public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
{
string dataPath = GetDataPath("iris.txt");
string testDataPath = dataPath;
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
// Pipeline
var loader = new TextLoader(env,
new TextLoader.Arguments()
{
HasHeader = false,
Column = 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)
}
}, new MultiFileSource(dataPath));
IDataTransform trans = new ConcatTransform(env, loader, "Features",
"SepalLength", "SepalWidth", "PetalLength", "PetalWidth");
// Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");
// Train
var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments()
{
NumThreads = 1
});
// Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
var cached = new CacheDataView(env, trans, prefetch: null);
var trainRoles = new RoleMappedData(cached, 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 = Evaluate(env, testDataScorer);
CompareMatrics(metrics);
// Create prediction engine and test predictions
var model = env.CreatePredictionEngine <IrisData, IrisPrediction>(testDataScorer);
ComparePredictions(model);
// Get feature importance i.e. weight vector
var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
Assert.Equal(7.757864, Convert.ToDouble(summary[0].Value), 5);
}
}
public void TrainSaveModelAndPredict()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
// Pipeline
var loader = new TextLoader(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(dataPath));
var trans = TextTransform.Create(env, MakeSentimentTextTransformArgs(), loader);
// Train
var trainer = new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments
{
NumThreads = 1
});
var cached = new CacheDataView(env, trans, prefetch: null);
var trainRoles = new RoleMappedData(cached, label: "Label", feature: "Features");
var predictor = trainer.Train(new Runtime.TrainContext(trainRoles));
PredictionEngine <SentimentData, SentimentPrediction> model;
using (var file = env.CreateTempFile())
{
// Save model.
var scoreRoles = new RoleMappedData(trans, label: "Label", feature: "Features");
using (var ch = env.Start("saving"))
TrainUtils.SaveModel(env, ch, file, predictor, scoreRoles);
// Load model.
using (var fs = file.OpenReadStream())
model = env.CreatePredictionEngine <SentimentData, SentimentPrediction>(fs);
}
// Take a couple examples out of the test data and run predictions on top.
var testLoader = new TextLoader(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(GetDataPath(SentimentTestPath)));
var testData = testLoader.AsEnumerable <SentimentData>(env, false);
foreach (var input in testData.Take(5))
{
var prediction = model.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 Extensibility()
{
var dataPath = GetDataPath(IrisDataPath);
using (var env = new TlcEnvironment())
{
var loader = TextLoader.ReadFile(env, MakeIrisTextLoaderArgs(), 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 lambda = LambdaTransform.CreateMap(env, loader, action);
var term = TermTransform.Create(env, lambda, "Label");
var concat = new ConcatTransform(env, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth")
.Transform(term);
var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments {
MaxIterations = 100, Shuffle = true, NumThreads = 1
});
IDataView trainData = trainer.Info.WantCaching ? (IDataView) new CacheDataView(env, concat, prefetch: null) : concat;
var trainRoles = new RoleMappedData(trainData, label: "Label", feature: "Features");
// Auto-normalization.
NormalizeTransform.CreateIfNeeded(env, ref trainRoles, trainer);
var predictor = trainer.Train(new Runtime.TrainContext(trainRoles));
var scoreRoles = new RoleMappedData(concat, label: "Label", feature: "Features");
IDataScorerTransform scorer = ScoreUtils.GetScorer(predictor, scoreRoles, env, trainRoles.Schema);
var keyToValue = new KeyToValueTransform(env, "PredictedLabel").Transform(scorer);
var model = env.CreatePredictionEngine <IrisData, IrisPrediction>(keyToValue);
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 = model.Predict(input);
Assert.True(prediction.PredictedLabel == input.Label);
}
}
}
public void Evaluation()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
// Pipeline
var loader = new TextLoader(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(dataPath));
var trans = TextTransform.Create(env, MakeSentimentTextTransformArgs(), loader);
// Train
var trainer = new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments
{
NumThreads = 1
});
var cached = new CacheDataView(env, trans, prefetch: null);
var trainRoles = new RoleMappedData(cached, label: "Label", feature: "Features");
var predictor = trainer.Train(new Runtime.TrainContext(trainRoles));
var scoreRoles = new RoleMappedData(trans, label: "Label", feature: "Features");
IDataScorerTransform scorer = ScoreUtils.GetScorer(predictor, scoreRoles, env, trainRoles.Schema);
// Create prediction engine and test predictions.
var model = env.CreatePredictionEngine <SentimentData, SentimentPrediction>(scorer);
// Take a couple examples out of the test data and run predictions on top.
var testLoader = new TextLoader(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(GetDataPath(SentimentTestPath)));
var testData = testLoader.AsEnumerable <SentimentData>(env, false);
var dataEval = new RoleMappedData(scorer, label: "Label", feature: "Features", opt: true);
var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments()
{
});
var metricsDict = evaluator.Evaluate(dataEval);
var metrics = BinaryClassificationMetrics.FromMetrics(env, metricsDict["OverallMetrics"], metricsDict["ConfusionMatrix"])[0];
}
}
void MultithreadedPrediction()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
// Pipeline
var loader = new TextLoader(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(dataPath));
var trans = TextTransform.Create(env, MakeSentimentTextTransformArgs(), loader);
// Train
var trainer = new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments
{
NumThreads = 1
});
var cached = new CacheDataView(env, trans, prefetch: null);
var trainRoles = new RoleMappedData(cached, label: "Label", feature: "Features");
var predictor = trainer.Train(new Runtime.TrainContext(trainRoles));
var scoreRoles = new RoleMappedData(trans, label: "Label", feature: "Features");
IDataScorerTransform scorer = ScoreUtils.GetScorer(predictor, scoreRoles, env, trainRoles.Schema);
// Create prediction engine and test predictions.
var model = env.CreatePredictionEngine <SentimentData, SentimentPrediction>(scorer);
// Take a couple examples out of the test data and run predictions on top.
var testLoader = new TextLoader(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(GetDataPath(SentimentTestPath)));
var testData = testLoader.AsEnumerable <SentimentData>(env, false);
Parallel.ForEach(testData, (input) =>
{
lock (model)
{
var prediction = model.Predict(input);
}
});
}
}
public void SimpleTrainAndPredict()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
// Pipeline
var loader = TextLoader.ReadFile(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(dataPath));
var trans = TextTransform.Create(env, MakeSentimentTextTransformArgs(), loader);
// Train
var trainer = new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments
{
NumThreads = 1
});
var cached = new CacheDataView(env, trans, prefetch: null);
var trainRoles = new RoleMappedData(cached, label: "Label", feature: "Features");
var predictor = trainer.Train(new Runtime.TrainContext(trainRoles));
var scoreRoles = new RoleMappedData(trans, label: "Label", feature: "Features");
IDataScorerTransform scorer = ScoreUtils.GetScorer(predictor, scoreRoles, env, trainRoles.Schema);
// Create prediction engine and test predictions.
var model = env.CreatePredictionEngine <SentimentData, SentimentPrediction>(scorer);
// Take a couple examples out of the test data and run predictions on top.
var testLoader = TextLoader.ReadFile(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(GetDataPath(SentimentTestPath)));
var testData = testLoader.AsEnumerable <SentimentData>(env, false);
foreach (var input in testData.Take(5))
{
var prediction = model.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 Metacomponents()
{
var dataPath = GetDataPath(IrisDataPath);
using (var env = new TlcEnvironment())
{
var loader = new TextLoader(env, MakeIrisTextLoaderArgs(), new MultiFileSource(dataPath));
var term = new TermTransform(env, loader, "Label");
var concat = new ConcatTransform(env, term, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");
var trainer = new Ova(env, new Ova.Arguments
{
PredictorType = new SimpleComponentFactory <ITrainer <IPredictorProducing <float> > >
(
(e) => new FastTreeBinaryClassificationTrainer(e, new FastTreeBinaryClassificationTrainer.Arguments())
)
});
IDataView trainData = trainer.Info.WantCaching ? (IDataView) new CacheDataView(env, concat, prefetch: null) : concat;
var trainRoles = new RoleMappedData(trainData, label: "Label", feature: "Features");
// Auto-normalization.
NormalizeTransform.CreateIfNeeded(env, ref trainRoles, trainer);
var predictor = trainer.Train(new Runtime.TrainContext(trainRoles));
var scoreRoles = new RoleMappedData(concat, label: "Label", feature: "Features");
IDataScorerTransform scorer = ScoreUtils.GetScorer(predictor, scoreRoles, env, trainRoles.Schema);
var keyToValue = new KeyToValueTransform(env, scorer, "PredictedLabel");
var model = env.CreatePredictionEngine <IrisData, IrisPrediction>(keyToValue);
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 = model.Predict(input);
Assert.True(prediction.PredictedLabel == input.Label);
}
}
}
void DecomposableTrainAndPredict()
{
var dataPath = GetDataPath(IrisDataPath);
using (var env = new TlcEnvironment())
{
var loader = TextLoader.ReadFile(env, MakeIrisTextLoaderArgs(), new MultiFileSource(dataPath));
var term = TermTransform.Create(env, loader, "Label");
var concat = new ConcatTransform(env, "Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth").Transform(term);
var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments {
MaxIterations = 100, Shuffle = true, NumThreads = 1
});
IDataView trainData = trainer.Info.WantCaching ? (IDataView) new CacheDataView(env, concat, prefetch: null) : concat;
var trainRoles = new RoleMappedData(trainData, label: "Label", feature: "Features");
// Auto-normalization.
NormalizeTransform.CreateIfNeeded(env, ref trainRoles, trainer);
var predictor = trainer.Train(new Runtime.TrainContext(trainRoles));
var scoreRoles = new RoleMappedData(concat, label: "Label", feature: "Features");
IDataScorerTransform scorer = ScoreUtils.GetScorer(predictor, scoreRoles, env, trainRoles.Schema);
// Cut out term transform from pipeline.
var newScorer = ApplyTransformUtils.ApplyAllTransformsToData(env, scorer, loader, term);
var keyToValue = new KeyToValueTransform(env, "PredictedLabel").Transform(newScorer);
var model = env.CreatePredictionEngine <IrisDataNoLabel, IrisPrediction>(keyToValue);
var testLoader = TextLoader.ReadFile(env, MakeIrisTextLoaderArgs(), new MultiFileSource(dataPath));
var testData = testLoader.AsEnumerable <IrisDataNoLabel>(env, false);
foreach (var input in testData.Take(20))
{
var prediction = model.Predict(input);
Assert.True(prediction.PredictedLabel == "Iris-setosa");
}
}
}
public void TensorFlowTransformMNISTConvTest()
{
var model_location = "mnist_model/frozen_saved_model.pb";
using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
var dataPath = GetDataPath("Train-Tiny-28x28.txt");
var testDataPath = GetDataPath("MNIST.Test.tiny.txt");
// Pipeline
var loader = TextLoader.ReadFile(env,
new TextLoader.Arguments()
{
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 = "Placeholder",
Source = new [] { new TextLoader.Range()
{
Min = 1, Max = 784
} },
Type = DataKind.Num
}
}
}, new MultiFileSource(dataPath));
IDataView trans = TensorFlowTransform.Create(env, loader, model_location, "Softmax", "Placeholder");
trans = new ConcatTransform(env, trans, "reshape_input", "Placeholder");
trans = TensorFlowTransform.Create(env, trans, model_location, "dense/Relu", "reshape_input");
trans = new ConcatTransform(env, trans, "Features", "Softmax", "dense/Relu");
var trainer = new LightGbmMulticlassTrainer(env, new LightGbmArguments());
var cached = new CacheDataView(env, trans, prefetch: null);
var trainRoles = new RoleMappedData(cached, 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 = Evaluate(env, testDataScorer);
Assert.Equal(0.99, metrics.AccuracyMicro, 2);
Assert.Equal(0.99, metrics.AccuracyMicro, 2);
// Create prediction engine and test predictions
var model = env.CreatePredictionEngine <MNISTData, MNISTPrediction>(testDataScorer);
var sample1 = new MNISTData()
{
Placeholder = new float[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 18, 18, 18, 126, 136, 175, 26,
166, 255, 247, 127, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 30, 36, 94, 154, 170, 253, 253, 253, 253, 253,
225, 172, 253, 242, 195, 64, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 49, 238, 253, 253, 253, 253, 253, 253, 253,
253, 251, 93, 82, 82, 56, 39, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 18, 219, 253, 253, 253, 253, 253, 198,
182, 247, 241, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 80, 156, 107, 253, 253, 205, 11, 0,
43, 154, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 14, 1, 154, 253, 90, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 139, 253, 190, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 11, 190, 253, 70, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 35, 241, 225, 160, 108, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 81, 240, 253, 253, 119, 25, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 45, 186, 253, 253, 150, 27, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 16, 93, 252, 253, 187, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 249, 253, 249, 64, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 46, 130, 183, 253, 253, 207, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 39, 148, 229, 253, 253, 253, 250, 182, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 114, 221, 253, 253, 253, 253, 201, 78, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 23, 66, 213, 253, 253, 253, 253, 198, 81, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 18, 171, 219, 253, 253, 253, 253, 195, 80, 9, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 55, 172, 226, 253, 253, 253, 253, 244, 133, 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 136, 253, 253, 253, 212, 135, 132, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
};
var prediction = model.Predict(sample1);
float max = -1;
int maxIndex = -1;
for (int i = 0; i < prediction.PredictedLabels.Length; i++)
{
if (prediction.PredictedLabels[i] > max)
{
max = prediction.PredictedLabels[i];
maxIndex = i;
}
}
Assert.Equal(5, maxIndex);
}
}
