal const string UserNameValue = "Multi-class Logistic Regression";
  internal const string ShortName = "mlr";
 

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/PriorTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class PriorTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Prior(labelColumn: "Sentiment"));
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // The Prior trainer outputs the proportion of a label in the dataset as the probability of that label.
+ // In this case it means that there is a split of around 64%-36% of positive and negative labels in the dataset.
+ // Expected output:
+ // Accuracy: 0.647058823529412
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/RandomTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class RandomTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext(seed: 1);
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Random());
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // We expect an output probability closet to 0.5 as the Random trainer outputs a random prediction.
+ // Regardless of the input features, the trainer will predict either positive or negative label with equal probability.
+ // Expected output (close to 0.5):
+ // Accuracy: 0.588235294117647
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSample.cs

@@ -0,0 +1,70 @@
+using System;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class CustomMappingSample
+ {
+ public static void Example()
+ {
+ // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+ // as well as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Get a small dataset as an IEnumerable and convert it to an IDataView.
+ var data = SamplesUtils.DatasetUtils.GetInfertData();
+ var trainData = mlContext.Data.ReadFromEnumerable(data);
+
+ // Preview of the data.
+ //
+ // Age Case Education Induced Parity PooledStratum RowNum ...
+ // 26 1 0-5yrs 1 6 3 1 ...
+ // 42 1 0-5yrs 1 1 1 2 ...
+ // 39 1 0-5yrs 2 6 4 3 ...
+ // 34 1 0-5yrs 2 4 2 4 ...
+ // 35 1 6-11yrs 1 3 32 5 ...
+
+ // We define the custom mapping between input and output rows that will be applied by the transformation.
+ Action<SamplesUtils.DatasetUtils.SampleInfertData, SampleInfertDataTransformed> mapping = 
+ (input, output) => output.IsUnderThirty = input.Age < 30;
+
+ // Custom transformations can be used to transform data directly, or as part of a pipeline. Below we transform data directly.
+ var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
+ var transformedData = transformer.Transform(trainData);
+
+ // Preview of the data.
+ //
+ // IsUnderThirty Age Case Education Induced Parity PooledStratum RowNum ...
+ // true 26 1 0-5yrs 1 6 3 1 ...
+ // false 42 1 0-5yrs 1 1 1 2 ...
+ // false 39 1 0-5yrs 2 6 4 3 ...
+ // false 34 1 0-5yrs 2 4 2 4 ...
+ // false 35 1 6-11yrs 1 3 32 5 ...
+
+ // Here instead we use it as part of a pipeline of estimators.
+ var pipeline = mlContext.Transforms.CustomMapping(mapping, null)
+ .Append(mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: new[] { "Parity", "Induced" }))
+ // It is useful to add a caching checkpoint before a trainer that does several passes over the data.
+ .AppendCacheCheckpoint(mlContext)
+ // We use binary FastTree to predict the label column that was generated by the custom mapping at the first step of the pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumn: "IsUnderThirty"));
+
+ // We can train the pipeline and use it to transform data.
+ transformedData = pipeline.Fit(trainData).Transform(trainData);
+ }
+
+ // Represents the transformed infertility dataset.
+ public class SampleInfertDataTransformed
+ {
+ public int RowNum { get; set; }
+ public string Education { get; set; }
+ public bool IsUnderThirty { get; set; }
+ public float Parity { get; set; }
+ public float Induced { get; set; }
+ public float Case { get; set; }
+ public float Spontaneous { get; set; }
+ public float Stratum { get; set; }
+ public float PooledStratum { get; set; }
+ }
+ }
+}

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoader.cs

@@ -905,7 +905,7 @@ private Schema ComputeOutputSchema()
 
  internal const string Summary = "Loads text data file.";
 
-public const string LoaderSignature = "TextLoader";
+internal const string LoaderSignature = "TextLoader";
 
  private const uint VerForceVectorSupported = 0x0001000A;
  private const uint VersionNoMinCount = 0x0001000C;

src/Microsoft.ML.Data/DataLoadSave/TransformWrapper.cs

@@ -20,7 +20,7 @@ namespace Microsoft.ML.Data
  // It needs to become internal.
  public sealed class TransformWrapper : ITransformer
  {
-public const string LoaderSignature = "TransformWrapper";
+internal const string LoaderSignature = "TransformWrapper";
  private const string TransformDirTemplate = "Step_{0:000}";
 
  private readonly IHost _host;

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -54,6 +54,10 @@ public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer
  private protected ISchemaBindableMapper BindableMapper;
  protected Schema TrainSchema;
 
+ /// <summary>
+ /// Whether a call to <see cref="GetRowToRowMapper(Schema)"/> should succeed, on an
+ /// appropriate schema.
+ /// </summary>
  public bool IsRowToRowMapper => true;
 
  /// <summary>
@@ -257,8 +261,8 @@ private protected GenericScorer GetGenericScorer()
  public sealed class AnomalyPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal AnomalyPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,
@@ -326,8 +330,8 @@ private static VersionInfo GetVersionInfo()
  public sealed class BinaryPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal BinaryPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -36,7 +36,7 @@ namespace Microsoft.ML.Trainers.FastTree
  public sealed partial class FastTreeRegressionTrainer
  : BoostingFastTreeTrainerBase<FastTreeRegressionTrainer.Options, RegressionPredictionTransformer<FastTreeRegressionModelParameters>, FastTreeRegressionModelParameters>
  {
-public const string LoadNameValue = "FastTreeRegression";
+internal const string LoadNameValue = "FastTreeRegression";
  internal const string UserNameValue = "FastTree (Boosted Trees) Regression";
  internal const string Summary = "Trains gradient boosted decision trees to fit target values using least-squares.";
  internal const string ShortName = "ftr";
@@ -142,7 +142,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -149,7 +149,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.LightGBM/LightGbmRankingTrainer.cs

@@ -75,9 +75,9 @@ private static LightGbmRankingModelParameters Create(IHostEnvironment env, Model
  /// <include file='doc.xml' path='doc/members/member[@name="LightGBM"]/*' />
  public sealed class LightGbmRankingTrainer : LightGbmTrainerBase<float, RankingPredictionTransformer<LightGbmRankingModelParameters>, LightGbmRankingModelParameters>
  {
-public const string UserName = "LightGBM Ranking";
-public const string LoadNameValue = "LightGBMRanking";
-public const string ShortName = "LightGBMRank";
+internal const string UserName = "LightGBM Ranking";
+internal const string LoadNameValue = "LightGBMRanking";
+internal const string ShortName = "LightGBMRank";
 
  public override PredictionKind PredictionKind => PredictionKind.Ranking;
 

src/Microsoft.ML.OnnxTransform/DnnImageFeaturizerTransform.cs

@@ -61,7 +61,7 @@ public sealed class DnnImageFeaturizerEstimator : IEstimator<TransformerChain<Co
  /// For an example, see Microsoft.ML.DnnImageFeaturizer.ResNet18 </param>
  /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
  /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
-public DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
+internal DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
  {
  _modelChain = modelFactory(new DnnImageFeaturizerInput(outputColumnName, inputColumnName ?? outputColumnName, env, new DnnImageModelSelector()));
  }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -2,6 +2,7 @@
 // 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;
 using Microsoft.ML.Data;
 using Microsoft.ML.Transforms;
 
@@ -61,5 +62,19 @@ public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog
  bool fallbackToCpu = false)
  => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnNames, inputColumnNames, modelFile, gpuDeviceId, fallbackToCpu);
 
+ /// <summary>
+ /// Creates a new instance of <see cref="DnnImageFeaturizerEstimator"/> which applies a pre-trained DNN model to featurize an image.
+ /// </summary>
+ /// <param name="catalog">The transform's catalog.</param>
+ /// <param name="outputColumnName">The name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
+ /// <param name="modelFactory">An extension method on the <see cref="DnnImageModelSelector"/> that creates a chain of two
+ /// <see cref="OnnxScoringEstimator"/> (one for preprocessing and one with a pretrained image DNN) with specific models
+ /// included in a package together with that extension method.</param>
+ /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
+ public static DnnImageFeaturizerEstimator DnnFeaturizeImage(this TransformsCatalog catalog,
+ string outputColumnName,
+ Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory,
+ string inputColumnName = null)
+ => new DnnImageFeaturizerEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, modelFactory, inputColumnName);
  }
 }

src/Microsoft.ML.StandardLearners/FactorizationMachine/FieldAwareFactorizationMachineModelParameters.cs

@@ -285,17 +285,17 @@ public float[] GetLatentWeights()
 
  public sealed class FieldAwareFactorizationMachinePredictionTransformer : PredictionTransformerBase<FieldAwareFactorizationMachineModelParameters>
  {
-public const string LoaderSignature = "FAFMPredXfer";
+internal const string LoaderSignature = "FAFMPredXfer";
 
  /// <summary>
  /// The name of the feature column used by the prediction transformer.
  /// </summary>
-public IReadOnlyList<string> FeatureColumns { get; }
+internal IReadOnlyList<string> FeatureColumns { get; }
 
  /// <summary>
  /// The type of the feature columns.
  /// </summary>
-public IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
+internal IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
 
  private readonly string _thresholdColumn;
  private readonly float _threshold;

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -35,7 +35,7 @@ public sealed partial class LogisticRegression : LbfgsTrainerBase<LogisticRegres
  BinaryPredictionTransformer<CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>,
  CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>
  {
-public const string LoadNameValue = "LogisticRegression";
+internal const string LoadNameValue = "LogisticRegression";
  internal const string UserNameValue = "Logistic Regression";
  internal const string ShortName = "lr";
  internal const string Summary = "Logistic Regression is a method in statistics used to predict the probability of occurrence of an event and can "

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/MulticlassLogisticRegression.cs

@@ -41,7 +41,7 @@ namespace Microsoft.ML.Trainers
  public sealed class MulticlassLogisticRegression : LbfgsTrainerBase<MulticlassLogisticRegression.Options,
  MulticlassPredictionTransformer<MulticlassLogisticRegressionModelParameters>, MulticlassLogisticRegressionModelParameters>
  {
-public const string LoadNameValue = "MultiClassLogisticRegression";
+internal const string LoadNameValue = "MultiClassLogisticRegression";
  internal const string UserNameValue = "Multi-class Logistic Regression";
  internal const string ShortName = "mlr";
 

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/PriorTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class PriorTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Prior(labelColumn: "Sentiment"));
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // The Prior trainer outputs the proportion of a label in the dataset as the probability of that label.
+ // In this case it means that there is a split of around 64%-36% of positive and negative labels in the dataset.
+ // Expected output:
+ // Accuracy: 0.647058823529412
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/RandomTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class RandomTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext(seed: 1);
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Random());
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // We expect an output probability closet to 0.5 as the Random trainer outputs a random prediction.
+ // Regardless of the input features, the trainer will predict either positive or negative label with equal probability.
+ // Expected output (close to 0.5):
+ // Accuracy: 0.588235294117647
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSample.cs

@@ -0,0 +1,70 @@
+using System;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class CustomMappingSample
+ {
+ public static void Example()
+ {
+ // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+ // as well as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Get a small dataset as an IEnumerable and convert it to an IDataView.
+ var data = SamplesUtils.DatasetUtils.GetInfertData();
+ var trainData = mlContext.Data.ReadFromEnumerable(data);
+
+ // Preview of the data.
+ //
+ // Age Case Education Induced Parity PooledStratum RowNum ...
+ // 26 1 0-5yrs 1 6 3 1 ...
+ // 42 1 0-5yrs 1 1 1 2 ...
+ // 39 1 0-5yrs 2 6 4 3 ...
+ // 34 1 0-5yrs 2 4 2 4 ...
+ // 35 1 6-11yrs 1 3 32 5 ...
+
+ // We define the custom mapping between input and output rows that will be applied by the transformation.
+ Action<SamplesUtils.DatasetUtils.SampleInfertData, SampleInfertDataTransformed> mapping = 
+ (input, output) => output.IsUnderThirty = input.Age < 30;
+
+ // Custom transformations can be used to transform data directly, or as part of a pipeline. Below we transform data directly.
+ var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
+ var transformedData = transformer.Transform(trainData);
+
+ // Preview of the data.
+ //
+ // IsUnderThirty Age Case Education Induced Parity PooledStratum RowNum ...
+ // true 26 1 0-5yrs 1 6 3 1 ...
+ // false 42 1 0-5yrs 1 1 1 2 ...
+ // false 39 1 0-5yrs 2 6 4 3 ...
+ // false 34 1 0-5yrs 2 4 2 4 ...
+ // false 35 1 6-11yrs 1 3 32 5 ...
+
+ // Here instead we use it as part of a pipeline of estimators.
+ var pipeline = mlContext.Transforms.CustomMapping(mapping, null)
+ .Append(mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: new[] { "Parity", "Induced" }))
+ // It is useful to add a caching checkpoint before a trainer that does several passes over the data.
+ .AppendCacheCheckpoint(mlContext)
+ // We use binary FastTree to predict the label column that was generated by the custom mapping at the first step of the pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumn: "IsUnderThirty"));
+
+ // We can train the pipeline and use it to transform data.
+ transformedData = pipeline.Fit(trainData).Transform(trainData);
+ }
+
+ // Represents the transformed infertility dataset.
+ public class SampleInfertDataTransformed
+ {
+ public int RowNum { get; set; }
+ public string Education { get; set; }
+ public bool IsUnderThirty { get; set; }
+ public float Parity { get; set; }
+ public float Induced { get; set; }
+ public float Case { get; set; }
+ public float Spontaneous { get; set; }
+ public float Stratum { get; set; }
+ public float PooledStratum { get; set; }
+ }
+ }
+}

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoader.cs

@@ -905,7 +905,7 @@ private Schema ComputeOutputSchema()
 
  internal const string Summary = "Loads text data file.";
 
-public const string LoaderSignature = "TextLoader";
+internal const string LoaderSignature = "TextLoader";
 
  private const uint VerForceVectorSupported = 0x0001000A;
  private const uint VersionNoMinCount = 0x0001000C;

src/Microsoft.ML.Data/DataLoadSave/TransformWrapper.cs

@@ -20,7 +20,7 @@ namespace Microsoft.ML.Data
  // It needs to become internal.
  public sealed class TransformWrapper : ITransformer
  {
-public const string LoaderSignature = "TransformWrapper";
+internal const string LoaderSignature = "TransformWrapper";
  private const string TransformDirTemplate = "Step_{0:000}";
 
  private readonly IHost _host;

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -54,6 +54,10 @@ public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer
  private protected ISchemaBindableMapper BindableMapper;
  protected Schema TrainSchema;
 
+ /// <summary>
+ /// Whether a call to <see cref="GetRowToRowMapper(Schema)"/> should succeed, on an
+ /// appropriate schema.
+ /// </summary>
  public bool IsRowToRowMapper => true;
 
  /// <summary>
@@ -257,8 +261,8 @@ private protected GenericScorer GetGenericScorer()
  public sealed class AnomalyPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal AnomalyPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,
@@ -326,8 +330,8 @@ private static VersionInfo GetVersionInfo()
  public sealed class BinaryPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal BinaryPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -36,7 +36,7 @@ namespace Microsoft.ML.Trainers.FastTree
  public sealed partial class FastTreeRegressionTrainer
  : BoostingFastTreeTrainerBase<FastTreeRegressionTrainer.Options, RegressionPredictionTransformer<FastTreeRegressionModelParameters>, FastTreeRegressionModelParameters>
  {
-public const string LoadNameValue = "FastTreeRegression";
+internal const string LoadNameValue = "FastTreeRegression";
  internal const string UserNameValue = "FastTree (Boosted Trees) Regression";
  internal const string Summary = "Trains gradient boosted decision trees to fit target values using least-squares.";
  internal const string ShortName = "ftr";
@@ -142,7 +142,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -149,7 +149,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.LightGBM/LightGbmRankingTrainer.cs

@@ -75,9 +75,9 @@ private static LightGbmRankingModelParameters Create(IHostEnvironment env, Model
  /// <include file='doc.xml' path='doc/members/member[@name="LightGBM"]/*' />
  public sealed class LightGbmRankingTrainer : LightGbmTrainerBase<float, RankingPredictionTransformer<LightGbmRankingModelParameters>, LightGbmRankingModelParameters>
  {
-public const string UserName = "LightGBM Ranking";
-public const string LoadNameValue = "LightGBMRanking";
-public const string ShortName = "LightGBMRank";
+internal const string UserName = "LightGBM Ranking";
+internal const string LoadNameValue = "LightGBMRanking";
+internal const string ShortName = "LightGBMRank";
 
  public override PredictionKind PredictionKind => PredictionKind.Ranking;
 

src/Microsoft.ML.OnnxTransform/DnnImageFeaturizerTransform.cs

@@ -61,7 +61,7 @@ public sealed class DnnImageFeaturizerEstimator : IEstimator<TransformerChain<Co
  /// For an example, see Microsoft.ML.DnnImageFeaturizer.ResNet18 </param>
  /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
  /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
-public DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
+internal DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
  {
  _modelChain = modelFactory(new DnnImageFeaturizerInput(outputColumnName, inputColumnName ?? outputColumnName, env, new DnnImageModelSelector()));
  }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -2,6 +2,7 @@
 // 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;
 using Microsoft.ML.Data;
 using Microsoft.ML.Transforms;
 
@@ -61,5 +62,19 @@ public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog
  bool fallbackToCpu = false)
  => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnNames, inputColumnNames, modelFile, gpuDeviceId, fallbackToCpu);
 
+ /// <summary>
+ /// Creates a new instance of <see cref="DnnImageFeaturizerEstimator"/> which applies a pre-trained DNN model to featurize an image.
+ /// </summary>
+ /// <param name="catalog">The transform's catalog.</param>
+ /// <param name="outputColumnName">The name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
+ /// <param name="modelFactory">An extension method on the <see cref="DnnImageModelSelector"/> that creates a chain of two
+ /// <see cref="OnnxScoringEstimator"/> (one for preprocessing and one with a pretrained image DNN) with specific models
+ /// included in a package together with that extension method.</param>
+ /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
+ public static DnnImageFeaturizerEstimator DnnFeaturizeImage(this TransformsCatalog catalog,
+ string outputColumnName,
+ Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory,
+ string inputColumnName = null)
+ => new DnnImageFeaturizerEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, modelFactory, inputColumnName);
  }
 }

src/Microsoft.ML.StandardLearners/FactorizationMachine/FieldAwareFactorizationMachineModelParameters.cs

@@ -285,17 +285,17 @@ public float[] GetLatentWeights()
 
  public sealed class FieldAwareFactorizationMachinePredictionTransformer : PredictionTransformerBase<FieldAwareFactorizationMachineModelParameters>
  {
-public const string LoaderSignature = "FAFMPredXfer";
+internal const string LoaderSignature = "FAFMPredXfer";
 
  /// <summary>
  /// The name of the feature column used by the prediction transformer.
  /// </summary>
-public IReadOnlyList<string> FeatureColumns { get; }
+internal IReadOnlyList<string> FeatureColumns { get; }
 
  /// <summary>
  /// The type of the feature columns.
  /// </summary>
-public IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
+internal IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
 
  private readonly string _thresholdColumn;
  private readonly float _threshold;

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -35,7 +35,7 @@ public sealed partial class LogisticRegression : LbfgsTrainerBase<LogisticRegres
  BinaryPredictionTransformer<CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>,
  CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>
  {
-public const string LoadNameValue = "LogisticRegression";
+internal const string LoadNameValue = "LogisticRegression";
  internal const string UserNameValue = "Logistic Regression";
  internal const string ShortName = "lr";
  internal const string Summary = "Logistic Regression is a method in statistics used to predict the probability of occurrence of an event and can "

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/MulticlassLogisticRegression.cs

@@ -41,7 +41,7 @@ namespace Microsoft.ML.Trainers
  public sealed class MulticlassLogisticRegression : LbfgsTrainerBase<MulticlassLogisticRegression.Options,
  MulticlassPredictionTransformer<MulticlassLogisticRegressionModelParameters>, MulticlassLogisticRegressionModelParameters>
  {
-public const string LoadNameValue = "MultiClassLogisticRegression";
+internal const string LoadNameValue = "MultiClassLogisticRegression";
  internal const string UserNameValue = "Multi-class Logistic Regression";
  internal const string ShortName = "mlr";
 

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/PriorTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class PriorTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Prior(labelColumn: "Sentiment"));
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // The Prior trainer outputs the proportion of a label in the dataset as the probability of that label.
+ // In this case it means that there is a split of around 64%-36% of positive and negative labels in the dataset.
+ // Expected output:
+ // Accuracy: 0.647058823529412
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/RandomTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class RandomTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext(seed: 1);
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Random());
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // We expect an output probability closet to 0.5 as the Random trainer outputs a random prediction.
+ // Regardless of the input features, the trainer will predict either positive or negative label with equal probability.
+ // Expected output (close to 0.5):
+ // Accuracy: 0.588235294117647
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSample.cs

@@ -0,0 +1,70 @@
+using System;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class CustomMappingSample
+ {
+ public static void Example()
+ {
+ // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+ // as well as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Get a small dataset as an IEnumerable and convert it to an IDataView.
+ var data = SamplesUtils.DatasetUtils.GetInfertData();
+ var trainData = mlContext.Data.ReadFromEnumerable(data);
+
+ // Preview of the data.
+ //
+ // Age Case Education Induced Parity PooledStratum RowNum ...
+ // 26 1 0-5yrs 1 6 3 1 ...
+ // 42 1 0-5yrs 1 1 1 2 ...
+ // 39 1 0-5yrs 2 6 4 3 ...
+ // 34 1 0-5yrs 2 4 2 4 ...
+ // 35 1 6-11yrs 1 3 32 5 ...
+
+ // We define the custom mapping between input and output rows that will be applied by the transformation.
+ Action<SamplesUtils.DatasetUtils.SampleInfertData, SampleInfertDataTransformed> mapping = 
+ (input, output) => output.IsUnderThirty = input.Age < 30;
+
+ // Custom transformations can be used to transform data directly, or as part of a pipeline. Below we transform data directly.
+ var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
+ var transformedData = transformer.Transform(trainData);
+
+ // Preview of the data.
+ //
+ // IsUnderThirty Age Case Education Induced Parity PooledStratum RowNum ...
+ // true 26 1 0-5yrs 1 6 3 1 ...
+ // false 42 1 0-5yrs 1 1 1 2 ...
+ // false 39 1 0-5yrs 2 6 4 3 ...
+ // false 34 1 0-5yrs 2 4 2 4 ...
+ // false 35 1 6-11yrs 1 3 32 5 ...
+
+ // Here instead we use it as part of a pipeline of estimators.
+ var pipeline = mlContext.Transforms.CustomMapping(mapping, null)
+ .Append(mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: new[] { "Parity", "Induced" }))
+ // It is useful to add a caching checkpoint before a trainer that does several passes over the data.
+ .AppendCacheCheckpoint(mlContext)
+ // We use binary FastTree to predict the label column that was generated by the custom mapping at the first step of the pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumn: "IsUnderThirty"));
+
+ // We can train the pipeline and use it to transform data.
+ transformedData = pipeline.Fit(trainData).Transform(trainData);
+ }
+
+ // Represents the transformed infertility dataset.
+ public class SampleInfertDataTransformed
+ {
+ public int RowNum { get; set; }
+ public string Education { get; set; }
+ public bool IsUnderThirty { get; set; }
+ public float Parity { get; set; }
+ public float Induced { get; set; }
+ public float Case { get; set; }
+ public float Spontaneous { get; set; }
+ public float Stratum { get; set; }
+ public float PooledStratum { get; set; }
+ }
+ }
+}

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoader.cs

@@ -905,7 +905,7 @@ private Schema ComputeOutputSchema()
 
  internal const string Summary = "Loads text data file.";
 
-public const string LoaderSignature = "TextLoader";
+internal const string LoaderSignature = "TextLoader";
 
  private const uint VerForceVectorSupported = 0x0001000A;
  private const uint VersionNoMinCount = 0x0001000C;

src/Microsoft.ML.Data/DataLoadSave/TransformWrapper.cs

@@ -20,7 +20,7 @@ namespace Microsoft.ML.Data
  // It needs to become internal.
  public sealed class TransformWrapper : ITransformer
  {
-public const string LoaderSignature = "TransformWrapper";
+internal const string LoaderSignature = "TransformWrapper";
  private const string TransformDirTemplate = "Step_{0:000}";
 
  private readonly IHost _host;

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -54,6 +54,10 @@ public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer
  private protected ISchemaBindableMapper BindableMapper;
  protected Schema TrainSchema;
 
+ /// <summary>
+ /// Whether a call to <see cref="GetRowToRowMapper(Schema)"/> should succeed, on an
+ /// appropriate schema.
+ /// </summary>
  public bool IsRowToRowMapper => true;
 
  /// <summary>
@@ -257,8 +261,8 @@ private protected GenericScorer GetGenericScorer()
  public sealed class AnomalyPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal AnomalyPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,
@@ -326,8 +330,8 @@ private static VersionInfo GetVersionInfo()
  public sealed class BinaryPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal BinaryPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -36,7 +36,7 @@ namespace Microsoft.ML.Trainers.FastTree
  public sealed partial class FastTreeRegressionTrainer
  : BoostingFastTreeTrainerBase<FastTreeRegressionTrainer.Options, RegressionPredictionTransformer<FastTreeRegressionModelParameters>, FastTreeRegressionModelParameters>
  {
-public const string LoadNameValue = "FastTreeRegression";
+internal const string LoadNameValue = "FastTreeRegression";
  internal const string UserNameValue = "FastTree (Boosted Trees) Regression";
  internal const string Summary = "Trains gradient boosted decision trees to fit target values using least-squares.";
  internal const string ShortName = "ftr";
@@ -142,7 +142,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -149,7 +149,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.LightGBM/LightGbmRankingTrainer.cs

@@ -75,9 +75,9 @@ private static LightGbmRankingModelParameters Create(IHostEnvironment env, Model
  /// <include file='doc.xml' path='doc/members/member[@name="LightGBM"]/*' />
  public sealed class LightGbmRankingTrainer : LightGbmTrainerBase<float, RankingPredictionTransformer<LightGbmRankingModelParameters>, LightGbmRankingModelParameters>
  {
-public const string UserName = "LightGBM Ranking";
-public const string LoadNameValue = "LightGBMRanking";
-public const string ShortName = "LightGBMRank";
+internal const string UserName = "LightGBM Ranking";
+internal const string LoadNameValue = "LightGBMRanking";
+internal const string ShortName = "LightGBMRank";
 
  public override PredictionKind PredictionKind => PredictionKind.Ranking;
 

src/Microsoft.ML.OnnxTransform/DnnImageFeaturizerTransform.cs

@@ -61,7 +61,7 @@ public sealed class DnnImageFeaturizerEstimator : IEstimator<TransformerChain<Co
  /// For an example, see Microsoft.ML.DnnImageFeaturizer.ResNet18 </param>
  /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
  /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
-public DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
+internal DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
  {
  _modelChain = modelFactory(new DnnImageFeaturizerInput(outputColumnName, inputColumnName ?? outputColumnName, env, new DnnImageModelSelector()));
  }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -2,6 +2,7 @@
 // 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;
 using Microsoft.ML.Data;
 using Microsoft.ML.Transforms;
 
@@ -61,5 +62,19 @@ public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog
  bool fallbackToCpu = false)
  => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnNames, inputColumnNames, modelFile, gpuDeviceId, fallbackToCpu);
 
+ /// <summary>
+ /// Creates a new instance of <see cref="DnnImageFeaturizerEstimator"/> which applies a pre-trained DNN model to featurize an image.
+ /// </summary>
+ /// <param name="catalog">The transform's catalog.</param>
+ /// <param name="outputColumnName">The name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
+ /// <param name="modelFactory">An extension method on the <see cref="DnnImageModelSelector"/> that creates a chain of two
+ /// <see cref="OnnxScoringEstimator"/> (one for preprocessing and one with a pretrained image DNN) with specific models
+ /// included in a package together with that extension method.</param>
+ /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
+ public static DnnImageFeaturizerEstimator DnnFeaturizeImage(this TransformsCatalog catalog,
+ string outputColumnName,
+ Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory,
+ string inputColumnName = null)
+ => new DnnImageFeaturizerEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, modelFactory, inputColumnName);
  }
 }

src/Microsoft.ML.StandardLearners/FactorizationMachine/FieldAwareFactorizationMachineModelParameters.cs

@@ -285,17 +285,17 @@ public float[] GetLatentWeights()
 
  public sealed class FieldAwareFactorizationMachinePredictionTransformer : PredictionTransformerBase<FieldAwareFactorizationMachineModelParameters>
  {
-public const string LoaderSignature = "FAFMPredXfer";
+internal const string LoaderSignature = "FAFMPredXfer";
 
  /// <summary>
  /// The name of the feature column used by the prediction transformer.
  /// </summary>
-public IReadOnlyList<string> FeatureColumns { get; }
+internal IReadOnlyList<string> FeatureColumns { get; }
 
  /// <summary>
  /// The type of the feature columns.
  /// </summary>
-public IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
+internal IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
 
  private readonly string _thresholdColumn;
  private readonly float _threshold;

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -35,7 +35,7 @@ public sealed partial class LogisticRegression : LbfgsTrainerBase<LogisticRegres
  BinaryPredictionTransformer<CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>,
  CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>
  {
-public const string LoadNameValue = "LogisticRegression";
+internal const string LoadNameValue = "LogisticRegression";
  internal const string UserNameValue = "Logistic Regression";
  internal const string ShortName = "lr";
  internal const string Summary = "Logistic Regression is a method in statistics used to predict the probability of occurrence of an event and can "

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/MulticlassLogisticRegression.cs

@@ -41,7 +41,7 @@ namespace Microsoft.ML.Trainers
  public sealed class MulticlassLogisticRegression : LbfgsTrainerBase<MulticlassLogisticRegression.Options,
  MulticlassPredictionTransformer<MulticlassLogisticRegressionModelParameters>, MulticlassLogisticRegressionModelParameters>
  {
-public const string LoadNameValue = "MultiClassLogisticRegression";
+internal const string LoadNameValue = "MultiClassLogisticRegression";
  internal const string UserNameValue = "Multi-class Logistic Regression";
  internal const string ShortName = "mlr";
 

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/PriorTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class PriorTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Prior(labelColumn: "Sentiment"));
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // The Prior trainer outputs the proportion of a label in the dataset as the probability of that label.
+ // In this case it means that there is a split of around 64%-36% of positive and negative labels in the dataset.
+ // Expected output:
+ // Accuracy: 0.647058823529412
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/RandomTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class RandomTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext(seed: 1);
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Random());
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // We expect an output probability closet to 0.5 as the Random trainer outputs a random prediction.
+ // Regardless of the input features, the trainer will predict either positive or negative label with equal probability.
+ // Expected output (close to 0.5):
+ // Accuracy: 0.588235294117647
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSample.cs

@@ -0,0 +1,70 @@
+using System;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class CustomMappingSample
+ {
+ public static void Example()
+ {
+ // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+ // as well as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Get a small dataset as an IEnumerable and convert it to an IDataView.
+ var data = SamplesUtils.DatasetUtils.GetInfertData();
+ var trainData = mlContext.Data.ReadFromEnumerable(data);
+
+ // Preview of the data.
+ //
+ // Age Case Education Induced Parity PooledStratum RowNum ...
+ // 26 1 0-5yrs 1 6 3 1 ...
+ // 42 1 0-5yrs 1 1 1 2 ...
+ // 39 1 0-5yrs 2 6 4 3 ...
+ // 34 1 0-5yrs 2 4 2 4 ...
+ // 35 1 6-11yrs 1 3 32 5 ...
+
+ // We define the custom mapping between input and output rows that will be applied by the transformation.
+ Action<SamplesUtils.DatasetUtils.SampleInfertData, SampleInfertDataTransformed> mapping = 
+ (input, output) => output.IsUnderThirty = input.Age < 30;
+
+ // Custom transformations can be used to transform data directly, or as part of a pipeline. Below we transform data directly.
+ var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
+ var transformedData = transformer.Transform(trainData);
+
+ // Preview of the data.
+ //
+ // IsUnderThirty Age Case Education Induced Parity PooledStratum RowNum ...
+ // true 26 1 0-5yrs 1 6 3 1 ...
+ // false 42 1 0-5yrs 1 1 1 2 ...
+ // false 39 1 0-5yrs 2 6 4 3 ...
+ // false 34 1 0-5yrs 2 4 2 4 ...
+ // false 35 1 6-11yrs 1 3 32 5 ...
+
+ // Here instead we use it as part of a pipeline of estimators.
+ var pipeline = mlContext.Transforms.CustomMapping(mapping, null)
+ .Append(mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: new[] { "Parity", "Induced" }))
+ // It is useful to add a caching checkpoint before a trainer that does several passes over the data.
+ .AppendCacheCheckpoint(mlContext)
+ // We use binary FastTree to predict the label column that was generated by the custom mapping at the first step of the pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumn: "IsUnderThirty"));
+
+ // We can train the pipeline and use it to transform data.
+ transformedData = pipeline.Fit(trainData).Transform(trainData);
+ }
+
+ // Represents the transformed infertility dataset.
+ public class SampleInfertDataTransformed
+ {
+ public int RowNum { get; set; }
+ public string Education { get; set; }
+ public bool IsUnderThirty { get; set; }
+ public float Parity { get; set; }
+ public float Induced { get; set; }
+ public float Case { get; set; }
+ public float Spontaneous { get; set; }
+ public float Stratum { get; set; }
+ public float PooledStratum { get; set; }
+ }
+ }
+}

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoader.cs

@@ -905,7 +905,7 @@ private Schema ComputeOutputSchema()
 
  internal const string Summary = "Loads text data file.";
 
-public const string LoaderSignature = "TextLoader";
+internal const string LoaderSignature = "TextLoader";
 
  private const uint VerForceVectorSupported = 0x0001000A;
  private const uint VersionNoMinCount = 0x0001000C;

src/Microsoft.ML.Data/DataLoadSave/TransformWrapper.cs

@@ -20,7 +20,7 @@ namespace Microsoft.ML.Data
  // It needs to become internal.
  public sealed class TransformWrapper : ITransformer
  {
-public const string LoaderSignature = "TransformWrapper";
+internal const string LoaderSignature = "TransformWrapper";
  private const string TransformDirTemplate = "Step_{0:000}";
 
  private readonly IHost _host;

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -54,6 +54,10 @@ public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer
  private protected ISchemaBindableMapper BindableMapper;
  protected Schema TrainSchema;
 
+ /// <summary>
+ /// Whether a call to <see cref="GetRowToRowMapper(Schema)"/> should succeed, on an
+ /// appropriate schema.
+ /// </summary>
  public bool IsRowToRowMapper => true;
 
  /// <summary>
@@ -257,8 +261,8 @@ private protected GenericScorer GetGenericScorer()
  public sealed class AnomalyPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal AnomalyPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,
@@ -326,8 +330,8 @@ private static VersionInfo GetVersionInfo()
  public sealed class BinaryPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal BinaryPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -36,7 +36,7 @@ namespace Microsoft.ML.Trainers.FastTree
  public sealed partial class FastTreeRegressionTrainer
  : BoostingFastTreeTrainerBase<FastTreeRegressionTrainer.Options, RegressionPredictionTransformer<FastTreeRegressionModelParameters>, FastTreeRegressionModelParameters>
  {
-public const string LoadNameValue = "FastTreeRegression";
+internal const string LoadNameValue = "FastTreeRegression";
  internal const string UserNameValue = "FastTree (Boosted Trees) Regression";
  internal const string Summary = "Trains gradient boosted decision trees to fit target values using least-squares.";
  internal const string ShortName = "ftr";
@@ -142,7 +142,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -149,7 +149,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.LightGBM/LightGbmRankingTrainer.cs

@@ -75,9 +75,9 @@ private static LightGbmRankingModelParameters Create(IHostEnvironment env, Model
  /// <include file='doc.xml' path='doc/members/member[@name="LightGBM"]/*' />
  public sealed class LightGbmRankingTrainer : LightGbmTrainerBase<float, RankingPredictionTransformer<LightGbmRankingModelParameters>, LightGbmRankingModelParameters>
  {
-public const string UserName = "LightGBM Ranking";
-public const string LoadNameValue = "LightGBMRanking";
-public const string ShortName = "LightGBMRank";
+internal const string UserName = "LightGBM Ranking";
+internal const string LoadNameValue = "LightGBMRanking";
+internal const string ShortName = "LightGBMRank";
 
  public override PredictionKind PredictionKind => PredictionKind.Ranking;
 

src/Microsoft.ML.OnnxTransform/DnnImageFeaturizerTransform.cs

@@ -61,7 +61,7 @@ public sealed class DnnImageFeaturizerEstimator : IEstimator<TransformerChain<Co
  /// For an example, see Microsoft.ML.DnnImageFeaturizer.ResNet18 </param>
  /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
  /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
-public DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
+internal DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
  {
  _modelChain = modelFactory(new DnnImageFeaturizerInput(outputColumnName, inputColumnName ?? outputColumnName, env, new DnnImageModelSelector()));
  }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -2,6 +2,7 @@
 // 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;
 using Microsoft.ML.Data;
 using Microsoft.ML.Transforms;
 
@@ -61,5 +62,19 @@ public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog
  bool fallbackToCpu = false)
  => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnNames, inputColumnNames, modelFile, gpuDeviceId, fallbackToCpu);
 
+ /// <summary>
+ /// Creates a new instance of <see cref="DnnImageFeaturizerEstimator"/> which applies a pre-trained DNN model to featurize an image.
+ /// </summary>
+ /// <param name="catalog">The transform's catalog.</param>
+ /// <param name="outputColumnName">The name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
+ /// <param name="modelFactory">An extension method on the <see cref="DnnImageModelSelector"/> that creates a chain of two
+ /// <see cref="OnnxScoringEstimator"/> (one for preprocessing and one with a pretrained image DNN) with specific models
+ /// included in a package together with that extension method.</param>
+ /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
+ public static DnnImageFeaturizerEstimator DnnFeaturizeImage(this TransformsCatalog catalog,
+ string outputColumnName,
+ Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory,
+ string inputColumnName = null)
+ => new DnnImageFeaturizerEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, modelFactory, inputColumnName);
  }
 }

src/Microsoft.ML.StandardLearners/FactorizationMachine/FieldAwareFactorizationMachineModelParameters.cs

@@ -285,17 +285,17 @@ public float[] GetLatentWeights()
 
  public sealed class FieldAwareFactorizationMachinePredictionTransformer : PredictionTransformerBase<FieldAwareFactorizationMachineModelParameters>
  {
-public const string LoaderSignature = "FAFMPredXfer";
+internal const string LoaderSignature = "FAFMPredXfer";
 
  /// <summary>
  /// The name of the feature column used by the prediction transformer.
  /// </summary>
-public IReadOnlyList<string> FeatureColumns { get; }
+internal IReadOnlyList<string> FeatureColumns { get; }
 
  /// <summary>
  /// The type of the feature columns.
  /// </summary>
-public IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
+internal IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
 
  private readonly string _thresholdColumn;
  private readonly float _threshold;

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -35,7 +35,7 @@ public sealed partial class LogisticRegression : LbfgsTrainerBase<LogisticRegres
  BinaryPredictionTransformer<CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>,
  CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>
  {
-public const string LoadNameValue = "LogisticRegression";
+internal const string LoadNameValue = "LogisticRegression";
  internal const string UserNameValue = "Logistic Regression";
  internal const string ShortName = "lr";
  internal const string Summary = "Logistic Regression is a method in statistics used to predict the probability of occurrence of an event and can "

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/MulticlassLogisticRegression.cs

@@ -41,7 +41,7 @@ namespace Microsoft.ML.Trainers
  public sealed class MulticlassLogisticRegression : LbfgsTrainerBase<MulticlassLogisticRegression.Options,
  MulticlassPredictionTransformer<MulticlassLogisticRegressionModelParameters>, MulticlassLogisticRegressionModelParameters>
  {
-public const string LoadNameValue = "MultiClassLogisticRegression";
+internal const string LoadNameValue = "MultiClassLogisticRegression";
  internal const string UserNameValue = "Multi-class Logistic Regression";
  internal const string ShortName = "mlr";
 

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/PriorTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class PriorTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Prior(labelColumn: "Sentiment"));
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // The Prior trainer outputs the proportion of a label in the dataset as the probability of that label.
+ // In this case it means that there is a split of around 64%-36% of positive and negative labels in the dataset.
+ // Expected output:
+ // Accuracy: 0.647058823529412
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/RandomTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class RandomTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext(seed: 1);
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Random());
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // We expect an output probability closet to 0.5 as the Random trainer outputs a random prediction.
+ // Regardless of the input features, the trainer will predict either positive or negative label with equal probability.
+ // Expected output (close to 0.5):
+ // Accuracy: 0.588235294117647
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSample.cs

@@ -0,0 +1,70 @@
+using System;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class CustomMappingSample
+ {
+ public static void Example()
+ {
+ // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+ // as well as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Get a small dataset as an IEnumerable and convert it to an IDataView.
+ var data = SamplesUtils.DatasetUtils.GetInfertData();
+ var trainData = mlContext.Data.ReadFromEnumerable(data);
+
+ // Preview of the data.
+ //
+ // Age Case Education Induced Parity PooledStratum RowNum ...
+ // 26 1 0-5yrs 1 6 3 1 ...
+ // 42 1 0-5yrs 1 1 1 2 ...
+ // 39 1 0-5yrs 2 6 4 3 ...
+ // 34 1 0-5yrs 2 4 2 4 ...
+ // 35 1 6-11yrs 1 3 32 5 ...
+
+ // We define the custom mapping between input and output rows that will be applied by the transformation.
+ Action<SamplesUtils.DatasetUtils.SampleInfertData, SampleInfertDataTransformed> mapping = 
+ (input, output) => output.IsUnderThirty = input.Age < 30;
+
+ // Custom transformations can be used to transform data directly, or as part of a pipeline. Below we transform data directly.
+ var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
+ var transformedData = transformer.Transform(trainData);
+
+ // Preview of the data.
+ //
+ // IsUnderThirty Age Case Education Induced Parity PooledStratum RowNum ...
+ // true 26 1 0-5yrs 1 6 3 1 ...
+ // false 42 1 0-5yrs 1 1 1 2 ...
+ // false 39 1 0-5yrs 2 6 4 3 ...
+ // false 34 1 0-5yrs 2 4 2 4 ...
+ // false 35 1 6-11yrs 1 3 32 5 ...
+
+ // Here instead we use it as part of a pipeline of estimators.
+ var pipeline = mlContext.Transforms.CustomMapping(mapping, null)
+ .Append(mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: new[] { "Parity", "Induced" }))
+ // It is useful to add a caching checkpoint before a trainer that does several passes over the data.
+ .AppendCacheCheckpoint(mlContext)
+ // We use binary FastTree to predict the label column that was generated by the custom mapping at the first step of the pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumn: "IsUnderThirty"));
+
+ // We can train the pipeline and use it to transform data.
+ transformedData = pipeline.Fit(trainData).Transform(trainData);
+ }
+
+ // Represents the transformed infertility dataset.
+ public class SampleInfertDataTransformed
+ {
+ public int RowNum { get; set; }
+ public string Education { get; set; }
+ public bool IsUnderThirty { get; set; }
+ public float Parity { get; set; }
+ public float Induced { get; set; }
+ public float Case { get; set; }
+ public float Spontaneous { get; set; }
+ public float Stratum { get; set; }
+ public float PooledStratum { get; set; }
+ }
+ }
+}

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoader.cs

@@ -905,7 +905,7 @@ private Schema ComputeOutputSchema()
 
  internal const string Summary = "Loads text data file.";
 
-public const string LoaderSignature = "TextLoader";
+internal const string LoaderSignature = "TextLoader";
 
  private const uint VerForceVectorSupported = 0x0001000A;
  private const uint VersionNoMinCount = 0x0001000C;

src/Microsoft.ML.Data/DataLoadSave/TransformWrapper.cs

@@ -20,7 +20,7 @@ namespace Microsoft.ML.Data
  // It needs to become internal.
  public sealed class TransformWrapper : ITransformer
  {
-public const string LoaderSignature = "TransformWrapper";
+internal const string LoaderSignature = "TransformWrapper";
  private const string TransformDirTemplate = "Step_{0:000}";
 
  private readonly IHost _host;

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -54,6 +54,10 @@ public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer
  private protected ISchemaBindableMapper BindableMapper;
  protected Schema TrainSchema;
 
+ /// <summary>
+ /// Whether a call to <see cref="GetRowToRowMapper(Schema)"/> should succeed, on an
+ /// appropriate schema.
+ /// </summary>
  public bool IsRowToRowMapper => true;
 
  /// <summary>
@@ -257,8 +261,8 @@ private protected GenericScorer GetGenericScorer()
  public sealed class AnomalyPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal AnomalyPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,
@@ -326,8 +330,8 @@ private static VersionInfo GetVersionInfo()
  public sealed class BinaryPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal BinaryPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -36,7 +36,7 @@ namespace Microsoft.ML.Trainers.FastTree
  public sealed partial class FastTreeRegressionTrainer
  : BoostingFastTreeTrainerBase<FastTreeRegressionTrainer.Options, RegressionPredictionTransformer<FastTreeRegressionModelParameters>, FastTreeRegressionModelParameters>
  {
-public const string LoadNameValue = "FastTreeRegression";
+internal const string LoadNameValue = "FastTreeRegression";
  internal const string UserNameValue = "FastTree (Boosted Trees) Regression";
  internal const string Summary = "Trains gradient boosted decision trees to fit target values using least-squares.";
  internal const string ShortName = "ftr";
@@ -142,7 +142,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -149,7 +149,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.LightGBM/LightGbmRankingTrainer.cs

@@ -75,9 +75,9 @@ private static LightGbmRankingModelParameters Create(IHostEnvironment env, Model
  /// <include file='doc.xml' path='doc/members/member[@name="LightGBM"]/*' />
  public sealed class LightGbmRankingTrainer : LightGbmTrainerBase<float, RankingPredictionTransformer<LightGbmRankingModelParameters>, LightGbmRankingModelParameters>
  {
-public const string UserName = "LightGBM Ranking";
-public const string LoadNameValue = "LightGBMRanking";
-public const string ShortName = "LightGBMRank";
+internal const string UserName = "LightGBM Ranking";
+internal const string LoadNameValue = "LightGBMRanking";
+internal const string ShortName = "LightGBMRank";
 
  public override PredictionKind PredictionKind => PredictionKind.Ranking;
 

src/Microsoft.ML.OnnxTransform/DnnImageFeaturizerTransform.cs

@@ -61,7 +61,7 @@ public sealed class DnnImageFeaturizerEstimator : IEstimator<TransformerChain<Co
  /// For an example, see Microsoft.ML.DnnImageFeaturizer.ResNet18 </param>
  /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
  /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
-public DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
+internal DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
  {
  _modelChain = modelFactory(new DnnImageFeaturizerInput(outputColumnName, inputColumnName ?? outputColumnName, env, new DnnImageModelSelector()));
  }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -2,6 +2,7 @@
 // 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;
 using Microsoft.ML.Data;
 using Microsoft.ML.Transforms;
 
@@ -61,5 +62,19 @@ public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog
  bool fallbackToCpu = false)
  => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnNames, inputColumnNames, modelFile, gpuDeviceId, fallbackToCpu);
 
+ /// <summary>
+ /// Creates a new instance of <see cref="DnnImageFeaturizerEstimator"/> which applies a pre-trained DNN model to featurize an image.
+ /// </summary>
+ /// <param name="catalog">The transform's catalog.</param>
+ /// <param name="outputColumnName">The name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
+ /// <param name="modelFactory">An extension method on the <see cref="DnnImageModelSelector"/> that creates a chain of two
+ /// <see cref="OnnxScoringEstimator"/> (one for preprocessing and one with a pretrained image DNN) with specific models
+ /// included in a package together with that extension method.</param>
+ /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
+ public static DnnImageFeaturizerEstimator DnnFeaturizeImage(this TransformsCatalog catalog,
+ string outputColumnName,
+ Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory,
+ string inputColumnName = null)
+ => new DnnImageFeaturizerEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, modelFactory, inputColumnName);
  }
 }

src/Microsoft.ML.StandardLearners/FactorizationMachine/FieldAwareFactorizationMachineModelParameters.cs

@@ -285,17 +285,17 @@ public float[] GetLatentWeights()
 
  public sealed class FieldAwareFactorizationMachinePredictionTransformer : PredictionTransformerBase<FieldAwareFactorizationMachineModelParameters>
  {
-public const string LoaderSignature = "FAFMPredXfer";
+internal const string LoaderSignature = "FAFMPredXfer";
 
  /// <summary>
  /// The name of the feature column used by the prediction transformer.
  /// </summary>
-public IReadOnlyList<string> FeatureColumns { get; }
+internal IReadOnlyList<string> FeatureColumns { get; }
 
  /// <summary>
  /// The type of the feature columns.
  /// </summary>
-public IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
+internal IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
 
  private readonly string _thresholdColumn;
  private readonly float _threshold;

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -35,7 +35,7 @@ public sealed partial class LogisticRegression : LbfgsTrainerBase<LogisticRegres
  BinaryPredictionTransformer<CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>,
  CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>
  {
-public const string LoadNameValue = "LogisticRegression";
+internal const string LoadNameValue = "LogisticRegression";
  internal const string UserNameValue = "Logistic Regression";
  internal const string ShortName = "lr";
  internal const string Summary = "Logistic Regression is a method in statistics used to predict the probability of occurrence of an event and can "

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/MulticlassLogisticRegression.cs

@@ -41,7 +41,7 @@ namespace Microsoft.ML.Trainers
  public sealed class MulticlassLogisticRegression : LbfgsTrainerBase<MulticlassLogisticRegression.Options,
  MulticlassPredictionTransformer<MulticlassLogisticRegressionModelParameters>, MulticlassLogisticRegressionModelParameters>
  {
-public const string LoadNameValue = "MultiClassLogisticRegression";
+internal const string LoadNameValue = "MultiClassLogisticRegression";
  internal const string UserNameValue = "Multi-class Logistic Regression";
  internal const string ShortName = "mlr";
 

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/PriorTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class PriorTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Prior(labelColumn: "Sentiment"));
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // The Prior trainer outputs the proportion of a label in the dataset as the probability of that label.
+ // In this case it means that there is a split of around 64%-36% of positive and negative labels in the dataset.
+ // Expected output:
+ // Accuracy: 0.647058823529412
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/RandomTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class RandomTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext(seed: 1);
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Random());
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // We expect an output probability closet to 0.5 as the Random trainer outputs a random prediction.
+ // Regardless of the input features, the trainer will predict either positive or negative label with equal probability.
+ // Expected output (close to 0.5):
+ // Accuracy: 0.588235294117647
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSample.cs

@@ -0,0 +1,70 @@
+using System;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class CustomMappingSample
+ {
+ public static void Example()
+ {
+ // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+ // as well as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Get a small dataset as an IEnumerable and convert it to an IDataView.
+ var data = SamplesUtils.DatasetUtils.GetInfertData();
+ var trainData = mlContext.Data.ReadFromEnumerable(data);
+
+ // Preview of the data.
+ //
+ // Age Case Education Induced Parity PooledStratum RowNum ...
+ // 26 1 0-5yrs 1 6 3 1 ...
+ // 42 1 0-5yrs 1 1 1 2 ...
+ // 39 1 0-5yrs 2 6 4 3 ...
+ // 34 1 0-5yrs 2 4 2 4 ...
+ // 35 1 6-11yrs 1 3 32 5 ...
+
+ // We define the custom mapping between input and output rows that will be applied by the transformation.
+ Action<SamplesUtils.DatasetUtils.SampleInfertData, SampleInfertDataTransformed> mapping = 
+ (input, output) => output.IsUnderThirty = input.Age < 30;
+
+ // Custom transformations can be used to transform data directly, or as part of a pipeline. Below we transform data directly.
+ var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
+ var transformedData = transformer.Transform(trainData);
+
+ // Preview of the data.
+ //
+ // IsUnderThirty Age Case Education Induced Parity PooledStratum RowNum ...
+ // true 26 1 0-5yrs 1 6 3 1 ...
+ // false 42 1 0-5yrs 1 1 1 2 ...
+ // false 39 1 0-5yrs 2 6 4 3 ...
+ // false 34 1 0-5yrs 2 4 2 4 ...
+ // false 35 1 6-11yrs 1 3 32 5 ...
+
+ // Here instead we use it as part of a pipeline of estimators.
+ var pipeline = mlContext.Transforms.CustomMapping(mapping, null)
+ .Append(mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: new[] { "Parity", "Induced" }))
+ // It is useful to add a caching checkpoint before a trainer that does several passes over the data.
+ .AppendCacheCheckpoint(mlContext)
+ // We use binary FastTree to predict the label column that was generated by the custom mapping at the first step of the pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumn: "IsUnderThirty"));
+
+ // We can train the pipeline and use it to transform data.
+ transformedData = pipeline.Fit(trainData).Transform(trainData);
+ }
+
+ // Represents the transformed infertility dataset.
+ public class SampleInfertDataTransformed
+ {
+ public int RowNum { get; set; }
+ public string Education { get; set; }
+ public bool IsUnderThirty { get; set; }
+ public float Parity { get; set; }
+ public float Induced { get; set; }
+ public float Case { get; set; }
+ public float Spontaneous { get; set; }
+ public float Stratum { get; set; }
+ public float PooledStratum { get; set; }
+ }
+ }
+}

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoader.cs

@@ -905,7 +905,7 @@ private Schema ComputeOutputSchema()
 
  internal const string Summary = "Loads text data file.";
 
-public const string LoaderSignature = "TextLoader";
+internal const string LoaderSignature = "TextLoader";
 
  private const uint VerForceVectorSupported = 0x0001000A;
  private const uint VersionNoMinCount = 0x0001000C;

src/Microsoft.ML.Data/DataLoadSave/TransformWrapper.cs

@@ -20,7 +20,7 @@ namespace Microsoft.ML.Data
  // It needs to become internal.
  public sealed class TransformWrapper : ITransformer
  {
-public const string LoaderSignature = "TransformWrapper";
+internal const string LoaderSignature = "TransformWrapper";
  private const string TransformDirTemplate = "Step_{0:000}";
 
  private readonly IHost _host;

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -54,6 +54,10 @@ public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer
  private protected ISchemaBindableMapper BindableMapper;
  protected Schema TrainSchema;
 
+ /// <summary>
+ /// Whether a call to <see cref="GetRowToRowMapper(Schema)"/> should succeed, on an
+ /// appropriate schema.
+ /// </summary>
  public bool IsRowToRowMapper => true;
 
  /// <summary>
@@ -257,8 +261,8 @@ private protected GenericScorer GetGenericScorer()
  public sealed class AnomalyPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal AnomalyPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,
@@ -326,8 +330,8 @@ private static VersionInfo GetVersionInfo()
  public sealed class BinaryPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal BinaryPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -36,7 +36,7 @@ namespace Microsoft.ML.Trainers.FastTree
  public sealed partial class FastTreeRegressionTrainer
  : BoostingFastTreeTrainerBase<FastTreeRegressionTrainer.Options, RegressionPredictionTransformer<FastTreeRegressionModelParameters>, FastTreeRegressionModelParameters>
  {
-public const string LoadNameValue = "FastTreeRegression";
+internal const string LoadNameValue = "FastTreeRegression";
  internal const string UserNameValue = "FastTree (Boosted Trees) Regression";
  internal const string Summary = "Trains gradient boosted decision trees to fit target values using least-squares.";
  internal const string ShortName = "ftr";
@@ -142,7 +142,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -149,7 +149,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.LightGBM/LightGbmRankingTrainer.cs

@@ -75,9 +75,9 @@ private static LightGbmRankingModelParameters Create(IHostEnvironment env, Model
  /// <include file='doc.xml' path='doc/members/member[@name="LightGBM"]/*' />
  public sealed class LightGbmRankingTrainer : LightGbmTrainerBase<float, RankingPredictionTransformer<LightGbmRankingModelParameters>, LightGbmRankingModelParameters>
  {
-public const string UserName = "LightGBM Ranking";
-public const string LoadNameValue = "LightGBMRanking";
-public const string ShortName = "LightGBMRank";
+internal const string UserName = "LightGBM Ranking";
+internal const string LoadNameValue = "LightGBMRanking";
+internal const string ShortName = "LightGBMRank";
 
  public override PredictionKind PredictionKind => PredictionKind.Ranking;
 

src/Microsoft.ML.OnnxTransform/DnnImageFeaturizerTransform.cs

@@ -61,7 +61,7 @@ public sealed class DnnImageFeaturizerEstimator : IEstimator<TransformerChain<Co
  /// For an example, see Microsoft.ML.DnnImageFeaturizer.ResNet18 </param>
  /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
  /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
-public DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
+internal DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
  {
  _modelChain = modelFactory(new DnnImageFeaturizerInput(outputColumnName, inputColumnName ?? outputColumnName, env, new DnnImageModelSelector()));
  }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -2,6 +2,7 @@
 // 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;
 using Microsoft.ML.Data;
 using Microsoft.ML.Transforms;
 
@@ -61,5 +62,19 @@ public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog
  bool fallbackToCpu = false)
  => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnNames, inputColumnNames, modelFile, gpuDeviceId, fallbackToCpu);
 
+ /// <summary>
+ /// Creates a new instance of <see cref="DnnImageFeaturizerEstimator"/> which applies a pre-trained DNN model to featurize an image.
+ /// </summary>
+ /// <param name="catalog">The transform's catalog.</param>
+ /// <param name="outputColumnName">The name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
+ /// <param name="modelFactory">An extension method on the <see cref="DnnImageModelSelector"/> that creates a chain of two
+ /// <see cref="OnnxScoringEstimator"/> (one for preprocessing and one with a pretrained image DNN) with specific models
+ /// included in a package together with that extension method.</param>
+ /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
+ public static DnnImageFeaturizerEstimator DnnFeaturizeImage(this TransformsCatalog catalog,
+ string outputColumnName,
+ Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory,
+ string inputColumnName = null)
+ => new DnnImageFeaturizerEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, modelFactory, inputColumnName);
  }
 }

src/Microsoft.ML.StandardLearners/FactorizationMachine/FieldAwareFactorizationMachineModelParameters.cs

@@ -285,17 +285,17 @@ public float[] GetLatentWeights()
 
  public sealed class FieldAwareFactorizationMachinePredictionTransformer : PredictionTransformerBase<FieldAwareFactorizationMachineModelParameters>
  {
-public const string LoaderSignature = "FAFMPredXfer";
+internal const string LoaderSignature = "FAFMPredXfer";
 
  /// <summary>
  /// The name of the feature column used by the prediction transformer.
  /// </summary>
-public IReadOnlyList<string> FeatureColumns { get; }
+internal IReadOnlyList<string> FeatureColumns { get; }
 
  /// <summary>
  /// The type of the feature columns.
  /// </summary>
-public IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
+internal IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
 
  private readonly string _thresholdColumn;
  private readonly float _threshold;

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -35,7 +35,7 @@ public sealed partial class LogisticRegression : LbfgsTrainerBase<LogisticRegres
  BinaryPredictionTransformer<CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>,
  CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>
  {
-public const string LoadNameValue = "LogisticRegression";
+internal const string LoadNameValue = "LogisticRegression";
  internal const string UserNameValue = "Logistic Regression";
  internal const string ShortName = "lr";
  internal const string Summary = "Logistic Regression is a method in statistics used to predict the probability of occurrence of an event and can "

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/MulticlassLogisticRegression.cs

@@ -41,7 +41,7 @@ namespace Microsoft.ML.Trainers
  public sealed class MulticlassLogisticRegression : LbfgsTrainerBase<MulticlassLogisticRegression.Options,
  MulticlassPredictionTransformer<MulticlassLogisticRegressionModelParameters>, MulticlassLogisticRegressionModelParameters>
  {
-public const string LoadNameValue = "MultiClassLogisticRegression";
+internal const string LoadNameValue = "MultiClassLogisticRegression";
  internal const string UserNameValue = "Multi-class Logistic Regression";
  internal const string ShortName = "mlr";
 

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/PriorTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class PriorTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Prior(labelColumn: "Sentiment"));
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // The Prior trainer outputs the proportion of a label in the dataset as the probability of that label.
+ // In this case it means that there is a split of around 64%-36% of positive and negative labels in the dataset.
+ // Expected output:
+ // Accuracy: 0.647058823529412
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/RandomTrainerSample.cs

@@ -0,0 +1,67 @@
+using System;
+using System.Linq;
+using Microsoft.ML.Data;
+using Microsoft.ML.Trainers;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class RandomTrainerSample
+ {
+ public static void Example()
+ {
+ // Downloading the dataset from github.com/dotnet/machinelearning.
+ // This will create a sentiment.tsv file in the filesystem.
+ // You can open this file, if you want to see the data. 
+ string dataFile = SamplesUtils.DatasetUtils.DownloadSentimentDataset();
+
+ // A preview of the data. 
+ // Sentiment	SentimentText
+ // 0 " :Erm, thank you. "
+ // 1 ==You're cool==
+
+ // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
+ // as a catalog of available operations and as the source of randomness.
+ var mlContext = new MLContext(seed: 1);
+
+ // Step 1: Read the data as an IDataView.
+ // First, we define the reader: specify the data columns and where to find them in the text file.
+ var reader = mlContext.Data.CreateTextLoader(
+ columns: new[]
+ {
+ new TextLoader.Column("Sentiment", DataKind.R4, 0),
+ new TextLoader.Column("SentimentText", DataKind.Text, 1)
+ },
+ hasHeader: true
+ );
+
+ // Read the data
+ var data = reader.Read(dataFile);
+
+ // Split it between training and test data
+ var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data);
+
+ // Step 2: Pipeline 
+ // Featurize the text column through the FeaturizeText API. 
+ // Then append a binary classifier, setting the "Label" column as the label of the dataset, and 
+ // the "Features" column produced by FeaturizeText as the features column.
+ var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
+ .AppendCacheCheckpoint(mlContext) // Add a data-cache step within a pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.Random());
+
+ // Step 3: Train the pipeline
+ var trainedPipeline = pipeline.Fit(trainTestData.TrainSet);
+
+ // Step 4: Evaluate on the test set
+ var transformedData = trainedPipeline.Transform(trainTestData.TestSet);
+ var evalMetrics = mlContext.BinaryClassification.Evaluate(transformedData, label: "Sentiment");
+
+ // Step 5: Inspect the output
+ Console.WriteLine("Accuracy: " + evalMetrics.Accuracy);
+
+ // We expect an output probability closet to 0.5 as the Random trainer outputs a random prediction.
+ // Regardless of the input features, the trainer will predict either positive or negative label with equal probability.
+ // Expected output (close to 0.5):
+ // Accuracy: 0.588235294117647
+ }
+ }
+}

docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/CustomMappingSample.cs

@@ -0,0 +1,70 @@
+using System;
+using Microsoft.ML.Data;
+
+namespace Microsoft.ML.Samples.Dynamic
+{
+ public class CustomMappingSample
+ {
+ public static void Example()
+ {
+ // Create a new ML context, for ML.NET operations. It can be used for exception tracking and logging, 
+ // as well as the source of randomness.
+ var mlContext = new MLContext();
+
+ // Get a small dataset as an IEnumerable and convert it to an IDataView.
+ var data = SamplesUtils.DatasetUtils.GetInfertData();
+ var trainData = mlContext.Data.ReadFromEnumerable(data);
+
+ // Preview of the data.
+ //
+ // Age Case Education Induced Parity PooledStratum RowNum ...
+ // 26 1 0-5yrs 1 6 3 1 ...
+ // 42 1 0-5yrs 1 1 1 2 ...
+ // 39 1 0-5yrs 2 6 4 3 ...
+ // 34 1 0-5yrs 2 4 2 4 ...
+ // 35 1 6-11yrs 1 3 32 5 ...
+
+ // We define the custom mapping between input and output rows that will be applied by the transformation.
+ Action<SamplesUtils.DatasetUtils.SampleInfertData, SampleInfertDataTransformed> mapping = 
+ (input, output) => output.IsUnderThirty = input.Age < 30;
+
+ // Custom transformations can be used to transform data directly, or as part of a pipeline. Below we transform data directly.
+ var transformer = mlContext.Transforms.CustomMappingTransformer(mapping, null);
+ var transformedData = transformer.Transform(trainData);
+
+ // Preview of the data.
+ //
+ // IsUnderThirty Age Case Education Induced Parity PooledStratum RowNum ...
+ // true 26 1 0-5yrs 1 6 3 1 ...
+ // false 42 1 0-5yrs 1 1 1 2 ...
+ // false 39 1 0-5yrs 2 6 4 3 ...
+ // false 34 1 0-5yrs 2 4 2 4 ...
+ // false 35 1 6-11yrs 1 3 32 5 ...
+
+ // Here instead we use it as part of a pipeline of estimators.
+ var pipeline = mlContext.Transforms.CustomMapping(mapping, null)
+ .Append(mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: new[] { "Parity", "Induced" }))
+ // It is useful to add a caching checkpoint before a trainer that does several passes over the data.
+ .AppendCacheCheckpoint(mlContext)
+ // We use binary FastTree to predict the label column that was generated by the custom mapping at the first step of the pipeline.
+ .Append(mlContext.BinaryClassification.Trainers.FastTree(labelColumn: "IsUnderThirty"));
+
+ // We can train the pipeline and use it to transform data.
+ transformedData = pipeline.Fit(trainData).Transform(trainData);
+ }
+
+ // Represents the transformed infertility dataset.
+ public class SampleInfertDataTransformed
+ {
+ public int RowNum { get; set; }
+ public string Education { get; set; }
+ public bool IsUnderThirty { get; set; }
+ public float Parity { get; set; }
+ public float Induced { get; set; }
+ public float Case { get; set; }
+ public float Spontaneous { get; set; }
+ public float Stratum { get; set; }
+ public float PooledStratum { get; set; }
+ }
+ }
+}

src/Microsoft.ML.Data/DataLoadSave/Text/TextLoader.cs

@@ -905,7 +905,7 @@ private Schema ComputeOutputSchema()
 
  internal const string Summary = "Loads text data file.";
 
-public const string LoaderSignature = "TextLoader";
+internal const string LoaderSignature = "TextLoader";
 
  private const uint VerForceVectorSupported = 0x0001000A;
  private const uint VersionNoMinCount = 0x0001000C;

src/Microsoft.ML.Data/DataLoadSave/TransformWrapper.cs

@@ -20,7 +20,7 @@ namespace Microsoft.ML.Data
  // It needs to become internal.
  public sealed class TransformWrapper : ITransformer
  {
-public const string LoaderSignature = "TransformWrapper";
+internal const string LoaderSignature = "TransformWrapper";
  private const string TransformDirTemplate = "Step_{0:000}";
 
  private readonly IHost _host;

src/Microsoft.ML.Data/Scorers/PredictionTransformer.cs

@@ -54,6 +54,10 @@ public abstract class PredictionTransformerBase<TModel> : IPredictionTransformer
  private protected ISchemaBindableMapper BindableMapper;
  protected Schema TrainSchema;
 
+ /// <summary>
+ /// Whether a call to <see cref="GetRowToRowMapper(Schema)"/> should succeed, on an
+ /// appropriate schema.
+ /// </summary>
  public bool IsRowToRowMapper => true;
 
  /// <summary>
@@ -257,8 +261,8 @@ private protected GenericScorer GetGenericScorer()
  public sealed class AnomalyPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal AnomalyPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,
@@ -326,8 +330,8 @@ private static VersionInfo GetVersionInfo()
  public sealed class BinaryPredictionTransformer<TModel> : SingleFeaturePredictionTransformerBase<TModel>
  where TModel : class
  {
-public readonly string ThresholdColumn;
-public readonly float Threshold;
+internal readonly string ThresholdColumn;
+internal readonly float Threshold;
 
  [BestFriend]
  internal BinaryPredictionTransformer(IHostEnvironment env, TModel model, Schema inputSchema, string featureColumn,

src/Microsoft.ML.FastTree/FastTreeRegression.cs

@@ -36,7 +36,7 @@ namespace Microsoft.ML.Trainers.FastTree
  public sealed partial class FastTreeRegressionTrainer
  : BoostingFastTreeTrainerBase<FastTreeRegressionTrainer.Options, RegressionPredictionTransformer<FastTreeRegressionModelParameters>, FastTreeRegressionModelParameters>
  {
-public const string LoadNameValue = "FastTreeRegression";
+internal const string LoadNameValue = "FastTreeRegression";
  internal const string UserNameValue = "FastTree (Boosted Trees) Regression";
  internal const string Summary = "Trains gradient boosted decision trees to fit target values using least-squares.";
  internal const string ShortName = "ftr";
@@ -142,7 +142,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.FastTree/FastTreeTweedie.cs

@@ -149,7 +149,7 @@ private protected override OptimizationAlgorithm ConstructOptimizationAlgorithm(
  /// </summary>
  /// <param name="set">The dataset</param>
  /// <returns>The list of regression targets, or null if <paramref name="set"/> was null</returns>
-public static float[] GetDatasetRegressionLabels(Dataset set)
+internal static float[] GetDatasetRegressionLabels(Dataset set)
  {
  if (set == null)
  return null;

src/Microsoft.ML.LightGBM/LightGbmRankingTrainer.cs

@@ -75,9 +75,9 @@ private static LightGbmRankingModelParameters Create(IHostEnvironment env, Model
  /// <include file='doc.xml' path='doc/members/member[@name="LightGBM"]/*' />
  public sealed class LightGbmRankingTrainer : LightGbmTrainerBase<float, RankingPredictionTransformer<LightGbmRankingModelParameters>, LightGbmRankingModelParameters>
  {
-public const string UserName = "LightGBM Ranking";
-public const string LoadNameValue = "LightGBMRanking";
-public const string ShortName = "LightGBMRank";
+internal const string UserName = "LightGBM Ranking";
+internal const string LoadNameValue = "LightGBMRanking";
+internal const string ShortName = "LightGBMRank";
 
  public override PredictionKind PredictionKind => PredictionKind.Ranking;
 

src/Microsoft.ML.OnnxTransform/DnnImageFeaturizerTransform.cs

@@ -61,7 +61,7 @@ public sealed class DnnImageFeaturizerEstimator : IEstimator<TransformerChain<Co
  /// For an example, see Microsoft.ML.DnnImageFeaturizer.ResNet18 </param>
  /// <param name="outputColumnName">Name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
  /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
-public DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
+internal DnnImageFeaturizerEstimator(IHostEnvironment env, string outputColumnName, Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory, string inputColumnName = null)
  {
  _modelChain = modelFactory(new DnnImageFeaturizerInput(outputColumnName, inputColumnName ?? outputColumnName, env, new DnnImageModelSelector()));
  }

src/Microsoft.ML.OnnxTransform/OnnxCatalog.cs

@@ -2,6 +2,7 @@
 // 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;
 using Microsoft.ML.Data;
 using Microsoft.ML.Transforms;
 
@@ -61,5 +62,19 @@ public static OnnxScoringEstimator ApplyOnnxModel(this TransformsCatalog catalog
  bool fallbackToCpu = false)
  => new OnnxScoringEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnNames, inputColumnNames, modelFile, gpuDeviceId, fallbackToCpu);
 
+ /// <summary>
+ /// Creates a new instance of <see cref="DnnImageFeaturizerEstimator"/> which applies a pre-trained DNN model to featurize an image.
+ /// </summary>
+ /// <param name="catalog">The transform's catalog.</param>
+ /// <param name="outputColumnName">The name of the column resulting from the transformation of <paramref name="inputColumnName"/>.</param>
+ /// <param name="modelFactory">An extension method on the <see cref="DnnImageModelSelector"/> that creates a chain of two
+ /// <see cref="OnnxScoringEstimator"/> (one for preprocessing and one with a pretrained image DNN) with specific models
+ /// included in a package together with that extension method.</param>
+ /// <param name="inputColumnName">Name of column to transform. If set to <see langword="null"/>, the value of the <paramref name="outputColumnName"/> will be used as source.</param>
+ public static DnnImageFeaturizerEstimator DnnFeaturizeImage(this TransformsCatalog catalog,
+ string outputColumnName,
+ Func<DnnImageFeaturizerInput, EstimatorChain<ColumnCopyingTransformer>> modelFactory,
+ string inputColumnName = null)
+ => new DnnImageFeaturizerEstimator(CatalogUtils.GetEnvironment(catalog), outputColumnName, modelFactory, inputColumnName);
  }
 }

src/Microsoft.ML.StandardLearners/FactorizationMachine/FieldAwareFactorizationMachineModelParameters.cs

@@ -285,17 +285,17 @@ public float[] GetLatentWeights()
 
  public sealed class FieldAwareFactorizationMachinePredictionTransformer : PredictionTransformerBase<FieldAwareFactorizationMachineModelParameters>
  {
-public const string LoaderSignature = "FAFMPredXfer";
+internal const string LoaderSignature = "FAFMPredXfer";
 
  /// <summary>
  /// The name of the feature column used by the prediction transformer.
  /// </summary>
-public IReadOnlyList<string> FeatureColumns { get; }
+internal IReadOnlyList<string> FeatureColumns { get; }
 
  /// <summary>
  /// The type of the feature columns.
  /// </summary>
-public IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
+internal IReadOnlyList<ColumnType> FeatureColumnTypes { get; }
 
  private readonly string _thresholdColumn;
  private readonly float _threshold;

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/LogisticRegression.cs

@@ -35,7 +35,7 @@ public sealed partial class LogisticRegression : LbfgsTrainerBase<LogisticRegres
  BinaryPredictionTransformer<CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>,
  CalibratedModelParametersBase<LinearBinaryModelParameters, PlattCalibrator>>
  {
-public const string LoadNameValue = "LogisticRegression";
+internal const string LoadNameValue = "LogisticRegression";
  internal const string UserNameValue = "Logistic Regression";
  internal const string ShortName = "lr";
  internal const string Summary = "Logistic Regression is a method in statistics used to predict the probability of occurrence of an event and can "

src/Microsoft.ML.StandardLearners/Standard/LogisticRegression/MulticlassLogisticRegression.cs

@@ -41,7 +41,7 @@ namespace Microsoft.ML.Trainers
  public sealed class MulticlassLogisticRegression : LbfgsTrainerBase<MulticlassLogisticRegression.Options,
  MulticlassPredictionTransformer<MulticlassLogisticRegressionModelParameters>, MulticlassLogisticRegressionModelParameters>
  {
-public const string LoadNameValue = "MultiClassLogisticRegression";
+internal const string LoadNameValue = "MultiClassLogisticRegression";
  internal const string UserNameValue = "Multi-class Logistic Regression";
  internal const string ShortName = "mlr";