public void New_SimpleTrainAndPredict()
{
using (var env = new LocalEnvironment(seed: 1, conc: 1))
{
var reader = new TextLoader(env, MakeSentimentTextLoaderArgs());
var data = reader.Read(new MultiFileSource(GetDataPath(TestDatasets.Sentiment.trainFilename)));
// Pipeline.
var pipeline = new TextTransform(env, "SentimentText", "Features")
.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 = model.MakePredictionFunction <SentimentData, SentimentPrediction>(env);
// Take a couple examples out of the test data and run predictions on top.
var testData = reader.Read(new MultiFileSource(GetDataPath(TestDatasets.Sentiment.testFilename)))
.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()
{
using (var env = new LocalEnvironment(seed: 1, conc: 1))
{
var reader = new TextLoader(env, MakeSentimentTextLoaderArgs());
var data = reader.Read(new MultiFileSource(GetDataPath(TestDatasets.Sentiment.trainFilename)));
// Pipeline.
var pipeline = new TextTransform(env, "SentimentText", "Features")
.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 = model.MakePredictionFunction <SentimentData, SentimentPrediction>(env);
// Take a couple examples out of the test data and run predictions on top.
var testData = reader.Read(new MultiFileSource(GetDataPath(TestDatasets.Sentiment.testFilename)))
.AsEnumerable <SentimentData>(env, false);
Parallel.ForEach(testData, (input) =>
{
lock (engine)
{
var prediction = engine.Predict(input);
}
});
}
}
public void SetupSentimentPipeline()
{
_sentimentExample = new SentimentData()
{
SentimentText = "Not a big fan of this."
};
string _sentimentDataPath = Program.GetInvariantCultureDataPath("wikipedia-detox-250-line-data.tsv");
using (var env = new ConsoleEnvironment(seed: 1, conc: 1, verbose: false, sensitivity: MessageSensitivity.None, outWriter: EmptyWriter.Instance))
{
var reader = new TextLoader(env,
new TextLoader.Arguments()
{
Separator = "\t",
HasHeader = true,
Column = new[]
{
new TextLoader.Column("Label", DataKind.BL, 0),
new TextLoader.Column("SentimentText", DataKind.Text, 1)
}
});
IDataView data = reader.Read(_sentimentDataPath);
var pipeline = new TextTransform(env, "SentimentText", "Features")
.Append(new LinearClassificationTrainer(env, "Features", "Label", advancedSettings: (s) => { s.NumThreads = 1; s.ConvergenceTolerance = 1e-2f; }));
var model = pipeline.Fit(data);
_sentimentModel = model.MakePredictionFunction <SentimentData, SentimentPrediction>(env);
}
}
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 TextTransform(env, "SentimentText", "Features")
.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 = loadedModel.MakePredictionFunction <SentimentData, SentimentPrediction>(env);
// 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);
}
}
}
public void New_IntrospectiveTraining()
{
using (var env = new LocalEnvironment(seed: 1, conc: 1))
{
var data = new TextLoader(env, MakeSentimentTextLoaderArgs())
.Read(new MultiFileSource(GetDataPath(TestDatasets.Sentiment.trainFilename)));
var pipeline = new TextTransform(env, "SentimentText", "Features")
.Append(new LinearClassificationTrainer(env, "Features", "Label", advancedSettings: (s) => s.NumThreads = 1));
// Train.
var model = pipeline.Fit(data);
// Get feature weights.
VBuffer <float> weights = default;
model.LastTransformer.Model.GetFeatureWeights(ref weights);
}
}
public void New_TrainWithValidationSet()
{
using (var env = new LocalEnvironment(seed: 1, conc: 1))
{
// Pipeline.
var reader = new TextLoader(env, MakeSentimentTextLoaderArgs());
var pipeline = new TextTransform(env, "SentimentText", "Features");
// Train the pipeline, prepare train and validation set.
var data = reader.Read(new MultiFileSource(GetDataPath(TestDatasets.Sentiment.trainFilename)));
var preprocess = pipeline.Fit(data);
var trainData = preprocess.Transform(data);
var validData = preprocess.Transform(reader.Read(new MultiFileSource(GetDataPath(TestDatasets.Sentiment.testFilename))));
// 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 TextLoader(env, MakeSentimentTextLoaderArgs())
.Read(new MultiFileSource(dataPath));
var pipeline = new TextTransform(env, "SentimentText", "Features")
.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);
}
}
public void TextFeaturizerWorkout()
{
string sentimentDataPath = GetDataPath("wikipedia-detox-250-line-data.tsv");
var data = TextLoader.CreateReader(Env, ctx => (
label: ctx.LoadBool(0),
text: ctx.LoadText(1)), hasHeader: true)
.Read(new MultiFileSource(sentimentDataPath));
var invalidData = TextLoader.CreateReader(Env, ctx => (
label: ctx.LoadBool(0),
text: ctx.LoadFloat(1)), hasHeader: true)
.Read(new MultiFileSource(sentimentDataPath))
.AsDynamic;
//var feat = Estimator.MakeNew(data)
// .Append(row => row.text.FeaturizeText(advancedSettings: s => { s.OutputTokens = true; }));
var feat = new TextTransform(Env, "text", "Data", advancedSettings: s => { s.OutputTokens = true; });
TestEstimatorCore(feat, data.AsDynamic, invalidInput: invalidData);
var outputPath = GetOutputPath("Text", "featurized.tsv");
using (var ch = Env.Start("save"))
{
var saver = new TextSaver(Env, new TextSaver.Arguments {
Silent = true
});
IDataView savedData = TakeFilter.Create(Env, feat.Fit(data.AsDynamic).Transform(data.AsDynamic), 4);
savedData = new ChooseColumnsTransform(Env, savedData, "Data", "Data_TransformedText");
using (var fs = File.Create(outputPath))
DataSaverUtils.SaveDataView(ch, saver, savedData, fs, keepHidden: true);
}
CheckEquality("Text", "featurized.tsv");
Done();
}
static void Main(string[] args)
{
//1. Create ML.NET context/environment
using (var env = new LocalEnvironment())
{
//2. Create DataReader with data schema mapped to file's columns
var reader = new TextLoader(env,
new TextLoader.Arguments()
{
Separator = "tab",
HasHeader = true,
Column = new[]
{
new TextLoader.Column("Label", DataKind.Bool, 0),
new TextLoader.Column("Text", DataKind.Text, 1)
}
});
//Load training data
IDataView trainingDataView = reader.Read(new MultiFileSource(TrainDataPath));
//3.Create a flexible pipeline (composed by a chain of estimators) for creating/traing the model.
var pipeline = new TextTransform(env, "Text", "Features") //Convert the text column to numeric vectors (Features column)
.Append(new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments(),
"Features",
"Label"));
//.Append(new LinearClassificationTrainer(env, "Features", "Label")); //(Simpler in ML.NET v0.7)
//4. Create and train the model
Console.WriteLine("=============== Create and Train the Model ===============");
var model = pipeline.Fit(trainingDataView);
Console.WriteLine("=============== End of training ===============");
Console.WriteLine();
//5. Evaluate the model and show accuracy stats
//Load evaluation/test data
IDataView testDataView = reader.Read(new MultiFileSource(TestDataPath));
Console.WriteLine("=============== Evaluating Model's accuracy with Test data===============");
var predictions = model.Transform(testDataView);
var binClassificationCtx = new BinaryClassificationContext(env);
var metrics = binClassificationCtx.Evaluate(predictions, "Label");
Console.WriteLine();
Console.WriteLine("Model quality metrics evaluation");
Console.WriteLine("------------------------------------------");
Console.WriteLine($"Accuracy: {metrics.Accuracy:P2}");
Console.WriteLine($"Auc: {metrics.Auc:P2}");
Console.WriteLine($"F1Score: {metrics.F1Score:P2}");
Console.WriteLine("=============== End of Model's evaluation ===============");
Console.WriteLine();
//6. Test Sentiment Prediction with one sample text
var predictionFunct = model.MakePredictionFunction <SentimentIssue, SentimentPrediction>(env);
SentimentIssue sampleStatement = new SentimentIssue
{
Text = "This is a very rude movie"
};
var resultprediction = predictionFunct.Predict(sampleStatement);
Console.WriteLine();
Console.WriteLine("=============== Test of model with a sample ===============");
Console.WriteLine($"Text: {sampleStatement.Text} | Prediction: {(Convert.ToBoolean(resultprediction.Prediction) ? "Toxic" : "Nice")} sentiment | Probability: {resultprediction.Probability} ");
// Save model to .ZIP file
SaveModelAsFile(env, model);
// Predict again but now testing the model loading from the .ZIP file
PredictWithModelLoadedFromFile(sampleStatement);
Console.WriteLine("=============== End of process, hit any key to finish ===============");
Console.ReadKey();
}
}