void New_MultithreadedPrediction()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
var reader = new TextLoader(env, MakeSentimentTextLoaderArgs());
var data = reader.Read(new MultiFileSource(dataPath));
// Pipeline.
var pipeline = new MyTextTransform(env, MakeSentimentTextTransformArgs())
.Append(new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments {
NumThreads = 1
}, "Features", "Label"));
// Train.
var model = pipeline.Fit(data);
// Create prediction engine and test predictions.
var engine = new MyPredictionEngine <SentimentData, SentimentPrediction>(env, model);
// Take a couple examples out of the test data and run predictions on top.
var testData = reader.Read(new MultiFileSource(GetDataPath(SentimentTestPath)))
.AsEnumerable <SentimentData>(env, false);
Parallel.ForEach(testData, (input) =>
{
lock (engine)
{
var prediction = engine.Predict(input);
}
});
}
}
public void New_ReconfigurablePrediction()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
var dataReader = new MyTextLoader(env, MakeSentimentTextLoaderArgs())
.Fit(new MultiFileSource(dataPath));
var data = dataReader.Read(new MultiFileSource(dataPath));
var testData = dataReader.Read(new MultiFileSource(testDataPath));
// Pipeline.
var pipeline = new MyTextTransform(env, MakeSentimentTextTransformArgs())
.Fit(data);
var trainer = new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments {
NumThreads = 1
}, "Features", "Label");
var trainData = pipeline.Transform(data);
var model = trainer.Fit(trainData);
var scoredTest = model.Transform(pipeline.Transform(testData));
var metrics = new MyBinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments()).Evaluate(scoredTest, "Label", "Probability");
var newModel = new BinaryPredictionTransformer <IPredictorProducing <float> >(env, model.Model, trainData.Schema, model.FeatureColumn, threshold: 0.01f, thresholdColumn: DefaultColumnNames.Probability);
var newScoredTest = newModel.Transform(pipeline.Transform(testData));
var newMetrics = new MyBinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments {
Threshold = 0.01f, UseRawScoreThreshold = false
}).Evaluate(newScoredTest, "Label", "Probability");
}
}
public void New_SimpleTrainAndPredict()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
var reader = new TextLoader(env, MakeSentimentTextLoaderArgs());
var data = reader.Read(new MultiFileSource(dataPath));
// Pipeline.
var pipeline = new MyTextTransform(env, MakeSentimentTextTransformArgs())
.Append(new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments {
NumThreads = 1
}, "Features", "Label"));
// Train.
var model = pipeline.Fit(data);
// Create prediction engine and test predictions.
var engine = new MyPredictionEngine <SentimentData, SentimentPrediction>(env, model);
// Take a couple examples out of the test data and run predictions on top.
var testData = 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);
}
}
}
void New_CrossValidation()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
var data = new MyTextLoader(env, MakeSentimentTextLoaderArgs())
.FitAndRead(new MultiFileSource(dataPath));
// Pipeline.
var pipeline = new MyTextTransform(env, MakeSentimentTextTransformArgs())
.Append(new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments
{
NumThreads = 1,
ConvergenceTolerance = 1f
}, "Features", "Label"));
var cv = new MyCrossValidation.BinaryCrossValidator(env)
{
NumFolds = 2
};
var cvResult = cv.CrossValidate(data, pipeline);
}
}
public void New_TrainWithInitialPredictor()
{
var dataPath = GetDataPath(SentimentDataPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
var data = new TextLoader(env, MakeSentimentTextLoaderArgs()).Read(new MultiFileSource(dataPath));
// Pipeline.
var pipeline = new MyTextTransform(env, MakeSentimentTextTransformArgs());
// Train the pipeline, prepare train set.
var trainData = pipeline.FitAndTransform(data);
// 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);
}
}
public void New_TrainWithValidationSet()
{
var dataPath = GetDataPath(SentimentDataPath);
var validationDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
// Pipeline.
var reader = new TextLoader(env, MakeSentimentTextLoaderArgs());
var pipeline = new MyTextTransform(env, MakeSentimentTextTransformArgs());
// Train the pipeline, prepare train and validation set.
var data = reader.Read(new MultiFileSource(dataPath));
var preprocess = pipeline.Fit(data);
var trainData = preprocess.Transform(data);
var validData = preprocess.Transform(reader.Read(new MultiFileSource(validationDataPath)));
// Train model with validation set.
var trainer = new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments(), "Features", "Label");
var model = trainer.Train(trainData, validData);
}
}
public void New_IntrospectiveTraining()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
var data = new MyTextLoader(env, MakeSentimentTextLoaderArgs())
.FitAndRead(new MultiFileSource(dataPath));
var pipeline = new MyTextTransform(env, MakeSentimentTextTransformArgs())
.Append(new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments {
NumThreads = 1
}, "Features", "Label"));
// Train.
var model = pipeline.Fit(data);
// Get feature weights.
VBuffer <float> weights = default;
model.LastTransformer.Model.GetFeatureWeights(ref weights);
}
}
