private ITransformer BuildAndTrainUsingParams(ColumnEnum column)
{
List <string> features = new List <string>();
TextFeaturizingEstimator textTransformer = null;
EstimatorChain <ColumnConcatenatingTransformer> estimatorColumn = null;
EstimatorChain <ITransformer> estimatorTransformer = null;
if (_includeDay)
{
textTransformer = _mlContext.Transforms.Text.FeaturizeText("DayString", "Day");
features.Add("DayString");
}
if (_includeMonth)
{
if (textTransformer != null)
{
estimatorTransformer = textTransformer.Append(_mlContext.Transforms.Text.FeaturizeText("MonthString", "Month"));
}
else
{
textTransformer = _mlContext.Transforms.Text.FeaturizeText("MonthString", "Month");
}
features.Add("MonthString");
}
if (_includeWeek)
{
features.Add("Week");
}
if (textTransformer == null)
{
var res = _mlContext.Transforms.Concatenate("Features", features.ToArray())
.Append(_mlContext.Transforms.CopyColumns("Label", System.Enum.GetName(typeof(ColumnEnum), column)))
.Append(_mlContext.Regression.Trainers.FastTreeTweedie());
return(res.Fit(_trainData));
}
if (estimatorTransformer != null)
{
var res2 = estimatorTransformer.Append(_mlContext.Transforms.Concatenate("Features", features.ToArray()))
.Append(_mlContext.Transforms.CopyColumns("Label", System.Enum.GetName(typeof(ColumnEnum), column)))
.Append(_mlContext.Regression.Trainers.FastTreeTweedie());
return(res2.Fit(_trainData));
}
var res3 = textTransformer.Append(_mlContext.Transforms.Concatenate("Features", features.ToArray()))
.Append(_mlContext.Transforms.CopyColumns("Label", System.Enum.GetName(typeof(ColumnEnum), column)))
.Append(_mlContext.Regression.Trainers.FastTreeTweedie());
return(res3.Fit(_trainData));
}
public ML <T, T2> Run()
{
IDataView trainingDataView = mlContext.Data.LoadFromEnumerable(this.data);
DataOperationsCatalog.TrainTestData dataSplit = mlContext.Data
.TrainTestSplit(trainingDataView, testFraction: 0.2);
switch (this.type)
{
case MLType.TextFeaturizingEstimator:
{
TextFeaturizingEstimator dataProcessPipeline = mlContext.Transforms.Text
.FeaturizeText(outputColumnName: "Features", inputColumnName: this.inputName);
SdcaLogisticRegressionBinaryTrainer sdcaRegressionTrainer = mlContext.BinaryClassification.Trainers
.SdcaLogisticRegression(labelColumnName: this.labelName, featureColumnName: "Features");
EstimatorChain <BinaryPredictionTransformer <CalibratedModelParametersBase <LinearBinaryModelParameters, PlattCalibrator> > > trainingPipeline = dataProcessPipeline.Append(sdcaRegressionTrainer);
trainedModel = trainingPipeline.Fit(dataSplit.TrainSet);
mlContext.Model.Save(trainedModel, dataSplit.TrainSet.Schema, this.modelName);
IDataView testSetTransform = trainedModel.Transform(dataSplit.TestSet);
this.modelMetrics = mlContext.BinaryClassification
.Evaluate(data: testSetTransform,
labelColumnName: this.labelName,
scoreColumnName: this.scoreName);
break;
}
case MLType.LightGbm:
{
var fields = this.thisType
.GetType()
.GetProperties(BindingFlags.Public | BindingFlags.Instance)
.Select(p => p.Name);
//mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel")
var featurePipeline = this.isFeaturesIncluded
? null
: mlContext.Transforms.Concatenate("Features", fields.ToArray());
var trainer = mlContext.Regression.Trainers
.LightGbm(new LightGbmRegressionTrainer.Options()
{
NumberOfIterations = 100,
LearningRate = 0.3227682f,
NumberOfLeaves = 55,
MinimumExampleCountPerLeaf = 10,
UseCategoricalSplit = false,
HandleMissingValue = true,
UseZeroAsMissingValue = false,
MinimumExampleCountPerGroup = 50,
MaximumCategoricalSplitPointCount = 32,
CategoricalSmoothing = 20,
L2CategoricalRegularization = 5,
Booster = new GradientBooster.Options()
{
L2Regularization = 0, L1Regularization = 0.5
},
LabelColumnName = this.labelName,
FeatureColumnName = "Features"
});
var pipeline2 = featurePipeline == null ? null : featurePipeline.Append(trainer);
if (pipeline2 == null)
{
trainedModel = trainer.Fit(dataSplit.TrainSet);
mlContext.Model.Save(trainedModel, dataSplit.TrainSet.Schema, this.modelName);
IDataView testSetTransform = trainedModel.Transform(dataSplit.TestSet);
var crossValidationResults = mlContext.Regression
.CrossValidate(trainingDataView, trainer, numberOfFolds: 5, labelColumnName: this.labelName);
}
else
{
trainedModel = pipeline2.Fit(dataSplit.TrainSet);
mlContext.Model.Save(trainedModel, dataSplit.TrainSet.Schema, this.modelName);
IDataView testSetTransform = trainedModel.Transform(dataSplit.TestSet);
var crossValidationResults = mlContext.Regression
.CrossValidate(trainingDataView,
pipeline2,
numberOfFolds: 5,
labelColumnName: this.labelName);
}
//this.modelMetrics = mlContext.Regression
//.Evaluate(data: testSetTransform,
// labelColumnName: this.labelName,
// scoreColumnName: this.scoreName);
break;
}
}
//var msg = $"Area Under Curve: {modelMetrics.AreaUnderRocCurve:P2}{Environment.NewLine}" +
// $"Area Under Precision Recall Curve: {modelMetrics.AreaUnderPrecisionRecallCurve:P2}" +
// $"{Environment.NewLine}" +
// $"Accuracy: {modelMetrics.Accuracy:P2}{Environment.NewLine}" +
// $"F1Score: {modelMetrics.F1Score:P2}{Environment.NewLine}" +
// $"Positive Recall: {modelMetrics.PositiveRecall:#.##}{Environment.NewLine}" +
// $"Negative Recall: {modelMetrics.NegativeRecall:#.##}{Environment.NewLine}";
this.isTaught = true;
return(this);
}
private static ITransformer BuildTrainEvaluateAndSaveModel(MLContext mlContext)
{
// STEP 1: Common data loading configuration
IDataView dataView = mlContext.Data.LoadFromTextFile <SentimentIssue>(DataPath, hasHeader: true);
DataOperationsCatalog.TrainTestData trainTestSplit =
mlContext.Data.TrainTestSplit(dataView, testFraction: 0.2);
IDataView trainingData = trainTestSplit.TrainSet;
IDataView testData = trainTestSplit.TestSet;
// STEP 2: Common data process configuration with pipeline data transformations
TextFeaturizingEstimator dataProcessPipeline = mlContext.Transforms.Text.FeaturizeText(outputColumnName: "Features",
inputColumnName: nameof(SentimentIssue.Text));
// (OPTIONAL) Peek data (such as 2 records) in training DataView after applying the ProcessPipeline's transformations into "Features"
ConsoleHelper.PeekDataViewInConsole(mlContext, dataView, dataProcessPipeline, 2);
//Peak the transformed features column
//ConsoleHelper.PeekVectorColumnDataInConsole(mlContext, "Features", dataView, dataProcessPipeline, 1);
// STEP 3: Set the training algorithm, then create and config the modelBuilder
SdcaLogisticRegressionBinaryTrainer trainer =
mlContext.BinaryClassification.Trainers.SdcaLogisticRegression(labelColumnName: "Label",
featureColumnName: "Features");
EstimatorChain <BinaryPredictionTransformer <CalibratedModelParametersBase <LinearBinaryModelParameters, PlattCalibrator> > > trainingPipeline = dataProcessPipeline.Append(trainer);
//Measure training time
Stopwatch watch = Stopwatch.StartNew();
// STEP 4: Train the model fitting to the DataSet
Console.WriteLine("=============== Training the model ===============");
ITransformer trainedModel = trainingPipeline.Fit(trainingData);
//Stop measuring time
watch.Stop();
long elapsedMs = watch.ElapsedMilliseconds;
Console.WriteLine($"***** Training time: {elapsedMs / 1000} seconds *****");
// STEP 5: Evaluate the model and show accuracy stats
Console.WriteLine("===== Evaluating Model's accuracy with Test data =====");
IDataView predictions = trainedModel.Transform(testData);
CalibratedBinaryClassificationMetrics metrics = mlContext.BinaryClassification.Evaluate(data: predictions, labelColumnName: "Label",
scoreColumnName: "Score");
ConsoleHelper.PrintBinaryClassificationMetrics(trainer.ToString(), metrics);
// STEP 6: Save/persist the trained model to a .ZIP file
mlContext.Model.Save(trainedModel, trainingData.Schema, ModelPath);
Console.WriteLine("The model is saved to {0}", ModelPath);
return(trainedModel);
}
