void New_DecomposableTrainAndPredict()
{
var dataPath = GetDataPath(IrisDataPath);
using (var env = new TlcEnvironment())
{
var data = new MyTextLoader(env, MakeIrisTextLoaderArgs())
.FitAndRead(new MultiFileSource(dataPath));
var pipeline = new MyConcatTransform(env, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth")
.Append(new MyTermTransform(env, "Label"), TransformerScope.TrainTest)
.Append(new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments {
MaxIterations = 100, Shuffle = true, NumThreads = 1
}, "Features", "Label"))
.Append(new MyKeyToValueTransform(env, "PredictedLabel"));
var model = pipeline.Fit(data).GetModelFor(TransformerScope.Scoring);
var engine = new MyPredictionEngine <IrisDataNoLabel, IrisPrediction>(env, model);
var testLoader = new TextLoader(env, MakeIrisTextLoaderArgs(), new MultiFileSource(dataPath));
var testData = testLoader.AsEnumerable <IrisData>(env, false);
foreach (var input in testData.Take(20))
{
var prediction = engine.Predict(input);
Assert.True(prediction.PredictedLabel == input.Label);
}
}
}
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);
}
}
}
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_TrainSaveModelAndPredict()
{
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);
ITransformer loadedModel;
using (var file = env.CreateTempFile())
{
// Save model.
using (var fs = file.CreateWriteStream())
model.SaveTo(env, fs);
// Load model.
loadedModel = TransformerChain.LoadFrom(env, file.OpenReadStream());
}
// Create prediction engine and test predictions.
var engine = new MyPredictionEngine <SentimentData, SentimentPrediction>(env, loadedModel);
// 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_Extensibility()
{
var dataPath = GetDataPath(IrisDataPath);
using (var env = new TlcEnvironment())
{
var data = new TextLoader(env, MakeIrisTextLoaderArgs())
.Read(new MultiFileSource(dataPath));
Action <IrisData, IrisData> action = (i, j) =>
{
j.Label = i.Label;
j.PetalLength = i.SepalLength > 3 ? i.PetalLength : i.SepalLength;
j.PetalWidth = i.PetalWidth;
j.SepalLength = i.SepalLength;
j.SepalWidth = i.SepalWidth;
};
var pipeline = new MyConcatTransform(env, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth")
.Append(new MyLambdaTransform <IrisData, IrisData>(env, action))
.Append(new TermEstimator(env, "Label"), TransformerScope.TrainTest)
.Append(new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments {
MaxIterations = 100, Shuffle = true, NumThreads = 1
}, "Features", "Label"))
.Append(new MyKeyToValueTransform(env, "PredictedLabel"));
var model = pipeline.Fit(data).GetModelFor(TransformerScope.Scoring);
var engine = new MyPredictionEngine <IrisData, IrisPrediction>(env, model);
var testLoader = TextLoader.ReadFile(env, MakeIrisTextLoaderArgs(), new MultiFileSource(dataPath));
var testData = testLoader.AsEnumerable <IrisData>(env, false);
foreach (var input in testData.Take(20))
{
var prediction = engine.Predict(input);
Assert.True(prediction.PredictedLabel == input.Label);
}
}
}
