Skip to content

Commit cd333c5

Browse files
ganikganik
authored
TrainTestSplit should be inside MLContext.Data (#2907)
* TrainTestSplit should be inside MLContext.Data * fix md files
1 parent 005fe05 commit cd333c5

File tree

47 files changed

+155
-157
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

47 files changed

+155
-157
lines changed

‎docs/code/MlNetCookBook.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -825,7 +825,7 @@ var pipeline =
825825
.Append(mlContext.MulticlassClassification.Trainers.StochasticDualCoordinateAscent());
826826

827827
// Split the data 90:10 into train and test sets, train and evaluate.
828-
var split = mlContext.MulticlassClassification.TrainTestSplit(data, testFraction: 0.1);
828+
var split = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
829829

830830
// Train the model.
831831
var model = pipeline.Fit(split.TrainSet);

‎docs/code/experimental/MlNetCookBookStaticApi.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -907,7 +907,7 @@ var learningPipeline = loader.MakeNewEstimator()
907907
Predictions: mlContext.MulticlassClassification.Trainers.Sdca(r.Label, r.Features)));
908908

909909
// Split the data 90:10 into train and test sets, train and evaluate.
910-
var (trainData, testData) = mlContext.MulticlassClassification.TrainTestSplit(data, testFraction: 0.1);
910+
var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
911911

912912
// Train the model.
913913
var model = learningPipeline.Fit(trainData);

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

+1-1
Original file line numberDiff line numberDiff line change
@@ -57,7 +57,7 @@ public static void Example()
5757

5858
IDataView data = loader.Load(dataFilePath);
5959

60-
var split = ml.BinaryClassification.TrainTestSplit(data, testFraction: 0.2);
60+
var split = ml.Data.TrainTestSplit(data, testFraction: 0.2);
6161

6262
var pipeline = ml.Transforms.Concatenate("Text", "workclass", "education", "marital-status",
6363
"relationship", "ethnicity", "sex", "native-country")

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@ public static void Example()
1616
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1717

1818
// Leave out 10% of data for testing.
19-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
19+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2020

2121
// Create data training pipeline.
2222
var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numIterations: 10);

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ public static void Example()
1818
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1919

2020
// Leave out 10% of data for testing.
21-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
21+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2222

2323
// Define the trainer options.
2424
var options = new AveragedPerceptronTrainer.Options()

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/FixedPlatt.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ public static void Example()
1515
// Download and featurize the dataset.
1616
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1717
// Leave out 10% of data for testing.
18-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.3);
18+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.3);
1919

2020
// Create data training pipeline for non calibrated trainer and train Naive calibrator on top of it.
2121
var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Isotonic.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ public static void Example()
1515
// Download and featurize the dataset.
1616
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1717
// Leave out 10% of data for testing.
18-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.3);
18+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.3);
1919

2020
// Create data training pipeline for non calibrated trainer and train Naive calibrator on top of it.
2121
var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Naive.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ public static void Example()
1515
// Download and featurize the dataset.
1616
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1717
// Leave out 10% of data for testing.
18-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.3);
18+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.3);
1919

2020
// Create data training pipeline for non calibrated trainer and train Naive calibrator on top of it.
2121
var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/Calibrators/Platt.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ public static void Example()
1515
// Download and featurize the dataset.
1616
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1717
// Leave out 10% of data for testing.
18-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.3);
18+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.3);
1919

2020
// Create data training pipeline for non calibrated trainer and train Naive calibrator on top of it.
2121
var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/LightGbm.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ public static void Example()
1212
var dataview = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1313

1414
// Leave out 10% of data for testing.
15-
var split = mlContext.BinaryClassification.TrainTestSplit(dataview, testFraction: 0.1);
15+
var split = mlContext.Data.TrainTestSplit(dataview, testFraction: 0.1);
1616

1717
// Create the Estimator.
1818
var pipeline = mlContext.BinaryClassification.Trainers.LightGbm();

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/LightGbmWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ public static void Example()
1515
var dataview = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1616

1717
// Leave out 10% of data for testing.
18-
var split = mlContext.BinaryClassification.TrainTestSplit(dataview, testFraction: 0.1);
18+
var split = mlContext.Data.TrainTestSplit(dataview, testFraction: 0.1);
1919

2020
// Create the pipeline with LightGbm Estimator using advanced options.
2121
var pipeline = mlContext.BinaryClassification.Trainers.LightGbm(

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticDualCoordinateAscentWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ public static void Example()
1919
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
2020

2121
// Leave out 10% of data for testing.
22-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
22+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2323

2424
// Define the trainer options.
2525
var options = new SdcaBinaryTrainer.Options()

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescent.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@ public static void Example()
1616
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1717

1818
// Leave out 10% of data for testing.
19-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
19+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2020

2121
// Create data training pipeline.
2222
var pipeline = mlContext.BinaryClassification.Trainers.StochasticGradientDescent();

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentNonCalibrated.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@ public static void Example()
1616
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1717

1818
// Leave out 10% of data for testing.
19-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
19+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2020

2121
// Create data training pipeline.
2222
var pipeline = mlContext.BinaryClassification.Trainers.StochasticGradientDescentNonCalibrated();

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentNonCalibratedWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ public static void Example()
1818
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1919

2020
// Leave out 10% of data for testing.
21-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
21+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2222

2323
// Create data training pipeline.
2424
var pipeline = mlContext.BinaryClassification

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/StochasticGradientDescentWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ public static void Example()
1818
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1919

2020
// Leave out 10% of data for testing.
21-
var trainTestData = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
21+
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2222

2323
// Define the trainer options.
2424
var options = new SgdBinaryTrainer.Options()

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SymbolicStochasticGradientDescent.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ public static void Example()
1717
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1818

1919
// Leave out 10% of data for testing.
20-
var split = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
20+
var split = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2121
// Create data training pipeline.
2222
var pipeline = mlContext.BinaryClassification.Trainers.SymbolicStochasticGradientDescent(labelColumnName: "IsOver50K", numberOfIterations: 25);
2323
var model = pipeline.Fit(split.TrainSet);

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/SymbolicStochasticGradientDescentWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ public static void Example()
1717
var data = SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
1818

1919
// Leave out 10% of data for testing.
20-
var split = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
20+
var split = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
2121
// Create data training pipeline
2222
var pipeline = mlContext.BinaryClassification.Trainers.SymbolicStochasticGradientDescent(
2323
new ML.Trainers.SymbolicStochasticGradientDescentClassificationTrainer.Options()

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/LightGbm.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ public static void Example()
3737

3838
// Split the static-typed data into training and test sets. Only training set is used in fitting
3939
// the created pipeline. Metrics are computed on the test.
40-
var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.5);
40+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.5);
4141

4242
// Train the model.
4343
var model = pipeline.Fit(split.TrainSet);

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/LightGbmWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -48,7 +48,7 @@ public static void Example()
4848

4949
// Split the static-typed data into training and test sets. Only training set is used in fitting
5050
// the created pipeline. Metrics are computed on the test.
51-
var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.5);
51+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.5);
5252

5353
// Train the model.
5454
var model = pipeline.Fit(split.TrainSet);

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/StochasticDualCoordinateAscent.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@ public static void Example()
3434

3535
// Split the data into training and test sets. Only training set is used in fitting
3636
// the created pipeline. Metrics are computed on the test.
37-
var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.1);
37+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
3838

3939
// Train the model.
4040
var model = pipeline.Fit(split.TrainSet);

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/MulticlassClassification/StochasticDualCoordinateAscentWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -45,7 +45,7 @@ public static void Example()
4545

4646
// Split the data into training and test sets. Only training set is used in fitting
4747
// the created pipeline. Metrics are computed on the test.
48-
var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.1);
48+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
4949

5050
// Train the model.
5151
var model = pipeline.Fit(split.TrainSet);

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbm.cs

+2-2
Original file line numberDiff line numberDiff line change
@@ -13,8 +13,8 @@ public static void Example()
1313

1414
// Leave out 10% of the dataset for testing. Since this is a ranking problem, we must ensure that the split
1515
// respects the GroupId column, i.e. rows with the same GroupId are either all in the train split or all in
16-
// the test split. The samplingKeyColumn parameter in Ranking.TrainTestSplit is used for this purpose.
17-
var split = mlContext.Ranking.TrainTestSplit(dataview, testFraction: 0.1, samplingKeyColumn: "GroupId");
16+
// the test split. The samplingKeyColumn parameter in Data.TrainTestSplit is used for this purpose.
17+
var split = mlContext.Data.TrainTestSplit(dataview, testFraction: 0.1, samplingKeyColumn: "GroupId");
1818

1919
// Create the Estimator pipeline. For simplicity, we will train a small tree with 4 leaves and 2 boosting iterations.
2020
var pipeline = mlContext.Ranking.Trainers.LightGbm(

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Ranking/LightGbmWithOptions.cs

+2-2
Original file line numberDiff line numberDiff line change
@@ -16,8 +16,8 @@ public static void Example()
1616

1717
// Leave out 10% of the dataset for testing. Since this is a ranking problem, we must ensure that the split
1818
// respects the GroupId column, i.e. rows with the same GroupId are either all in the train split or all in
19-
// the test split. The samplingKeyColumn parameter in Ranking.TrainTestSplit is used for this purpose.
20-
var split = mlContext.Ranking.TrainTestSplit(dataview, testFraction: 0.1, samplingKeyColumn: "GroupId");
19+
// the test split. The samplingKeyColumn parameter in Data.TrainTestSplit is used for this purpose.
20+
var split = mlContext.Data.TrainTestSplit(dataview, testFraction: 0.1, samplingKeyColumn: "GroupId");
2121

2222
// Create the Estimator pipeline. For simplicity, we will train a small tree with 4 leaves and 2 boosting iterations.
2323
var pipeline = mlContext.Ranking.Trainers.LightGbm(

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbm.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -23,7 +23,7 @@ public static void Example()
2323
// 21.60 0.02731 00.00 7.070 0 0.4690 6.4210 78.90 ...
2424
// 34.70 0.02729 00.00 7.070 0 0.4690 7.1850 61.10 ...
2525

26-
var split = mlContext.Regression.TrainTestSplit(dataView, testFraction: 0.1);
26+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
2727

2828
// Create the estimator, here we only need LightGbm trainer
2929
// as data is already processed in a form consumable by the trainer.

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/LightGbmWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ public static void Example()
2525
// 21.60 0.02731 00.00 7.070 0 0.4690 6.4210 78.90 ...
2626
// 34.70 0.02729 00.00 7.070 0 0.4690 7.1850 61.10 ...
2727

28-
var split = mlContext.Regression.TrainTestSplit(dataView, testFraction: 0.1);
28+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
2929

3030
// Create a pipeline with LightGbm estimator with advanced options.
3131
// Here we only need LightGbm trainer as data is already processed

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/OrdinaryLeastSquares.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -39,7 +39,7 @@ public static void Example()
3939
// 21.60 0.02731 00.00 7.070 0 0.4690 6.4210 78.90
4040
// 34.70 0.02729 00.00 7.070 0 0.4690 7.1850 61.10
4141

42-
var split = mlContext.Regression.TrainTestSplit(dataView, testFraction: 0.2);
42+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.2);
4343

4444
// Create the estimator, here we only need OrdinaryLeastSquares trainer
4545
// as data is already processed in a form consumable by the trainer

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/OrdinaryLeastSquaresWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,7 @@ public static void Example()
4040
// 21.60 0.02731 00.00 7.070 0 0.4690 6.4210 78.90
4141
// 34.70 0.02729 00.00 7.070 0 0.4690 7.1850 61.10
4242

43-
var split = mlContext.Regression.TrainTestSplit(dataView, testFraction: 0.2);
43+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.2);
4444

4545
// Create the estimator, here we only need OrdinaryLeastSquares trainer
4646
// as data is already processed in a form consumable by the trainer

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/StochasticDualCoordinateAscent.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ public static void Example()
1919

2020
// Split the data into training and test sets. Only training set is used in fitting
2121
// the created pipeline. Metrics are computed on the test.
22-
var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.1);
22+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
2323

2424
// Train the model.
2525
var pipeline = mlContext.Regression.Trainers.StochasticDualCoordinateAscent();

‎docs/samples/Microsoft.ML.Samples/Dynamic/Trainers/Regression/StochasticDualCoordinateAscentWithOptions.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ public static void Example()
1818

1919
// Split the data into training and test sets. Only training set is used in fitting
2020
// the created pipeline. Metrics are computed on the test.
21-
var split = mlContext.MulticlassClassification.TrainTestSplit(dataView, testFraction: 0.1);
21+
var split = mlContext.Data.TrainTestSplit(dataView, testFraction: 0.1);
2222

2323
// Create trainer options.
2424
var options = new SdcaRegressionTrainer.Options

‎docs/samples/Microsoft.ML.Samples/Static/AveragedPerceptronBinaryClassification.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -55,7 +55,7 @@ public static void AveragedPerceptronBinaryClassification()
5555

5656
// Load the data, and leave 10% out, so we can use them for testing
5757
var data = loader.Load(dataFilePath);
58-
var (trainData, testData) = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
58+
var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
5959

6060
// Create the Estimator
6161
var learningPipeline = loader.MakeNewEstimator()

‎docs/samples/Microsoft.ML.Samples/Static/FastTreeBinaryClassification.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,7 @@ public static void FastTreeBinaryClassification()
5656

5757
// Loader the data, and leave 10% out, so we can use them for testing
5858
var data = loader.Load(dataFilePath);
59-
var (trainData, testData) = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
59+
var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
6060

6161
// Create the Estimator
6262
var learningPipeline = loader.MakeNewEstimator()

‎docs/samples/Microsoft.ML.Samples/Static/LightGBMBinaryClassification.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,7 @@ public static void LightGbmBinaryClassification()
5656

5757
// Load the data, and leave 10% out, so we can use them for testing
5858
var data = loader.Load(dataFilePath);
59-
var (trainData, testData) = mlContext.BinaryClassification.TrainTestSplit(data, testFraction: 0.1);
59+
var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
6060

6161
// Create the Estimator
6262
var learningPipeline = loader.MakeNewEstimator()

‎docs/samples/Microsoft.ML.Samples/Static/LightGBMMulticlassWithInMemoryData.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -52,7 +52,7 @@ public void MultiClassLightGbmStaticPipelineWithInMemoryData()
5252

5353
// Split the static-typed data into training and test sets. Only training set is used in fitting
5454
// the created pipeline. Metrics are computed on the test.
55-
var (trainingData, testingData) = mlContext.MulticlassClassification.TrainTestSplit(staticDataView, testFraction: 0.5);
55+
var (trainingData, testingData) = mlContext.Data.TrainTestSplit(staticDataView, testFraction: 0.5);
5656

5757
// Train the model.
5858
var model = pipe.Fit(trainingData);

‎docs/samples/Microsoft.ML.Samples/Static/LightGBMRegression.cs

+1-1
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,7 @@ public static void LightGbmRegression()
2828

2929
// Load the data, and leave 10% out, so we can use them for testing
3030
var data = loader.Load(new MultiFileSource(dataFile));
31-
var (trainData, testData) = mlContext.Regression.TrainTestSplit(data, testFraction: 0.1);
31+
var (trainData, testData) = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
3232

3333
// The predictor that gets produced out of training
3434
LightGbmRegressionModelParameters pred = null;

0 commit comments

Comments
 (0)