/// <summary>
/// Performs cross validation on a pipeline.
/// </summary>
/// <typeparam name="TInput">Class type that represents input schema.</typeparam>
/// <typeparam name="TOutput">Class type that represents prediction schema.</typeparam>
/// <param name="pipeline">Machine learning pipeline may contain loader, transforms and at least one trainer.</param>
/// <returns>List containing metrics and predictor model for each fold</returns>
public CrossValidationOutput <TInput, TOutput> CrossValidate <TInput, TOutput>(LearningPipeline pipeline)
where TInput : class
where TOutput : class, new()
{
var environment = new MLContext();
{
Experiment subGraph = environment.CreateExperiment();
ILearningPipelineStep step = null;
List <ILearningPipelineLoader> loaders = new List <ILearningPipelineLoader>();
List <Var <TransformModel> > transformModels = new List <Var <TransformModel> >();
Var <TransformModel> lastTransformModel = null;
Var <IDataView> firstPipelineDataStep = null;
Var <PredictorModel> firstModel = null;
ILearningPipelineItem firstTransform = null;
foreach (ILearningPipelineItem currentItem in pipeline)
{
if (currentItem is ILearningPipelineLoader loader)
{
loaders.Add(loader);
continue;
}
step = currentItem.ApplyStep(step, subGraph);
if (step is ILearningPipelineDataStep dataStep && dataStep.Model != null)
{
transformModels.Add(dataStep.Model);
if (firstPipelineDataStep == null)
{
firstPipelineDataStep = dataStep.Data;
firstTransform = currentItem;
}
}
/// <summary>
/// Performs train-test on a pipeline.
/// </summary>
/// <typeparam name="TInput">Class type that represents input schema.</typeparam>
/// <typeparam name="TOutput">Class type that represents prediction schema.</typeparam>
/// <param name="pipeline">Machine learning pipeline that contains <see cref="ILearningPipelineLoader"/>,
/// transforms and at least one trainer.</param>
/// <param name="testData"><see cref="ILearningPipelineLoader"/> that represents the test dataset.</param>
/// <returns>Metrics and predictor model.</returns>
public TrainTestEvaluatorOutput <TInput, TOutput> TrainTestEvaluate <TInput, TOutput>(LearningPipeline pipeline, ILearningPipelineLoader testData)
where TInput : class
where TOutput : class, new()
{
using (var environment = new TlcEnvironment())
{
Experiment subGraph = environment.CreateExperiment();
ILearningPipelineStep step = null;
List <ILearningPipelineLoader> loaders = new List <ILearningPipelineLoader>();
List <Var <ITransformModel> > transformModels = new List <Var <ITransformModel> >();
Var <ITransformModel> lastTransformModel = null;
Var <IDataView> firstPipelineDataStep = null;
Var <IPredictorModel> firstModel = null;
ILearningPipelineItem firstTransform = null;
foreach (ILearningPipelineItem currentItem in pipeline)
{
if (currentItem is ILearningPipelineLoader loader)
{
loaders.Add(loader);
continue;
}
step = currentItem.ApplyStep(step, subGraph);
if (step is ILearningPipelineDataStep dataStep && dataStep.Model != null)
{
transformModels.Add(dataStep.Model);
if (firstPipelineDataStep == null)
{
firstPipelineDataStep = dataStep.Data;
firstTransform = currentItem;
}
}
public PredictionModel<IrisData, IrisPrediction> Train()
{
string datapath = textBox1.Text;
int index = listBox1.SelectedIndex;
switch (index)
{
case 0:
algorithm = new StochasticDualCoordinateAscentClassifier();
break;
case 1:
algorithm = new NaiveBayesClassifier();
break;
case 2:
algorithm = new FastForestBinaryClassifier();
break;
}
GetColumns gc = new GetColumns();
var iris = gc.getColumns();
var pipeline = new LearningPipeline {
new TextLoader(datapath).CreateFrom<IrisData>(useHeader: true, separator: ','),
new Dictionarizer("Label"),
new ColumnConcatenator("Features", iris),
algorithm,
new PredictedLabelColumnOriginalValueConverter() { PredictedLabelColumn = "PredictedLabel" }
};
PredictionModel<IrisData, IrisPrediction> model = pipeline.Train<IrisData, IrisPrediction>();
return model;
}
/// <summary>
/// Removes an existing <see cref="ILearningPipelineItem"/>ILearningPipelineItem</see> item.
/// </summary>
/// <param name="item"></param>
/// <returns></returns>
public IFluentLearningPipeline <TInput, TOutput> Remove(ILearningPipelineItem item)
{
if (item is null)
{
throw new ArgumentNullException(nameof(item));
}
if (HasPipeline)
{
_pipeline.Remove(item);
}
return(this);
}
/// <summary>
/// Add a <see cref="ILearningPipelineItem"/>ILearningPipelineItem</see> to the LearningPipeline
/// </summary>
/// <param name="item"></param>
/// <returns></returns>
/// <exception cref="ArgumentNullException"></exception>
public IFluentLearningPipeline <TInput, TOutput> Add(ILearningPipelineItem item)
{
if (item is null)
{
throw new ArgumentNullException(nameof(item));
}
if (HasPipeline && !_pipeline.Contains(item))
{
_pipeline.Add(item);
}
return(this);
}
public ModelBuilder(string trainingDataLocation, ILearningPipelineItem algorythm)
{
_trainingDataLocation = trainingDataLocation;
_algorythm = algorythm;
}
TrainAndGetMetrics(ILearningPipelineLoader dataTrain, ILearningPipelineLoader dataTest, ILearningPipelineItem trainer)
{
var pipeline = new LearningPipeline();
pipeline.Add(dataTrain);
pipeline.Add(trainer);
var model = pipeline.Train <MLNetData, MLNetPredict>();
var evaluator = new BinaryClassificationEvaluator();
var metrics = evaluator.Evaluate(model, dataTest);
return(metrics.Accuracy, metrics.Auc, metrics.F1Score, model);
}
private LocalEnvironment _mlContext = new LocalEnvironment(seed: null); // v0.6;
public PredictionModel <BinaryClassificationData, BinaryClassificationPrediction> BuildAndTrain(string trainingDataPath, ILearningPipelineItem algorithm)
{
var pipeline = new LearningPipeline();
pipeline.Add(new TextLoader(trainingDataPath).CreateFrom <BinaryClassificationData>(useHeader: true, separator: ';'));
pipeline.Add(new MissingValueSubstitutor("FixedAcidity")
{
ReplacementKind = NAReplaceTransformReplacementKind.Mean
});
pipeline.Add(MakeNormalizer());
pipeline.Add(new ColumnConcatenator("Features",
"FixedAcidity",
"VolatileAcidity",
"CitricAcid",
"ResidualSugar",
"Chlorides",
"FreeSulfurDioxide",
"TotalSulfurDioxide",
"Density",
"Ph",
"Sulphates",
"Alcohol"));
pipeline.Add(algorithm);
return(pipeline.Train <BinaryClassificationData, BinaryClassificationPrediction>());
}
public Task <PredictionModel <BinaryClassificationData, BinaryClassificationPrediction> > BuildAndTrain(string trainingDataPath, ILearningPipelineItem algorithm)
{
return(Task.Run(() =>
{
return _model.BuildAndTrain(trainingDataPath, algorithm);
}));
}
