/// <summary>
/// Loads the classifier provided by the <c>classifierFactory</c> which is modelled using the specified <c>model_file</c>.
/// Then, the classifier is used to evaluate the accuracy of the <c>vector_data</c>.
/// A report on the classification details is printed to the <c>output_file</c>.
/// </summary>
/// <param name="model_file">A file containing a serialization of the classifier model.</param>
/// <param name="sys_output">A report on the classification details.</param>
/// <param name="classifierFactory">Provides the necessary classifier.</param>
internal static double ReportOnModel(
FeatureVectorFile vectorFile
, string sys_output
, Func <TextIdMapper, TextIdMapper, Classifier> classifierFactory
, Func <Classifier, List <FeatureVector>, TextIdMapper, TextIdMapper, string[]> getDetailsFunc
)
{
int gold_i = 0;
TextIdMapper featureToFeatureId = new TextIdMapper();
TextIdMapper classToClassId = new TextIdMapper();
TextIdMapper[] headerToHeaderIds = new TextIdMapper[] { classToClassId };
Classifier classifier = classifierFactory(classToClassId, featureToFeatureId);
var vectors = vectorFile.LoadFromSVMLight(featureToFeatureId, headerToHeaderIds, FeatureType.Binary);
var goldClasses = vectorFile.Headers[gold_i];
var systemClasses = classifier.Classify(vectors);
string[] details = getDetailsFunc(classifier, vectors, classToClassId, featureToFeatureId);
var accuracy = ProgramOutput.GenerateSysOutput(sys_output, FileCreationMode.CreateNew, vectors, classToClassId, goldClasses, systemClasses, details, heading: Path.GetFileName(vectorFile.Path));
return(accuracy);
}
// Public Methods
public override double ExecuteCommand()
{
FeatureVectorFile vectorFile_train = new FeatureVectorFile(path: training_data_file, noOfHeaderColumns: 1, featureDelimiter: ' ', isSortRequired: true);
FeatureVectorFile vectorFile_test = new FeatureVectorFile(path: test_data_file, noOfHeaderColumns: 1, featureDelimiter: ' ', isSortRequired: true);
int gold_i = 0;
TextIdMapper featureToFeatureId = new TextIdMapper();
TextIdMapper classToClassId = new TextIdMapper();
TextIdMapper[] headerToHeaderIds = new TextIdMapper[] { classToClassId };
var trainingVectors = vectorFile_train.LoadFromSVMLight(featureToFeatureId, headerToHeaderIds, FeatureType.Binary);
var goldClasses_train = vectorFile_train.Headers[gold_i];
var testVectors = vectorFile_test.LoadFromSVMLight(featureToFeatureId, headerToHeaderIds, FeatureType.Binary);
var goldClasses_test = vectorFile_test.Headers[gold_i];
var classifier = new kNNClassifier(k_val, (SimilarityFunction)similarity_func, trainingVectors, classToClassId.Count, gold_i);
var systemClasses_train = classifier.Classify(trainingVectors);
var systemClasses_test = classifier.Classify(testVectors);
var details_train = ProgramOutput.GetDistributionDetails(classifier, trainingVectors, classToClassId);
var details_test = ProgramOutput.GetDistributionDetails(classifier, testVectors, classToClassId);
ProgramOutput.GenerateSysOutput(sys_output, FileCreationMode.CreateNew, trainingVectors, classToClassId, goldClasses_train, systemClasses_train, details_train, "training data");
var testAccuracy = ProgramOutput.GenerateSysOutput(sys_output, FileCreationMode.Append, testVectors, classToClassId, goldClasses_test, systemClasses_test, details_test, "test data");
return(testAccuracy);
}
/// <summary>
/// Trains the classifier provided by the <c>classifierFactory</c> on the <c>training_data</c>.
/// Then, the classifier is used to evaluate the accuracy of both the <c>training_data</c> and <c>test_data</c>.
/// A report on the classification details is printed to the <c>output_file</c>.
/// </summary>
/// <param name="output_file">A report on the classification details.</param>
/// <param name="classifierFactory">Provides the necessary classifier.</param>
internal static void ReportOnTrainingAndTesting(
FeatureVectorFile vectorFile_train
, FeatureVectorFile vectorFile_test
, string output_file
, Func <List <FeatureVector>, int, int, Classifier> classifierFactory
, Func <Classifier, List <FeatureVector>, TextIdMapper, string[]> getDetailsFunc
)
{
int gold_i = 0;
TextIdMapper featureToFeatureId = new TextIdMapper();
TextIdMapper classToClassId = new TextIdMapper();
TextIdMapper[] headerToHeaderIds = new TextIdMapper[] { classToClassId };
var trainingVectors = vectorFile_train.LoadFromSVMLight(featureToFeatureId, headerToHeaderIds, FeatureType.Binary);
var goldClasses_train = vectorFile_train.Headers[gold_i];
var testVectors = vectorFile_test.LoadFromSVMLight(featureToFeatureId, headerToHeaderIds, FeatureType.Binary);
var goldClasses_test = vectorFile_test.Headers[gold_i];
Classifier classifier = classifierFactory(trainingVectors, classToClassId.Count, gold_i);
var systemClasses_train = classifier.Classify(trainingVectors);
var systemClasses_test = classifier.Classify(testVectors);
var details_train = ProgramOutput.GetDistributionDetails(classifier, trainingVectors, classToClassId);
var details_test = ProgramOutput.GetDistributionDetails(classifier, testVectors, classToClassId);
ProgramOutput.GenerateSysOutput(output_file, FileCreationMode.CreateNew, trainingVectors, classToClassId, goldClasses_train, systemClasses_train, details_train, "training data");
ProgramOutput.GenerateSysOutput(output_file, FileCreationMode.Append, testVectors, classToClassId, goldClasses_test, systemClasses_test, details_test, "test data");
}