public void SetupBreastCancerPipeline()
{
_breastCancerExample = new BreastCancerData()
{
Features = new[] { 5f, 1f, 1f, 1f, 2f, 1f, 3f, 1f, 1f }
};
string _breastCancerDataPath = BaseTestClass.GetDataPath("breast-cancer.txt");
var env = new MLContext(seed: 1, conc: 1);
var reader = new TextLoader(env, columns: new[]
{
new TextLoader.Column("Label", DataKind.BL, 0),
new TextLoader.Column("Features", DataKind.R4, new[] { new TextLoader.Range(1, 9) })
},
hasHeader: false
);
IDataView data = reader.Read(_breastCancerDataPath);
var pipeline = env.BinaryClassification.Trainers.StochasticDualCoordinateAscent(
new SdcaBinaryTrainer.Options {
NumThreads = 1, ConvergenceTolerance = 1e-2f,
});
var model = pipeline.Fit(data);
_breastCancerModel = model.CreatePredictionEngine <BreastCancerData, BreastCancerPrediction>(env);
}
public void Setup()
{
_context = new MLContext(1);
var data = _context.Data.LoadFromTextFile <SentimentData>(BaseTestClass.GetDataPath("wikipedia-detox-250-line-data.tsv"), hasHeader: true);
// Pipeline.
var pipeline = _context.Transforms.Text.FeaturizeText("Features", "SentimentText")
.AppendCacheCheckpoint(_context)
.Append(_context.BinaryClassification.Trainers.SdcaNonCalibrated(
new SdcaNonCalibratedBinaryTrainer.Options {
NumberOfThreads = 1
}));
// Train.
var model = pipeline.Fit(data);
var modelPath = "temp.zip";
// Save model.
_context.Model.Save(model, data.Schema, modelPath);
// Load model.
_trainedModel = _context.Model.Load(modelPath, out var inputSchema);
_trainedModelOldFormat = _context.Model.Load(Path.Combine("TestModels", "SentimentModel.zip"), out inputSchema);
}
void CrossValidation()
{
var mlContext = new MLContext(seed: 1);
// Get the dataset.
var data = mlContext.Data.CreateTextLoader(TestDatasets.housing.GetLoaderColumns(),
hasHeader: TestDatasets.housing.fileHasHeader, separatorChar: TestDatasets.housing.fileSeparator)
.Load(BaseTestClass.GetDataPath(TestDatasets.housing.trainFilename));
// Create a pipeline to train on the sentiment data.
var pipeline = mlContext.Transforms.Concatenate("Features", new string[] {
"CrimesPerCapita", "PercentResidental", "PercentNonRetail", "CharlesRiver", "NitricOxides", "RoomsPerDwelling",
"PercentPre40s", "EmploymentDistance", "HighwayDistance", "TaxRate", "TeacherRatio"
})
.Append(mlContext.Transforms.CopyColumns("Label", "MedianHomeValue"))
.Append(mlContext.Regression.Trainers.OrdinaryLeastSquares());
// Compute the CV result.
var cvResult = mlContext.Regression.CrossValidate(data, pipeline, numFolds: 5);
// Check that the results are valid
Assert.IsType <RegressionMetrics>(cvResult[0].Metrics);
Assert.IsType <TransformerChain <RegressionPredictionTransformer <OrdinaryLeastSquaresRegressionModelParameters> > >(cvResult[0].Model);
Assert.True(cvResult[0].ScoredHoldOutSet is IDataView);
Assert.Equal(5, cvResult.Length);
// And validate the metrics.
foreach (var result in cvResult)
{
Common.AssertMetrics(result.Metrics);
}
}
public void ReconfigurablePrediction()
{
var mlContext = new MLContext(seed: 789);
// Get the dataset, create a train and test
var data = mlContext.Data.CreateTextLoader(TestDatasets.housing.GetLoaderColumns(),
hasHeader: TestDatasets.housing.fileHasHeader, separatorChar: TestDatasets.housing.fileSeparator)
.Load(BaseTestClass.GetDataPath(TestDatasets.housing.trainFilename));
var split = mlContext.Data.TrainTestSplit(data, testFraction: 0.2);
// Create a pipeline to train on the housing data
var pipeline = mlContext.Transforms.Concatenate("Features", new string[] {
"CrimesPerCapita", "PercentResidental", "PercentNonRetail", "CharlesRiver", "NitricOxides", "RoomsPerDwelling",
"PercentPre40s", "EmploymentDistance", "HighwayDistance", "TaxRate", "TeacherRatio"
})
.Append(mlContext.Transforms.CopyColumns("Label", "MedianHomeValue"))
.Append(mlContext.Regression.Trainers.Ols());
var model = pipeline.Fit(split.TrainSet);
var scoredTest = model.Transform(split.TestSet);
var metrics = mlContext.Regression.Evaluate(scoredTest);
Common.AssertMetrics(metrics);
// Todo #2465: Allow the setting of threshold and thresholdColumn for scoring.
// This is no longer possible in the API
//var newModel = new BinaryPredictionTransformer<IPredictorProducing<float>>(ml, model.Model, trainData.Schema, model.FeatureColumnName, threshold: 0.01f, thresholdColumn: DefaultColumnNames.Probability);
//var newScoredTest = newModel.Transform(pipeline.Transform(testData));
//var newMetrics = mlContext.BinaryClassification.Evaluate(scoredTest);
// And the Threshold and ThresholdColumn properties are not settable.
//var predictor = model.LastTransformer;
//predictor.Threshold = 0.01; // Not possible
}
public void SetupSentimentPipeline()
{
_sentimentExample = new SentimentData()
{
SentimentText = "Not a big fan of this."
};
string _sentimentDataPath = BaseTestClass.GetDataPath("wikipedia-detox-250-line-data.tsv");
var env = new MLContext(seed: 1, conc: 1);
var reader = new TextLoader(env, columns: new[]
{
new TextLoader.Column("Label", DataKind.BL, 0),
new TextLoader.Column("SentimentText", DataKind.Text, 1)
},
hasHeader: true
);
IDataView data = reader.Read(_sentimentDataPath);
var pipeline = new TextFeaturizingEstimator(env, "Features", "SentimentText")
.Append(env.BinaryClassification.Trainers.StochasticDualCoordinateAscent(
new SdcaBinaryTrainer.Options {
NumThreads = 1, ConvergenceTolerance = 1e-2f,
}));
var model = pipeline.Fit(data);
_sentimentModel = model.CreatePredictionEngine <SentimentData, SentimentPrediction>(env);
}
public void SetupSentimentPipeline()
{
_sentimentExample = new SentimentData()
{
SentimentText = "Not a big fan of this."
};
string _sentimentDataPath = BaseTestClass.GetDataPath("wikipedia-detox-250-line-data.tsv");
var mlContext = new MLContext(seed: 1, conc: 1);
// Create text loader.
var options = new TextLoader.Options()
{
Columns = new[]
{
new TextLoader.Column("Label", DataKind.Boolean, 0),
new TextLoader.Column("SentimentText", DataKind.String, 1)
},
HasHeader = true,
};
var loader = new TextLoader(mlContext, options: options);
IDataView data = loader.Load(_sentimentDataPath);
var pipeline = mlContext.Transforms.Text.FeaturizeText("Features", "SentimentText")
.Append(mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscentNonCalibrated(
new SdcaNonCalibratedBinaryTrainer.Options {
NumberOfThreads = 1, ConvergenceTolerance = 1e-2f,
}));
var model = pipeline.Fit(data);
_sentimentModel = model.CreatePredictionEngine <SentimentData, SentimentPrediction>(mlContext);
}
public void SetupBreastCancerPipeline()
{
_breastCancerExample = new BreastCancerData()
{
Features = new[] { 5f, 1f, 1f, 1f, 2f, 1f, 3f, 1f, 1f }
};
string _breastCancerDataPath = BaseTestClass.GetDataPath("breast-cancer.txt");
var env = new MLContext(seed: 1, conc: 1);
// Create text loader.
var options = new TextLoader.Options()
{
Columns = new[]
{
new TextLoader.Column("Label", DataKind.Boolean, 0),
new TextLoader.Column("Features", DataKind.Single, new[] { new TextLoader.Range(1, 9) })
},
HasHeader = false,
};
var loader = new TextLoader(env, options: options);
IDataView data = loader.Load(_breastCancerDataPath);
var pipeline = env.BinaryClassification.Trainers.StochasticDualCoordinateAscentNonCalibrated(
new SdcaNonCalibratedBinaryTrainer.Options {
NumberOfThreads = 1, ConvergenceTolerance = 1e-2f,
});
var model = pipeline.Fit(data);
_breastCancerModel = model.CreatePredictionEngine <BreastCancerData, BreastCancerPrediction>(env);
}
public void SetupIrisPipeline()
{
_irisExample = new IrisData()
{
SepalLength = 3.3f,
SepalWidth = 1.6f,
PetalLength = 0.2f,
PetalWidth = 5.1f,
};
string _irisDataPath = BaseTestClass.GetDataPath("iris.txt");
var env = new MLContext(seed: 1, conc: 1);
var reader = new TextLoader(env,
columns: new[]
{
new TextLoader.Column("Label", DataKind.R4, 0),
new TextLoader.Column("SepalLength", DataKind.R4, 1),
new TextLoader.Column("SepalWidth", DataKind.R4, 2),
new TextLoader.Column("PetalLength", DataKind.R4, 3),
new TextLoader.Column("PetalWidth", DataKind.R4, 4),
},
hasHeader: true
);
IDataView data = reader.Read(_irisDataPath);
var pipeline = new ColumnConcatenatingEstimator(env, "Features", new[] { "SepalLength", "SepalWidth", "PetalLength", "PetalWidth" })
.Append(new SdcaMultiClassTrainer(env, "Label", "Features", advancedSettings: (s) => { s.NumThreads = 1; s.ConvergenceTolerance = 1e-2f; }));
var model = pipeline.Fit(data);
_irisModel = model.CreatePredictionEngine <IrisData, IrisPrediction>(env);
}
public void SetupTrainingSpeedTests()
{
_dataPath_Digits = BaseTestClass.GetDataPath(TestDatasets.Digits.trainFilename);
if (!File.Exists(_dataPath_Digits))
{
throw new FileNotFoundException(string.Format(Errors.DatasetNotFound, _dataPath_Digits));
}
}
public void SetupTrainingSpeedTests()
{
_mslrWeb10k_Validate = BaseTestClass.GetDataPath(TestDatasets.MSLRWeb.validFilename);
_mslrWeb10k_Train = BaseTestClass.GetDataPath(TestDatasets.MSLRWeb.trainFilename);
if (!File.Exists(_mslrWeb10k_Validate))
{
throw new FileNotFoundException(string.Format(Errors.DatasetNotFound, _mslrWeb10k_Validate));
}
if (!File.Exists(_mslrWeb10k_Train))
{
throw new FileNotFoundException(string.Format(Errors.DatasetNotFound, _mslrWeb10k_Train));
}
}
public void TrainWithValidationSet()
{
var mlContext = new MLContext(seed: 1);
// Get the dataset.
var data = mlContext.Data.CreateTextLoader(TestDatasets.housing.GetLoaderColumns(),
hasHeader: TestDatasets.housing.fileHasHeader, separatorChar: TestDatasets.housing.fileSeparator)
.Load(BaseTestClass.GetDataPath(TestDatasets.housing.trainFilename));
var dataSplit = mlContext.Regression.TrainTestSplit(data, testFraction: 0.2);
var trainData = dataSplit.TrainSet;
var validData = dataSplit.TestSet;
// Create a pipeline to featurize the dataset.
var pipeline = mlContext.Transforms.Concatenate("Features", new string[] {
"CrimesPerCapita", "PercentResidental", "PercentNonRetail", "CharlesRiver", "NitricOxides", "RoomsPerDwelling",
"PercentPre40s", "EmploymentDistance", "HighwayDistance", "TaxRate", "TeacherRatio"
})
.Append(mlContext.Transforms.CopyColumns("Label", "MedianHomeValue"))
.AppendCacheCheckpoint(mlContext) as IEstimator <ITransformer>;
// Preprocess the datasets.
var preprocessor = pipeline.Fit(trainData);
var preprocessedTrainData = preprocessor.Transform(trainData);
var preprocessedValidData = preprocessor.Transform(validData);
// Train the model with a validation set.
var trainedModel = mlContext.Regression.Trainers.FastTree(new Trainers.FastTree.FastTreeRegressionTrainer.Options {
NumberOfTrees = 2,
EarlyStoppingMetric = EarlyStoppingMetric.L2Norm,
EarlyStoppingRule = new GeneralityLossRule()
})
.Fit(trainData: preprocessedTrainData, validationData: preprocessedValidData);
// Combine the model.
var model = preprocessor.Append(trainedModel);
// Score the data sets.
var scoredTrainData = model.Transform(trainData);
var scoredValidData = model.Transform(validData);
var trainMetrics = mlContext.Regression.Evaluate(scoredTrainData);
var validMetrics = mlContext.Regression.Evaluate(scoredValidData);
Common.AssertMetrics(trainMetrics);
Common.AssertMetrics(validMetrics);
}
public void SetupIrisPipeline()
{
_irisExample = new IrisData()
{
SepalLength = 3.3f,
SepalWidth = 1.6f,
PetalLength = 0.2f,
PetalWidth = 5.1f,
};
string _irisDataPath = BaseTestClass.GetDataPath("iris.txt");
var env = new MLContext(seed: 1);
// Create text loader.
var options = new TextLoader.Options()
{
Columns = new[]
{
new TextLoader.Column("Label", DataKind.Single, 0),
new TextLoader.Column("SepalLength", DataKind.Single, 1),
new TextLoader.Column("SepalWidth", DataKind.Single, 2),
new TextLoader.Column("PetalLength", DataKind.Single, 3),
new TextLoader.Column("PetalWidth", DataKind.Single, 4),
},
HasHeader = true,
};
var loader = new TextLoader(env, options: options);
IDataView data = loader.Load(_irisDataPath);
var pipeline = new ColumnConcatenatingEstimator(env, "Features", new[] { "SepalLength", "SepalWidth", "PetalLength", "PetalWidth" })
.Append(env.Transforms.Conversion.MapValueToKey("Label"))
.Append(env.MulticlassClassification.Trainers.SdcaCalibrated(
new SdcaCalibratedMulticlassTrainer.Options {
NumberOfThreads = 1, ConvergenceTolerance = 1e-2f,
}));
var model = pipeline.Fit(data);
_irisModel = env.Model.CreatePredictionEngine <IrisData, IrisPrediction>(model);
}
public void SetupScoringSpeedTests()
{
_dataPath_Wiki = BaseTestClass.GetDataPath(TestDatasets.WikiDetox.trainFilename);
if (!File.Exists(_dataPath_Wiki))
{
throw new FileNotFoundException(string.Format(Errors.DatasetNotFound, _dataPath_Wiki));
}
_modelPath_Wiki = Path.Combine(Path.GetDirectoryName(typeof(MulticlassClassificationTest).Assembly.Location), @"WikiModel.zip");
string cmd = @"CV k=5 data=" + _dataPath_Wiki +
" loader=TextLoader{quote=- sparse=- col=Label:R4:0 col=rev_id:TX:1 col=comment:TX:2 col=logged_in:BL:4 col=ns:TX:5 col=sample:TX:6 col=split:TX:7 col=year:R4:3 header=+} xf=Convert{col=logged_in type=R4}" +
" xf=CategoricalTransform{col=ns}" +
" xf=TextTransform{col=FeaturesText:comment wordExtractor=NGramExtractorTransform{ngram=2}}" +
" xf=Concat{col=Features:FeaturesText,logged_in,ns}" +
" tr=OVA{p=AveragedPerceptron{iter=10}}" +
" out={" + _modelPath_Wiki + "}";
var environment = EnvironmentFactory.CreateClassificationEnvironment <TextLoader, OneHotEncodingTransformer, AveragedPerceptronTrainer, LinearBinaryModelParameters>();
cmd.ExecuteMamlCommand(environment);
}
public void SetupScoringSpeedTests()
{
_mslrWeb10k_Test = BaseTestClass.GetDataPath(TestDatasets.MSLRWeb.testFilename);
_mslrWeb10k_Validate = BaseTestClass.GetDataPath(TestDatasets.MSLRWeb.validFilename);
_mslrWeb10k_Train = BaseTestClass.GetDataPath(TestDatasets.MSLRWeb.trainFilename);
if (!File.Exists(_mslrWeb10k_Test))
{
throw new FileNotFoundException(string.Format(Errors.DatasetNotFound, _mslrWeb10k_Test));
}
if (!File.Exists(_mslrWeb10k_Validate))
{
throw new FileNotFoundException(string.Format(Errors.DatasetNotFound, _mslrWeb10k_Validate));
}
if (!File.Exists(_mslrWeb10k_Train))
{
throw new FileNotFoundException(string.Format(Errors.DatasetNotFound, _mslrWeb10k_Train));
}
_modelPath_MSLR = Path.Combine(Path.GetDirectoryName(typeof(RankingTest).Assembly.Location), "FastTreeRankingModel.zip");
string cmd = @"TrainTest test=" + _mslrWeb10k_Validate +
" eval=RankingEvaluator{t=10}" +
" data=" + _mslrWeb10k_Train +
" loader=TextLoader{col=Label:R4:0 col=GroupId:TX:1 col=Features:R4:2-138}" +
" xf=HashTransform{col=GroupId}" +
" xf=NAHandleTransform{col=Features}" +
" tr=FastTreeRanking{}" +
" out={" + _modelPath_MSLR + "}";
var environment = EnvironmentFactory.CreateRankingEnvironment <RankerEvaluator, TextLoader, HashingTransformer, FastTreeRankingTrainer, FastTreeRankingModelParameters>();
cmd.ExecuteMamlCommand(environment);
}