public void New_SimpleTrainAndPredict() { var dataPath = GetDataPath(SentimentDataPath); var testDataPath = GetDataPath(SentimentTestPath); using (var env = new TlcEnvironment(seed: 1, conc: 1)) { // Pipeline. var pipeline = new MyTextLoader(env, MakeSentimentTextLoaderArgs()) .Append(new MyTextTransform(env, MakeSentimentTextTransformArgs())) .Append(new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments { NumThreads = 1 }, "Features", "Label")); // Train. var model = pipeline.Fit(new MultiFileSource(dataPath)); // Create prediction engine and test predictions. var engine = new MyPredictionEngine <SentimentData, SentimentPrediction>(env, model.Transformer); // Take a couple examples out of the test data and run predictions on top. var testData = model.Reader.Read(new MultiFileSource(GetDataPath(SentimentTestPath))) .AsEnumerable <SentimentData>(env, false); foreach (var input in testData.Take(5)) { var prediction = engine.Predict(input); // Verify that predictions match and scores are separated from zero. Assert.Equal(input.Sentiment, prediction.Sentiment); Assert.True(input.Sentiment && prediction.Score > 1 || !input.Sentiment && prediction.Score < -1); } } }
public void New_TrainWithInitialPredictor() { var dataPath = GetDataPath(SentimentDataPath); using (var env = new TlcEnvironment(seed: 1, conc: 1)) { // Pipeline. var pipeline = new MyTextLoader(env, MakeSentimentTextLoaderArgs()) .Append(new MyTextTransform(env, MakeSentimentTextTransformArgs())); // Train the pipeline, prepare train set. var reader = pipeline.Fit(new MultiFileSource(dataPath)); var trainData = reader.Read(new MultiFileSource(dataPath)); // Train the first predictor. var trainer = new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments { NumThreads = 1 }, "Features", "Label"); var firstModel = trainer.Fit(trainData); // Train the second predictor on the same data. var secondTrainer = new MyAveragedPerceptron(env, new AveragedPerceptronTrainer.Arguments(), "Features", "Label"); var finalModel = secondTrainer.Train(trainData, firstModel.Model); } }
void New_FileBasedSavingOfData() { var dataPath = GetDataPath(SentimentDataPath); var testDataPath = GetDataPath(SentimentTestPath); using (var env = new TlcEnvironment(seed: 1, conc: 1)) { // Pipeline. var pipeline = new MyTextLoader(env, MakeSentimentTextLoaderArgs()) .Append(new MyTextTransform(env, MakeSentimentTextTransformArgs())); var trainData = pipeline.Fit(new MultiFileSource(dataPath)).Read(new MultiFileSource(dataPath)); using (var file = env.CreateOutputFile("i.idv")) trainData.SaveAsBinary(env, file.CreateWriteStream()); var trainer = new MySdca(env, new LinearClassificationTrainer.Arguments { NumThreads = 1 }, "Features", "Label"); var loadedTrainData = new BinaryLoader(env, new BinaryLoader.Arguments(), new MultiFileSource("i.idv")); // Train. var model = trainer.Train(loadedTrainData); DeleteOutputPath("i.idv"); } }
public void New_Evaluation() { var dataPath = GetDataPath(SentimentDataPath); var testDataPath = GetDataPath(SentimentTestPath); using (var env = new TlcEnvironment(seed: 1, conc: 1)) { // Pipeline. var pipeline = new MyTextLoader(env, MakeSentimentTextLoaderArgs()) .Append(new MyTextTransform(env, MakeSentimentTextTransformArgs())) .Append(new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments { NumThreads = 1 }, "Features", "Label")); // Train. var model = pipeline.Fit(new MultiFileSource(dataPath)); // Evaluate on the test set. var dataEval = model.Read(new MultiFileSource(testDataPath)); var evaluator = new MyBinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments() { }); var metrics = evaluator.Evaluate(dataEval); } }
void New_MultithreadedPrediction() { var dataPath = GetDataPath(SentimentDataPath); var testDataPath = GetDataPath(SentimentTestPath); using (var env = new TlcEnvironment(seed: 1, conc: 1)) { // Pipeline. var pipeline = new MyTextLoader(env, MakeSentimentTextLoaderArgs()) .Append(new MyTextTransform(env, MakeSentimentTextTransformArgs())) .Append(new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments { NumThreads = 1 }, "Features", "Label")); // Train. var model = pipeline.Fit(new MultiFileSource(dataPath)); // Create prediction engine and test predictions. var engine = new MyPredictionEngine <SentimentData, SentimentPrediction>(env, model.Transformer); // Take a couple examples out of the test data and run predictions on top. var testData = model.Reader.Read(new MultiFileSource(GetDataPath(SentimentTestPath))) .AsEnumerable <SentimentData>(env, false); Parallel.ForEach(testData, (input) => { lock (engine) { var prediction = engine.Predict(input); } }); } }
public void New_TrainWithValidationSet() { var dataPath = GetDataPath(SentimentDataPath); var validationDataPath = GetDataPath(SentimentTestPath); using (var env = new TlcEnvironment(seed: 1, conc: 1)) { // Pipeline. var pipeline = new MyTextLoader(env, MakeSentimentTextLoaderArgs()) .Append(new MyTextTransform(env, MakeSentimentTextTransformArgs())); // Train the pipeline, prepare train and validation set. var reader = pipeline.Fit(new MultiFileSource(dataPath)); var trainData = reader.Read(new MultiFileSource(dataPath)); var validData = reader.Read(new MultiFileSource(validationDataPath)); // Train model with validation set. var trainer = new MySdca(env, new Runtime.Learners.LinearClassificationTrainer.Arguments(), "Features", "Label"); var model = trainer.Train(trainData, validData); } }