/// <summary>
/// Runs the module.
/// </summary>
/// <param name="args">The command line arguments for the module.</param>
/// <param name="usagePrefix">The prefix to print before the usage string.</param>
/// <returns>True if the run was successful, false otherwise.</returns>
public override bool Run(string[] args, string usagePrefix)
{
string trainingSetFile = string.Empty;
string maxParameterChangesFile = string.Empty;
string modelFile = string.Empty;
int iterationCount = BayesPointMachineClassifierTrainingSettings.IterationCountDefault;
int batchCount = BayesPointMachineClassifierTrainingSettings.BatchCountDefault;
var parser = new CommandLineParser();
parser.RegisterParameterHandler("--training-set", "FILE", "File with training data", v => trainingSetFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--results", "FILE", "File to store the maximum parameter differences", v => maxParameterChangesFile = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--model", "FILE", "File to store the trained binary Bayes point machine model", v => modelFile = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--iterations", "NUM", "Number of training algorithm iterations (defaults to " + iterationCount + ")", v => iterationCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--batches", "NUM", "Number of batches to split the training data into (defaults to " + batchCount + ")", v => batchCount = v, CommandLineParameterType.Optional);
if (!parser.TryParse(args, usagePrefix))
{
return(false);
}
var trainingSet = ClassifierPersistenceUtils.LoadLabeledFeatureValues(trainingSetFile);
BayesPointMachineClassifierModuleUtilities.WriteDataSetInfo(trainingSet);
var classifier = BayesPointMachineClassifier.CreateBinaryClassifier(Mappings.Classifier);
classifier.Settings.Training.IterationCount = iterationCount;
classifier.Settings.Training.BatchCount = batchCount;
BayesPointMachineClassifierModuleUtilities.DiagnoseClassifier(classifier, trainingSet, maxParameterChangesFile, modelFile);
return(true);
}
/// <summary>
/// Runs the module.
/// </summary>
/// <param name="args">The command line arguments for the module.</param>
/// <param name="usagePrefix">The prefix to print before the usage string.</param>
/// <returns>True if the run was successful, false otherwise.</returns>
public override bool Run(string[] args, string usagePrefix)
{
string testSetFile = string.Empty;
string modelFile = string.Empty;
string predictionsFile = string.Empty;
var parser = new CommandLineParser();
parser.RegisterParameterHandler("--test-set", "FILE", "File with test data", v => testSetFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--model", "FILE", "File with a trained multi-class Bayes point machine model", v => modelFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--predictions", "FILE", "File to store predictions for the test data", v => predictionsFile = v, CommandLineParameterType.Required);
if (!parser.TryParse(args, usagePrefix))
{
return(false);
}
var testSet = ClassifierPersistenceUtils.LoadLabeledFeatureValues(testSetFile);
BayesPointMachineClassifierModuleUtilities.WriteDataSetInfo(testSet);
var classifier =
BayesPointMachineClassifier.LoadMulticlassClassifier <IList <LabeledFeatureValues>, LabeledFeatureValues, IList <LabelDistribution>, string, IDictionary <string, double> >(modelFile);
// Predict labels
var predictions = classifier.PredictDistribution(testSet);
// Write labels to file
ClassifierPersistenceUtils.SaveLabelDistributions(predictionsFile, predictions);
return(true);
}
public override void Evaluate(
string inputModelFileName,
string reportFileName,
string positiveClassLabel,
string groundTruthFileName,
string predictionsFileName,
string weightsFileName,
string calibrationCurveFileName,
string precisionRecallCurveFileName,
string rocCurveFileName)
{
IBayesPointMachineClassifier <
IList <Vector>, int, IList <string>, string, IDictionary <string, double>,
BayesPointMachineClassifierTrainingSettings,
BinaryBayesPointMachineClassifierPredictionSettings <string> > classifier = null;
// Validate
_validate.Evaluate(
inputModelFileName: inputModelFileName,
reportFileName: reportFileName,
groundTruthFileName: groundTruthFileName,
predictionsFileName: predictionsFileName,
weightsFileName: weightsFileName,
calibrationCurveFileName: calibrationCurveFileName,
precisionRecallCurveFileName: precisionRecallCurveFileName,
rocCurveFileName: rocCurveFileName);
// Load model
if (string.IsNullOrEmpty(inputModelFileName))
{
classifier =
BayesPointMachineClassifier.LoadBinaryClassifier <
IList <Vector>, int, IList <string>, string, IDictionary <string, double> >
(inputModelFileName);
}
else
{
classifier = _classifier;
}
EvaluationReportsMapped evaluationReports = new EvaluationReportsMapped(
classifier,
_evaluator,
_x,
_y,
_yPredicDistrib,
_yPredicLabel,
reportFileName,
positiveClassLabel,
groundTruthFileName,
predictionsFileName,
weightsFileName,
calibrationCurveFileName,
precisionRecallCurveFileName,
rocCurveFileName);
}
/// <summary>
/// Runs the module.
/// </summary>
/// <param name="args">The command line arguments for the module.</param>
/// <param name="usagePrefix">The prefix to print before the usage string.</param>
/// <returns>True if the run was successful, false otherwise.</returns>
public override bool Run(string[] args, string usagePrefix)
{
string trainingSetFile = string.Empty;
string modelFile = string.Empty;
int iterationCount = BayesPointMachineClassifierTrainingSettings.IterationCountDefault;
int batchCount = BayesPointMachineClassifierTrainingSettings.BatchCountDefault;
bool computeModelEvidence = BayesPointMachineClassifierTrainingSettings.ComputeModelEvidenceDefault;
var parser = new CommandLineParser();
parser.RegisterParameterHandler("--training-set", "FILE", "File with training data", v => trainingSetFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--model", "FILE", "File to store the trained multi-class Bayes point machine model", v => modelFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--iterations", "NUM", "Number of training algorithm iterations (defaults to " + iterationCount + ")", v => iterationCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--batches", "NUM", "Number of batches to split the training data into (defaults to " + batchCount + ")", v => batchCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--compute-evidence", "Compute model evidence (defaults to " + computeModelEvidence + ")", () => computeModelEvidence = true);
if (!parser.TryParse(args, usagePrefix))
{
return(false);
}
var trainingSet = ClassifierPersistenceUtils.LoadLabeledFeatureValues(trainingSetFile);
BayesPointMachineClassifierModuleUtilities.WriteDataSetInfo(trainingSet);
var featureSet = trainingSet.Count > 0 ? trainingSet.First().FeatureSet : null;
var mapping = new ClassifierMapping(featureSet);
var classifier = BayesPointMachineClassifier.CreateMulticlassClassifier(mapping);
classifier.Settings.Training.IterationCount = iterationCount;
classifier.Settings.Training.BatchCount = batchCount;
classifier.Settings.Training.ComputeModelEvidence = computeModelEvidence;
classifier.Train(trainingSet);
if (classifier.Settings.Training.ComputeModelEvidence)
{
Console.WriteLine("Log evidence = {0,10:0.0000}", classifier.LogModelEvidence);
}
classifier.Save(modelFile);
return(true);
}
void TestML()
{
ExpectList el = new PK10ExpectReader().ReadNewestData(DateTime.Now.AddDays(-17));//至少180*16天+当天的记录数>1000
//MessageBox.Show(el.LastData.OpenCode);
var mapping = new DaXiao_Mapping();
var classifier = BayesPointMachineClassifier.CreateMulticlassClassifier(mapping);
FeatureLabeItems trainingSet = new PKDataListSetFactory(el).OccurFeatureAndLabels();
classifier.Train(trainingSet.FeatureVectors, trainingSet.Labels);
List <Vector> testVector = new List <Vector>();//1
Vector v = Vector.Zero(1);
v[0] = 1;
testVector.Add(v);
var predictions = classifier.PredictDistribution(testVector);
string estimate = classifier.Predict(0, testVector);
MessageBox.Show(estimate);
}
public override IDictionary <string, double> PredictInstance(
string inputModelFileName,
DistributionName distributionName,
InferenceAlgorithm inferenceEngineAlgorithm,
int instance,
double noise)
{
TraceListeners.Log(TraceEventType.Warning, 0,
"Advanced setting will not be used: " +
"distributionName, inferenceEngineAlgorithm & noise.", false, true);
// Validate
_validate.PredictInstance(
inputModelFileName: inputModelFileName,
instance: instance,
numObservations: _numObservations);
IBayesPointMachineClassifier <
IList <Vector>, int, IList <string>, string, IDictionary <string, double>,
BayesPointMachineClassifierTrainingSettings,
BinaryBayesPointMachineClassifierPredictionSettings <string> > classifier = null;
// Load model
if (string.IsNullOrEmpty(inputModelFileName))
{
classifier =
BayesPointMachineClassifier.LoadBinaryClassifier <
IList <Vector>, int, IList <string>, string, IDictionary <string, double> >
(inputModelFileName);
}
else
{
classifier = _classifier;
}
IDictionary <string, double> yPredicted =
classifier.PredictDistribution(instance, _x);
// string yPredicLabel = classifier.Predict(instance, _x);
return(yPredicted);
}
/// <summary>
/// Runs the module.
/// </summary>
/// <param name="args">The command line arguments for the module.</param>
/// <param name="usagePrefix">The prefix to print before the usage string.</param>
/// <returns>True if the run was successful, false otherwise.</returns>
public override bool Run(string[] args, string usagePrefix)
{
string modelFile = string.Empty;
string samplesFile = string.Empty;
var parser = new CommandLineParser();
parser.RegisterParameterHandler("--model", "FILE", "File with a trained binary Bayes point machine model", v => modelFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--samples", "FILE", "File to store samples of the weights", v => samplesFile = v, CommandLineParameterType.Required);
if (!parser.TryParse(args, usagePrefix))
{
return(false);
}
var classifier =
BayesPointMachineClassifier.LoadBinaryClassifier <IList <LabeledFeatureValues>, LabeledFeatureValues, IList <LabelDistribution>, string, IDictionary <string, double> >(modelFile);
BayesPointMachineClassifierModuleUtilities.SampleWeights(classifier, samplesFile);
return(true);
}
public override void TrainIncremental(
string inputModelFileName,
string outputModelFileName,
int iterationCount,
bool computeModelEvidence,
int batchCount,
DistributionName distributionName,
InferenceAlgorithm inferenceEngineAlgorithm,
double noise)
{
TraceListeners.Log(TraceEventType.Warning, 0,
"Advanced setting will not be used: " +
"distributionName, inferenceEngineAlgorithm & noise.", false, true);
// Validate
_validate.TrainIncremental(
inputModelFileName: inputModelFileName,
outputModelFileName: outputModelFileName,
iterationCount: iterationCount,
batchCount: batchCount);
// Load model
IBayesPointMachineClassifier <
IList <Vector>, int, IList <string>, string, IDictionary <string, double>,
BayesPointMachineClassifierTrainingSettings,
BinaryBayesPointMachineClassifierPredictionSettings <string> > classifier =
BayesPointMachineClassifier.LoadBinaryClassifier <
IList <Vector>, int, IList <string>, string, IDictionary <string, double> >
(inputModelFileName);
// Set settings
classifier.Settings.Training.ComputeModelEvidence = computeModelEvidence;
classifier.Settings.Training.IterationCount = iterationCount;
classifier.Settings.Training.BatchCount = batchCount;
// train
classifier.TrainIncremental(_x, _y);
classifier.Save(outputModelFileName);
}
/// <summary>
/// Runs the module.
/// </summary>
/// <param name="args">The command line arguments for the module.</param>
/// <param name="usagePrefix">The prefix to print before the usage string.</param>
/// <returns>True if the run was successful, false otherwise.</returns>
public override bool Run(string[] args, string usagePrefix)
{
string trainingSetFile = string.Empty;
string inputModelFile = string.Empty;
string outputModelFile = string.Empty;
int iterationCount = BayesPointMachineClassifierTrainingSettings.IterationCountDefault;
int batchCount = BayesPointMachineClassifierTrainingSettings.BatchCountDefault;
var parser = new CommandLineParser();
parser.RegisterParameterHandler("--training-set", "FILE", "File with training data", v => trainingSetFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--input-model", "FILE", "File with the trained multi-class Bayes point machine model", v => inputModelFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--model", "FILE", "File to store the incrementally trained multi-class Bayes point machine model", v => outputModelFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--iterations", "NUM", "Number of training algorithm iterations (defaults to " + iterationCount + ")", v => iterationCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--batches", "NUM", "Number of batches to split the training data into (defaults to " + batchCount + ")", v => batchCount = v, CommandLineParameterType.Optional);
if (!parser.TryParse(args, usagePrefix))
{
return(false);
}
var trainingSet = ClassifierPersistenceUtils.LoadLabeledFeatureValues(trainingSetFile);
BayesPointMachineClassifierModuleUtilities.WriteDataSetInfo(trainingSet);
var classifier = BayesPointMachineClassifier.LoadMulticlassClassifier <IList <LabeledFeatureValues>, LabeledFeatureValues, IList <LabelDistribution>, string, IDictionary <string, double> >(inputModelFile);
classifier.Settings.Training.IterationCount = iterationCount;
classifier.Settings.Training.BatchCount = batchCount;
classifier.TrainIncremental(trainingSet);
classifier.Save(outputModelFile);
return(true);
}
public BPMMapped(
string[] labels)
{
Debug.Assert(labels != null, "The labels must not be null.");
Debug.Assert(labels.Length == 2, "The labels must have two possible values.");
// Initialise the validations
_validate = new Validate();
// Create a BPM from the mapping
_mapping = new GenericClassifierMapping(labels);
_classifier = BayesPointMachineClassifier.CreateBinaryClassifier(_mapping);
// Evaluator mapping
var evaluatorMapping = _mapping.ForEvaluation();
_evaluator = new ClassifierEvaluator
<IList <Vector>, int, IList <string>, string>(evaluatorMapping);
// Other initialisations
_availableDatasetName = new DatasetName();
_numObservations = 0;
_numFeatures = 0;
}
public override void Predict(
string inputModelFileName,
DistributionName distributionName,
InferenceAlgorithm inferenceEngineAlgorithm,
double noise)
{
TraceListeners.Log(TraceEventType.Warning, 0,
"Advanced setting will not be used: " +
"distributionName, inferenceEngineAlgorithm & noise.", false, true);
// Validate
_validate.Predict(inputModelFileName);
// Define the classifier
IBayesPointMachineClassifier <
IList <Vector>, int, IList <string>, string, IDictionary <string, double>,
BayesPointMachineClassifierTrainingSettings,
BinaryBayesPointMachineClassifierPredictionSettings <string> > classifier = null;
// Load model
if (string.IsNullOrEmpty(inputModelFileName))
{
classifier =
BayesPointMachineClassifier.LoadBinaryClassifier <
IList <Vector>, int, IList <string>, string, IDictionary <string, double> >
(inputModelFileName);
}
else
{
classifier = _classifier;
}
_validate.ValidatePredict(_x, _x);
_yPredicDistrib = classifier.PredictDistribution(_x);
_yPredicLabel = classifier.Predict(_x);
}
/// <summary>
/// Runs the module.
/// </summary>
/// <param name="args">The command line arguments for the module.</param>
/// <param name="usagePrefix">The prefix to print before the usage string.</param>
/// <returns>True if the run was successful, false otherwise.</returns>
public override bool Run(string[] args, string usagePrefix)
{
string dataSetFile = string.Empty;
string resultsFile = string.Empty;
int crossValidationFoldCount = 5;
int iterationCount = BayesPointMachineClassifierTrainingSettings.IterationCountDefault;
int batchCount = BayesPointMachineClassifierTrainingSettings.BatchCountDefault;
bool computeModelEvidence = BayesPointMachineClassifierTrainingSettings.ComputeModelEvidenceDefault;
var parser = new CommandLineParser();
parser.RegisterParameterHandler("--data-set", "FILE", "File with training data", v => dataSetFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--results", "FILE", "File with cross-validation results", v => resultsFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--folds", "NUM", "Number of cross-validation folds (defaults to " + crossValidationFoldCount + ")", v => crossValidationFoldCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--iterations", "NUM", "Number of training algorithm iterations (defaults to " + iterationCount + ")", v => iterationCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--batches", "NUM", "Number of batches to split the training data into (defaults to " + batchCount + ")", v => batchCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--compute-evidence", "Compute model evidence (defaults to " + computeModelEvidence + ")", () => computeModelEvidence = true);
if (!parser.TryParse(args, usagePrefix))
{
return(false);
}
// Load and shuffle data
var dataSet = ClassifierPersistenceUtils.LoadLabeledFeatureValues(dataSetFile);
BayesPointMachineClassifierModuleUtilities.WriteDataSetInfo(dataSet);
Rand.Restart(562);
Rand.Shuffle(dataSet);
// Create evaluator
var evaluatorMapping = Mappings.Classifier.ForEvaluation();
var evaluator = new ClassifierEvaluator <IList <LabeledFeatureValues>, LabeledFeatureValues, IList <LabelDistribution>, string>(evaluatorMapping);
// Create performance metrics
var accuracy = new List <double>();
var negativeLogProbability = new List <double>();
var auc = new List <double>();
var evidence = new List <double>();
var iterationCounts = new List <double>();
var trainingTime = new List <double>();
// Run cross-validation
int validationSetSize = dataSet.Count / crossValidationFoldCount;
Console.WriteLine("Running {0}-fold cross-validation on {1}", crossValidationFoldCount, dataSetFile);
// TODO: Use chained mapping to implement cross-validation
for (int fold = 0; fold < crossValidationFoldCount; fold++)
{
// Construct training and validation sets for fold
int validationSetStart = fold * validationSetSize;
int validationSetEnd = (fold + 1 == crossValidationFoldCount)
? dataSet.Count
: (fold + 1) * validationSetSize;
var trainingSet = new List <LabeledFeatureValues>();
var validationSet = new List <LabeledFeatureValues>();
for (int instance = 0; instance < dataSet.Count; instance++)
{
if (validationSetStart <= instance && instance < validationSetEnd)
{
validationSet.Add(dataSet[instance]);
}
else
{
trainingSet.Add(dataSet[instance]);
}
}
// Print info
Console.WriteLine(" Fold {0} [validation set instances {1} - {2}]", fold + 1, validationSetStart, validationSetEnd - 1);
// Create classifier
var classifier = BayesPointMachineClassifier.CreateBinaryClassifier(Mappings.Classifier);
classifier.Settings.Training.IterationCount = iterationCount;
classifier.Settings.Training.BatchCount = batchCount;
classifier.Settings.Training.ComputeModelEvidence = computeModelEvidence;
int currentIterationCount = 0;
classifier.IterationChanged += (sender, eventArgs) => { currentIterationCount = eventArgs.CompletedIterationCount; };
// Train classifier
var stopWatch = new Stopwatch();
stopWatch.Start();
classifier.Train(trainingSet);
stopWatch.Stop();
// Produce predictions
var predictions = classifier.PredictDistribution(validationSet).ToList();
var predictedLabels = predictions.Select(
prediction => prediction.Aggregate((aggregate, next) => next.Value > aggregate.Value ? next : aggregate).Key).ToList();
// Iteration count
iterationCounts.Add(currentIterationCount);
// Training time
trainingTime.Add(stopWatch.ElapsedMilliseconds);
// Compute accuracy
accuracy.Add(1 - (evaluator.Evaluate(validationSet, predictedLabels, Metrics.ZeroOneError) / predictions.Count));
// Compute mean negative log probability
negativeLogProbability.Add(evaluator.Evaluate(validationSet, predictions, Metrics.NegativeLogProbability) / predictions.Count);
// Compute M-measure (averaged pairwise AUC)
auc.Add(evaluator.AreaUnderRocCurve(validationSet, predictions));
// Compute log evidence if desired
evidence.Add(computeModelEvidence ? classifier.LogModelEvidence : double.NaN);
// Persist performance metrics
Console.WriteLine(
" Accuracy = {0,5:0.0000} NegLogProb = {1,5:0.0000} AUC = {2,5:0.0000}{3} Iterations = {4} Training time = {5}",
accuracy[fold],
negativeLogProbability[fold],
auc[fold],
computeModelEvidence ? string.Format(" Log evidence = {0,5:0.0000}", evidence[fold]) : string.Empty,
iterationCounts[fold],
BayesPointMachineClassifierModuleUtilities.FormatElapsedTime(trainingTime[fold]));
BayesPointMachineClassifierModuleUtilities.SavePerformanceMetrics(
resultsFile, accuracy, negativeLogProbability, auc, evidence, iterationCounts, trainingTime);
}
return(true);
}
/// <summary>
/// CrossValidate diagnosis
/// </summary>
/// <param name="x"></param>
/// <param name="y"></param>
/// <param name="mapping"></param>
/// <param name="reportFileName"></param>
/// <param name="crossValidationFoldCount"></param>
/// <param name="iterationCount"></param>
/// <param name="computeModelEvidence"></param>
/// <param name="batchCount"></param>
/// <remarks>Adapted from MicrosoftResearch.Infer.Learners</remarks>
public CrossValidateMapped(
Vector[] x,
IList <string> y,
GenericClassifierMapping mapping,
string reportFileName,
int crossValidationFoldCount, //folds
int iterationCount,
bool computeModelEvidence,
int batchCount)
{
Debug.Assert(x != null, "The feature vector must not be null.");
Debug.Assert(y != null, "The targe variable must not be null.");
Debug.Assert(mapping != null, "The classifier map must not be null.");
Debug.Assert(!string.IsNullOrEmpty(reportFileName), "The report file name must not be null/empty.");
Debug.Assert(iterationCount > 0, "The iteration count must be greater than zero.");
Debug.Assert(batchCount > 0, "The batch count must be greater than zero.");
// Shuffle dataset
shuffleVector(x);
// Create evaluator
var evaluatorMapping = mapping.ForEvaluation();
var evaluator = new ClassifierEvaluator <
IList <Vector>, // the type of the instance source,
int, // the type of an instance
IList <string>, // the type of the label source
string>( // the type of a label.
evaluatorMapping);
// Create performance metrics
var accuracy = new List <double>();
var negativeLogProbability = new List <double>();
var auc = new List <double>();
var evidence = new List <double>();
var iterationCounts = new List <double>();
var trainingTime = new List <double>();
// Run cross-validation
int validationSetSize = x.Length / crossValidationFoldCount;
int trainingSetSize = x.Length - validationSetSize;
int validationFoldSetSize = 0;
int trainingFoldSetSize = 0;
Console.WriteLine(
"Running {0}-fold cross-validation", crossValidationFoldCount);
if (validationSetSize == 0 || trainingSetSize == 0)
{
Console.WriteLine("Invalid number of folds");
Console.ReadKey();
System.Environment.Exit(1);
}
for (int fold = 0; fold < crossValidationFoldCount; fold++)
{
// Construct training and validation sets for fold
int validationSetStart = fold * validationSetSize;
int validationSetEnd = (fold + 1 == crossValidationFoldCount)
? x.Length
: (fold + 1) * validationSetSize;
validationFoldSetSize = validationSetEnd - validationSetStart;
trainingFoldSetSize = x.Length - validationFoldSetSize;
Vector[] trainingSet = new Vector[trainingFoldSetSize];
Vector[] validationSet = new Vector[validationFoldSetSize];
IList <string> trainingSetLabels = new List <string>();
IList <string> validationSetLabels = new List <string>();
for (int instance = 0, iv = 0, it = 0; instance < x.Length; instance++)
{
if (validationSetStart <= instance && instance < validationSetEnd)
{
validationSet[iv++] = x[instance];
validationSetLabels.Add(y[instance]);
}
else
{
trainingSet[it++] = x[instance];
trainingSetLabels.Add(y[instance]);
}
}
// Print info
Console.WriteLine(" Fold {0} [validation set instances {1} - {2}]", fold + 1, validationSetStart, validationSetEnd - 1);
// Create classifier
var classifier = BayesPointMachineClassifier.CreateBinaryClassifier(mapping);
classifier.Settings.Training.IterationCount = iterationCount;
classifier.Settings.Training.BatchCount = batchCount;
classifier.Settings.Training.ComputeModelEvidence = computeModelEvidence;
int currentIterationCount = 0;
classifier.IterationChanged += (sender, eventArgs) => { currentIterationCount = eventArgs.CompletedIterationCount; };
// Train classifier
var stopWatch = new Stopwatch();
stopWatch.Start();
classifier.Train(trainingSet, trainingSetLabels);
stopWatch.Stop();
// Produce predictions
IEnumerable <IDictionary <string, double> > predictions =
classifier.PredictDistribution(validationSet);
var predictedLabels = classifier.Predict(validationSet);
// Iteration count
iterationCounts.Add(currentIterationCount);
// Training time
trainingTime.Add(stopWatch.ElapsedMilliseconds);
// Compute accuracy
accuracy.Add(1 - (evaluator.Evaluate(validationSet, validationSetLabels, predictedLabels, Metrics.ZeroOneError) / predictions.Count()));
// Compute mean negative log probability
negativeLogProbability.Add(evaluator.Evaluate(validationSet, validationSetLabels, predictions, Metrics.NegativeLogProbability) / predictions.Count());
// Compute M-measure (averaged pairwise AUC)
auc.Add(evaluator.AreaUnderRocCurve(validationSet, validationSetLabels, predictions));
// Compute log evidence if desired
evidence.Add(computeModelEvidence ? classifier.LogModelEvidence : double.NaN);
// Persist performance metrics
Console.WriteLine(
" Accuracy = {0,5:0.0000} NegLogProb = {1,5:0.0000} AUC = {2,5:0.0000}{3} Iterations = {4} Training time = {5}",
accuracy[fold],
negativeLogProbability[fold],
auc[fold],
computeModelEvidence ? string.Format(" Log evidence = {0,5:0.0000}", evidence[fold]) : string.Empty,
iterationCounts[fold],
FormatElapsedTime(trainingTime[fold]));
SavePerformanceMetrics(
reportFileName, accuracy, negativeLogProbability, auc, evidence, iterationCounts, trainingTime);
}
}
/// <summary>
/// Diagnoses the Bayes point machine classifier on the specified data set.
/// </summary>
/// <param name="x"></param>
/// <param name="y"></param>
/// <param name="mapping"></param>
/// <param name="reportFileName">The name of the file to store the maximum parameter differences.</param>
/// <param name="outputModelFileName">The name of the file to store the trained Bayes point machine model.</param>
/// <param name="iterationCount"></param>
/// <param name="computeModelEvidence"></param>
/// <param name="batchCount"></param>
/// <remarks>Adapted from MicrosoftResearch.Infer.Learners</remarks>
public void DiagnoseClassifier(
Vector[] x,
IList <string> y,
GenericClassifierMapping mapping,
string outputModelFileName,
string reportFileName,
int iterationCount,
bool computeModelEvidence,
int batchCount)
{
Debug.Assert(x != null, "The feature vector must not be null.");
Debug.Assert(y != null, "The targe variable must not be null.");
Debug.Assert(mapping != null, "The classifier map must not be null.");
Debug.Assert(!string.IsNullOrEmpty(reportFileName), "The report file name must not be null/empty.");
Debug.Assert(iterationCount > 0, "The iteration count must be greater than zero.");
Debug.Assert(batchCount > 0, "The batch count must be greater than zero.");
// create a BPM from the mapping
var classifier = BayesPointMachineClassifier.CreateBinaryClassifier(mapping);
classifier.Settings.Training.ComputeModelEvidence = computeModelEvidence;
classifier.Settings.Training.IterationCount = iterationCount;
classifier.Settings.Training.BatchCount = batchCount;
// Create prior distributions over weights
Dictionary <int, double[]> maxMean;
Dictionary <int, double[]> maxVar;
int classCount = 2;
int featureCount = x.Length;
var priorWeightDistributions = Util.ArrayInit(classCount, c => Util.ArrayInit(featureCount, f => new Gaussian(0.0, 1.0)));
// Create IterationChanged handler
var watch = new Stopwatch();
classifier.IterationChanged += (sender, eventArgs) =>
{
watch.Stop();
double maxParameterChange = MaxDiff(eventArgs.WeightPosteriorDistributions, priorWeightDistributions, out maxMean, out maxVar);
if (!string.IsNullOrEmpty(reportFileName))
{
SaveMaximumParameterDifference(
reportFileName,
eventArgs.CompletedIterationCount,
maxParameterChange,
watch.ElapsedMilliseconds,
maxMean,
maxVar);
}
Console.WriteLine(
"[{0}] Iteration {1,-4} dp = {2,-20} dt = {3,5}ms",
DateTime.Now.ToLongTimeString(),
eventArgs.CompletedIterationCount,
maxParameterChange,
watch.ElapsedMilliseconds);
// Copy weight marginals
for (int c = 0; c < eventArgs.WeightPosteriorDistributions.Count; c++)
{
for (int f = 0; f < eventArgs.WeightPosteriorDistributions[c].Count; f++)
{
priorWeightDistributions[c][f] = eventArgs.WeightPosteriorDistributions[c][f];
}
}
watch.Restart();
};
// Write file header
if (!string.IsNullOrEmpty(reportFileName))
{
using (var writer = new StreamWriter(reportFileName))
{
writer.WriteLine("# time, # iteration, " +
"# maximum absolute parameter difference, " +
"# iteration time in milliseconds, " +
"# Max Mean, # Max Var.");
}
}
// Train the Bayes point machine classifier
Console.WriteLine("[{0}] Starting training...", DateTime.Now.ToLongTimeString());
watch.Start();
classifier.Train(x, y);
// Compute evidence
if (classifier.Settings.Training.ComputeModelEvidence)
{
Console.WriteLine("Log evidence = {0,10:0.0000}", classifier.LogModelEvidence);
}
// Save trained model
if (!string.IsNullOrEmpty(outputModelFileName))
{
classifier.Save(outputModelFileName);
}
}
void ProcessData()
{
var mapping = new JiOu_Mapping();
var classifier = BayesPointMachineClassifier.CreateMulticlassClassifier(mapping);
}
