TrainTestSplit should be inside MLContext.Data (#2907)

ganik · web-flow · commit cd333c59180c · 2019-03-11T12:43:29.000-07:00
* TrainTestSplit should be inside MLContext.Data

* fix md files
diff --git a/docs/code/MlNetCookBook.md b/docs/code/MlNetCookBook.md
@@ -825,7 +825,7 @@ var pipeline =
     .Append(mlContext.MulticlassClassification.Trainers.StochasticDualCoordinateAscent());
 
 // Split the data 90:10 into train and test sets, train and evaluate.
-var split = mlContext.MulticlassClassification.TrainTestSplit(data, testFraction: 0.1);
+var split = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
 // Train the model.
 var model = pipeline.Fit(split.TrainSet);
diff --git a/docs/code/experimental/MlNetCookBookStaticApi.md b/docs/code/experimental/MlNetCookBookStaticApi.md
@@ -907,7 +907,7 @@ var learningPipeline = loader.MakeNewEstimator()
         Predictions: mlContext.MulticlassClassification.Trainers.Sdca(r.Label, r.Features)));
 
 // Split the data 90:10 into train and test sets, train and evaluate.
-var (trainData, testData) = mlContext.MulticlassClassification.TrainTestSplit(data, testFraction: 0.1);
+var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
 // Train the model.
 var model = learningPipeline.Fit(trainData);
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/LogisticRegression.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/LogisticRegression.cs
@@ -57,7 +57,7 @@ public static void Example()
 
             IDataView data = loader.Load(dataFilePath);
 
-            var split = ml.BinaryClassification.TrainTestSplit(data, testFraction: 0.2);
+            var split = ml.Data.TrainTestSplit(data, testFraction: 0.2);
 
             var pipeline = ml.Transforms.Concatenate("Text", "workclass", "education", "marital-status",
                     "relationship", "ethnicity", "sex", "native-country")
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs
@@ -16,7 +16,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Create data training pipeline.
             var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numIterations: 10);
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs
@@ -18,7 +18,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Define the trainer options.
             var options = new AveragedPerceptronTrainer.Options()
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/FixedPlatt.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/FixedPlatt.cs
@@ -15,7 +15,7 @@ public static void Example()
             // Download and featurize the dataset.
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.3);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.3);
 
             // Create data training pipeline for non calibrated trainer and train Naive calibrator on top of it.
             var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Isotonic.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Isotonic.cs
@@ -15,7 +15,7 @@ public static void Example()
             // Download and featurize the dataset.
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.3);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.3);
 
             // Create data training pipeline for non calibrated trainer and train Naive calibrator on top of it.
             var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Naive.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Naive.cs
@@ -15,7 +15,7 @@ public static void Example()
             // Download and featurize the dataset.
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.3);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.3);
 
             // Create data training pipeline for non calibrated trainer and train Naive calibrator on top of it.
             var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Platt.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Platt.cs
@@ -15,7 +15,7 @@ public static void Example()
             // Download and featurize the dataset.
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.3);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.3);
 
             // Create data training pipeline for non calibrated trainer and train Naive calibrator on top of it.
             var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/LightGbm.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/LightGbm.cs
@@ -12,7 +12,7 @@ public static void Example()
             var dataview = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var split = mlContext.BinaryClassification.TrainTestSplit(dataview, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(dataview, testFraction: 0.1);
 
             // Create the Estimator.
             var pipeline = mlContext.BinaryClassification.Trainers.LightGbm();
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/LightGbmWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/LightGbmWithOptions.cs
@@ -15,7 +15,7 @@ public static void Example()
             var dataview = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var split = mlContext.BinaryClassification.TrainTestSplit(dataview, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(dataview, testFraction: 0.1);
 
             // Create the pipeline with LightGbm Estimator using advanced options.
             var pipeline = mlContext.BinaryClassification.Trainers.LightGbm(
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticDualCoordinateAscentWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticDualCoordinateAscentWithOptions.cs
@@ -19,7 +19,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Define the trainer options.
             var options = new SdcaBinaryTrainer.Options()
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescent.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescent.cs
@@ -16,7 +16,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Create data training pipeline.
             var pipeline = mlContext.BinaryClassification.Trainers.StochasticGradientDescent();
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentNonCalibrated.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentNonCalibrated.cs
@@ -16,7 +16,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Create data training pipeline.
             var pipeline = mlContext.BinaryClassification.Trainers.StochasticGradientDescentNonCalibrated();
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentNonCalibratedWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentNonCalibratedWithOptions.cs
@@ -18,7 +18,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Create data training pipeline.
             var pipeline = mlContext.BinaryClassification
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentWithOptions.cs
@@ -18,7 +18,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Define the trainer options.
             var options = new SgdBinaryTrainer.Options()
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SymbolicStochasticGradientDescent.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SymbolicStochasticGradientDescent.cs
@@ -17,7 +17,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var split = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
             // Create data training pipeline.
             var pipeline = mlContext.BinaryClassification.Trainers.SymbolicStochasticGradientDescent(labelColumnName: "IsOver50K", numberOfIterations: 25);
             var model = pipeline.Fit(split.TrainSet);
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SymbolicStochasticGradientDescentWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SymbolicStochasticGradientDescentWithOptions.cs
@@ -17,7 +17,7 @@ public static void Example()
             var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 
             // Leave out 10% of data for testing.
-            var split = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
             // Create data training pipeline
             var pipeline = mlContext.BinaryClassification.Trainers.SymbolicStochasticGradientDescent(
                     new ML.Trainers.SymbolicStochasticGradientDescentClassificationTrainer.Options()
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/LightGbm.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/LightGbm.cs
@@ -37,7 +37,7 @@ public static void Example()
 
             // Split the static-typed data into training and test sets. Only training set is used in fitting
             // the created pipeline. Metrics are computed on the test.
-            var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.5);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.5);
 
             // Train the model.
             var model = pipeline.Fit(split.TrainSet);
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/LightGbmWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/LightGbmWithOptions.cs
@@ -48,7 +48,7 @@ public static void Example()
 
             // Split the static-typed data into training and test sets. Only training set is used in fitting
             // the created pipeline. Metrics are computed on the test.
-            var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.5);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.5);
 
             // Train the model.
             var model = pipeline.Fit(split.TrainSet);
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/StochasticDualCoordinateAscent.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/StochasticDualCoordinateAscent.cs
@@ -34,7 +34,7 @@ public static void Example()
 
             // Split the data into training and test sets. Only training set is used in fitting
             // the created pipeline. Metrics are computed on the test.
-            var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
 
             // Train the model.
             var model = pipeline.Fit(split.TrainSet);
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/StochasticDualCoordinateAscentWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/StochasticDualCoordinateAscentWithOptions.cs
@@ -45,7 +45,7 @@ public static void Example()
 
             // Split the data into training and test sets. Only training set is used in fitting
             // the created pipeline. Metrics are computed on the test.
-            var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
 
             // Train the model.
             var model = pipeline.Fit(split.TrainSet);
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbm.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbm.cs
@@ -13,8 +13,8 @@ public static void Example()
 
             // Leave out 10% of the dataset for testing. Since this is a ranking problem, we must ensure that the split
             // respects the GroupId column, i.e. rows with the same GroupId are either all in the train split or all in
-            // the test split. The samplingKeyColumn parameter in Ranking.TrainTestSplit is used for this purpose.
-            var split = mlContext.Ranking.TrainTestSplit(dataview, testFraction: 0.1, samplingKeyColumn: "GroupId");
+            // the test split. The samplingKeyColumn parameter in Data.TrainTestSplit is used for this purpose.
+            var split = mlContext.Data.TrainTestSplit(dataview, testFraction: 0.1, samplingKeyColumn: "GroupId");
 
             // Create the Estimator pipeline. For simplicity, we will train a small tree with 4 leaves and 2 boosting iterations.
             var pipeline = mlContext.Ranking.Trainers.LightGbm(
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbmWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbmWithOptions.cs
@@ -16,8 +16,8 @@ public static void Example()
 
             // Leave out 10% of the dataset for testing. Since this is a ranking problem, we must ensure that the split
             // respects the GroupId column, i.e. rows with the same GroupId are either all in the train split or all in
-            // the test split. The samplingKeyColumn parameter in Ranking.TrainTestSplit is used for this purpose.
-            var split = mlContext.Ranking.TrainTestSplit(dataview, testFraction: 0.1, samplingKeyColumn: "GroupId");
+            // the test split. The samplingKeyColumn parameter in Data.TrainTestSplit is used for this purpose.
+            var split = mlContext.Data.TrainTestSplit(dataview, testFraction: 0.1, samplingKeyColumn: "GroupId");
 
             // Create the Estimator pipeline. For simplicity, we will train a small tree with 4 leaves and 2 boosting iterations.
             var pipeline = mlContext.Ranking.Trainers.LightGbm(
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbm.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbm.cs
@@ -23,7 +23,7 @@ public static void Example()
             // 21.60              0.02731            00.00                7.070               0               0.4690          6.4210              78.90             ...
             // 34.70              0.02729            00.00                7.070               0               0.4690          7.1850              61.10             ...
 
-            var split = mlContext.Regression.TrainTestSplit(dataView, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
 
             // Create the estimator, here we only need LightGbm trainer
             // as data is already processed in a form consumable by the trainer.
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbmWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbmWithOptions.cs
@@ -25,7 +25,7 @@ public static void Example()
             // 21.60              0.02731            00.00                7.070               0               0.4690          6.4210              78.90             ...
             // 34.70              0.02729            00.00                7.070               0               0.4690          7.1850              61.10             ...
 
-            var split = mlContext.Regression.TrainTestSplit(dataView, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
 
             // Create a pipeline with LightGbm estimator with advanced options.
             // Here we only need LightGbm trainer as data is already processed
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/OrdinaryLeastSquares.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/OrdinaryLeastSquares.cs
@@ -39,7 +39,7 @@ public static void Example()
             // 21.60              0.02731            00.00                7.070               0               0.4690          6.4210              78.90
             // 34.70              0.02729            00.00                7.070               0               0.4690          7.1850              61.10
 
-            var split = mlContext.Regression.TrainTestSplit(dataView, testFraction: 0.2);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.2);
 
             // Create the estimator, here we only need OrdinaryLeastSquares trainer 
             // as data is already processed in a form consumable by the trainer
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/OrdinaryLeastSquaresWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/OrdinaryLeastSquaresWithOptions.cs
@@ -40,7 +40,7 @@ public static void Example()
             // 21.60              0.02731            00.00                7.070               0               0.4690          6.4210              78.90
             // 34.70              0.02729            00.00                7.070               0               0.4690          7.1850              61.10
 
-            var split = mlContext.Regression.TrainTestSplit(dataView, testFraction: 0.2);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.2);
 
             // Create the estimator, here we only need OrdinaryLeastSquares trainer 
             // as data is already processed in a form consumable by the trainer
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/StochasticDualCoordinateAscent.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/StochasticDualCoordinateAscent.cs
@@ -19,7 +19,7 @@ public static void Example()
 
             // Split the data into training and test sets. Only training set is used in fitting
             // the created pipeline. Metrics are computed on the test.
-            var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
 
             // Train the model.
             var pipeline = mlContext.Regression.Trainers.StochasticDualCoordinateAscent();
diff --git a/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/StochasticDualCoordinateAscentWithOptions.cs b/docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/StochasticDualCoordinateAscentWithOptions.cs
@@ -18,7 +18,7 @@ public static void Example()
 
             // Split the data into training and test sets. Only training set is used in fitting
             // the created pipeline. Metrics are computed on the test.
-            var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.1);
+            var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
 
             // Create trainer options.
             var options = new SdcaRegressionTrainer.Options
diff --git a/docs/samples/Microsoft.ML.Samples/Static/AveragedPerceptronBinaryClassification.cs b/docs/samples/Microsoft.ML.Samples/Static/AveragedPerceptronBinaryClassification.cs
@@ -55,7 +55,7 @@ public static void AveragedPerceptronBinaryClassification()
 
             // Load the data, and leave 10% out, so we can use them for testing
             var data = loader.Load(dataFilePath);
-            var (trainData, testData) = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Create the Estimator
             var learningPipeline = loader.MakeNewEstimator()
diff --git a/docs/samples/Microsoft.ML.Samples/Static/FastTreeBinaryClassification.cs b/docs/samples/Microsoft.ML.Samples/Static/FastTreeBinaryClassification.cs
@@ -56,7 +56,7 @@ public static void FastTreeBinaryClassification()
 
             // Loader the data, and leave 10% out, so we can use them for testing
             var data = loader.Load(dataFilePath);
-            var (trainData, testData) = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Create the Estimator
             var learningPipeline = loader.MakeNewEstimator()
diff --git a/docs/samples/Microsoft.ML.Samples/Static/LightGBMBinaryClassification.cs b/docs/samples/Microsoft.ML.Samples/Static/LightGBMBinaryClassification.cs
@@ -56,7 +56,7 @@ public static void LightGbmBinaryClassification()
 
             // Load the data, and leave 10% out, so we can use them for testing
             var data = loader.Load(dataFilePath);
-            var (trainData, testData) = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
+            var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // Create the Estimator
             var learningPipeline = loader.MakeNewEstimator()
diff --git a/docs/samples/Microsoft.ML.Samples/Static/LightGBMMulticlassWithInMemoryData.cs b/docs/samples/Microsoft.ML.Samples/Static/LightGBMMulticlassWithInMemoryData.cs
@@ -52,7 +52,7 @@ public void MultiClassLightGbmStaticPipelineWithInMemoryData()
 
             // Split the static-typed data into training and test sets. Only training set is used in fitting
             // the created pipeline. Metrics are computed on the test.
-            var (trainingData, testingData) = mlContext.MulticlassClassification.TrainTestSplit(staticDataView, testFraction: 0.5);
+            var (trainingData, testingData) = mlContext.Data.TrainTestSplit(staticDataView, testFraction: 0.5);
 
             // Train the model.
             var model = pipe.Fit(trainingData);
diff --git a/docs/samples/Microsoft.ML.Samples/Static/LightGBMRegression.cs b/docs/samples/Microsoft.ML.Samples/Static/LightGBMRegression.cs
@@ -28,7 +28,7 @@ public static void LightGbmRegression()
 
             // Load the data, and leave 10% out, so we can use them for testing
             var data = loader.Load(new MultiFileSource(dataFile));
-            var (trainData, testData) = mlContext.Regression.TrainTestSplit(data, testFraction: 0.1);
+            var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 
             // The predictor that gets produced out of training
             LightGbmRegressionModelParameters pred = null;
diff --git a/docs/samples/Microsoft.ML.Samples/Static/SDCABinaryClassification.cs b/docs/samples/Microsoft.ML.Samples/Static/SDCABinaryClassification.cs
diff --git a/docs/samples/Microsoft.ML.Samples/Static/SDCARegression.cs b/docs/samples/Microsoft.ML.Samples/Static/SDCARegression.cs
diff --git a/src/Microsoft.ML.Data/DataLoadSave/DataOperationsCatalog.cs b/src/Microsoft.ML.Data/DataLoadSave/DataOperationsCatalog.cs
diff --git a/src/Microsoft.ML.Data/TrainCatalog.cs b/src/Microsoft.ML.Data/TrainCatalog.cs
diff --git a/src/Microsoft.ML.StaticPipe/TrainingStaticExtensions.cs b/src/Microsoft.ML.StaticPipe/TrainingStaticExtensions.cs
diff --git a/test/Microsoft.ML.Functional.Tests/Prediction.cs b/test/Microsoft.ML.Functional.Tests/Prediction.cs
diff --git a/test/Microsoft.ML.Functional.Tests/Validation.cs b/test/Microsoft.ML.Functional.Tests/Validation.cs
diff --git a/test/Microsoft.ML.StaticPipelineTesting/StaticPipeTests.cs b/test/Microsoft.ML.StaticPipelineTesting/StaticPipeTests.cs
diff --git a/test/Microsoft.ML.StaticPipelineTesting/Training.cs b/test/Microsoft.ML.StaticPipelineTesting/Training.cs
diff --git a/test/Microsoft.ML.Tests/Scenarios/Api/CookbookSamples/CookbookSamples.cs b/test/Microsoft.ML.Tests/Scenarios/Api/CookbookSamples/CookbookSamples.cs
diff --git a/test/Microsoft.ML.Tests/Scenarios/Api/CookbookSamples/CookbookSamplesDynamicApi.cs b/test/Microsoft.ML.Tests/Scenarios/Api/CookbookSamples/CookbookSamplesDynamicApi.cs
diff --git a/test/Microsoft.ML.Tests/Scenarios/Api/TestApi.cs b/test/Microsoft.ML.Tests/Scenarios/Api/TestApi.cs
