public void TrainSentiment() { var env = new MLContext(seed: 1); // Pipeline var arguments = new TextLoader.Arguments() { Column = new TextLoader.Column[] { new TextLoader.Column() { Name = "Label", Source = new[] { new TextLoader.Range() { Min = 0, Max = 0 } }, Type = DataKind.Num }, new TextLoader.Column() { Name = "SentimentText", Source = new[] { new TextLoader.Range() { Min = 1, Max = 1 } }, Type = DataKind.Text } }, HasHeader = true, AllowQuoting = false, AllowSparse = false }; var loader = env.Data.ReadFromTextFile(_sentimentDataPath, arguments); var text = TextFeaturizingEstimator.Create(env, new TextFeaturizingEstimator.Arguments() { Column = new TextFeaturizingEstimator.Column { Name = "WordEmbeddings", Source = new[] { "SentimentText" } }, OutputTokens = true, KeepPunctuations = false, UsePredefinedStopWordRemover = true, VectorNormalizer = TextFeaturizingEstimator.TextNormKind.None, CharFeatureExtractor = null, WordFeatureExtractor = null, }, loader); var trans = WordEmbeddingsExtractingTransformer.Create(env, new WordEmbeddingsExtractingTransformer.Arguments() { Column = new WordEmbeddingsExtractingTransformer.Column[1] { new WordEmbeddingsExtractingTransformer.Column { Name = "Features", Source = "WordEmbeddings_TransformedText" } }, ModelKind = WordEmbeddingsExtractingTransformer.PretrainedModelKind.Sswe, }, text); // Train var trainer = new SdcaMultiClassTrainer(env, "Label", "Features", maxIterations: 20); var predicted = trainer.Fit(trans); _consumer.Consume(predicted); }
public void TrainAndPredictSentimentModelWithDirectionInstantiationTestWithWordEmbedding() { var dataPath = GetDataPath(SentimentDataPath); var testDataPath = GetDataPath(SentimentTestPath); using (var env = new ConsoleEnvironment(seed: 1, conc: 1)) { // Pipeline var loader = TextLoader.ReadFile(env, new TextLoader.Arguments() { Separator = "tab", HasHeader = true, Column = new[] { new TextLoader.Column("Label", DataKind.Num, 0), new TextLoader.Column("SentimentText", DataKind.Text, 1) } }, new MultiFileSource(dataPath)); var text = TextFeaturizingEstimator.Create(env, new TextFeaturizingEstimator.Arguments() { Column = new TextFeaturizingEstimator.Column { Name = "WordEmbeddings", Source = new[] { "SentimentText" } }, OutputTokens = true, KeepPunctuations = false, StopWordsRemover = new PredefinedStopWordsRemoverFactory(), VectorNormalizer = TextFeaturizingEstimator.TextNormKind.None, CharFeatureExtractor = null, WordFeatureExtractor = null, }, loader); var trans = WordEmbeddingsExtractingTransformer.Create(env, new WordEmbeddingsExtractingTransformer.Arguments() { Column = new WordEmbeddingsExtractingTransformer.Column[1] { new WordEmbeddingsExtractingTransformer.Column { Name = "Features", Source = "WordEmbeddings_TransformedText" } }, ModelKind = WordEmbeddingsExtractingTransformer.PretrainedModelKind.Sswe, }, text); // Train var trainer = new FastTreeBinaryClassificationTrainer(env, DefaultColumnNames.Label, DefaultColumnNames.Features, numLeaves: 5, numTrees: 5, minDatapointsInLeaves: 2); var trainRoles = new RoleMappedData(trans, label: "Label", feature: "Features"); var pred = trainer.Train(trainRoles); // Get scorer and evaluate the predictions from test data IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath); var metrics = EvaluateBinary(env, testDataScorer); // SSWE is a simple word embedding model + we train on a really small dataset, so metrics are not great. Assert.Equal(.6667, metrics.Accuracy, 4); Assert.Equal(.71, metrics.Auc, 1); Assert.Equal(.58, metrics.Auprc, 2); // Create prediction engine and test predictions var model = env.CreateBatchPredictionEngine <SentimentData, SentimentPrediction>(testDataScorer); var sentiments = GetTestData(); var predictions = model.Predict(sentiments, false); Assert.Equal(2, predictions.Count()); Assert.True(predictions.ElementAt(0).Sentiment); Assert.True(predictions.ElementAt(1).Sentiment); // Get feature importance based on feature gain during training var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema); Assert.Equal(1.0, (double)summary[0].Value, 1); } }
public void TrainSentiment() { using (var env = new ConsoleEnvironment(seed: 1)) { // Pipeline var loader = TextLoader.ReadFile(env, new TextLoader.Arguments() { AllowQuoting = false, AllowSparse = false, Separator = "tab", HasHeader = true, Column = new[] { new TextLoader.Column() { Name = "Label", Source = new [] { new TextLoader.Range() { Min = 0, Max = 0 } }, Type = DataKind.Num }, new TextLoader.Column() { Name = "SentimentText", Source = new [] { new TextLoader.Range() { Min = 1, Max = 1 } }, Type = DataKind.Text } } }, new MultiFileSource(_sentimentDataPath)); var text = TextFeaturizingEstimator.Create(env, new TextFeaturizingEstimator.Arguments() { Column = new TextFeaturizingEstimator.Column { Name = "WordEmbeddings", Source = new[] { "SentimentText" } }, OutputTokens = true, KeepPunctuations = false, StopWordsRemover = new PredefinedStopWordsRemoverFactory(), VectorNormalizer = TextFeaturizingEstimator.TextNormKind.None, CharFeatureExtractor = null, WordFeatureExtractor = null, }, loader); var trans = WordEmbeddingsExtractingTransformer.Create(env, new WordEmbeddingsExtractingTransformer.Arguments() { Column = new WordEmbeddingsExtractingTransformer.Column[1] { new WordEmbeddingsExtractingTransformer.Column { Name = "Features", Source = "WordEmbeddings_TransformedText" } }, ModelKind = WordEmbeddingsExtractingTransformer.PretrainedModelKind.Sswe, }, text); // Train var trainer = new SdcaMultiClassTrainer(env, "Label", "Features", maxIterations: 20); var trainRoles = new RoleMappedData(trans, label: "Label", feature: "Features"); var predicted = trainer.Train(trainRoles); _consumer.Consume(predicted); } }