public virtual MultinomialLogisticClassifier <L, F> TrainClassifier(GeneralDataset <L, F> dataset)
{
numClasses = dataset.NumClasses();
numFeatures = dataset.NumFeatures();
data = dataset.GetDataArray();
if (dataset is RVFDataset <object, object> )
{
dataValues = dataset.GetValuesArray();
}
else
{
dataValues = LogisticUtils.InitializeDataValues(data);
}
AugmentFeatureMatrix(data, dataValues);
labels = dataset.GetLabelsArray();
return(new MultinomialLogisticClassifier <L, F>(TrainWeights(), dataset.featureIndex, dataset.labelIndex));
}
public virtual LogisticClassifier <L, F> TrainClassifier(GeneralDataset <L, F> data, double l1reg, double tol, LogPrior prior, bool biased)
{
if (data is RVFDataset)
{
((RVFDataset <L, F>)data).EnsureRealValues();
}
if (data.labelIndex.Size() != 2)
{
throw new Exception("LogisticClassifier is only for binary classification!");
}
IMinimizer <IDiffFunction> minim;
if (!biased)
{
LogisticObjectiveFunction lof = null;
if (data is Dataset <object, object> )
{
lof = new LogisticObjectiveFunction(data.NumFeatureTypes(), data.GetDataArray(), data.GetLabelsArray(), prior);
}
else
{
if (data is RVFDataset <object, object> )
{
lof = new LogisticObjectiveFunction(data.NumFeatureTypes(), data.GetDataArray(), data.GetValuesArray(), data.GetLabelsArray(), prior);
}
}
if (l1reg > 0.0)
{
minim = ReflectionLoading.LoadByReflection("edu.stanford.nlp.optimization.OWLQNMinimizer", l1reg);
}
else
{
minim = new QNMinimizer(lof);
}
weights = minim.Minimize(lof, tol, new double[data.NumFeatureTypes()]);
}
else
{
BiasedLogisticObjectiveFunction lof = new BiasedLogisticObjectiveFunction(data.NumFeatureTypes(), data.GetDataArray(), data.GetLabelsArray(), prior);
if (l1reg > 0.0)
{
minim = ReflectionLoading.LoadByReflection("edu.stanford.nlp.optimization.OWLQNMinimizer", l1reg);
}
else
{
minim = new QNMinimizer(lof);
}
weights = minim.Minimize(lof, tol, new double[data.NumFeatureTypes()]);
}
featureIndex = data.featureIndex;
classes[0] = data.labelIndex.Get(0);
classes[1] = data.labelIndex.Get(1);
return(new LogisticClassifier <L, F>(weights, featureIndex, classes));
}
public virtual LogisticClassifier <L, F> TrainWeightedData(GeneralDataset <L, F> data, float[] dataWeights)
{
if (data is RVFDataset)
{
((RVFDataset <L, F>)data).EnsureRealValues();
}
if (data.labelIndex.Size() != 2)
{
throw new Exception("LogisticClassifier is only for binary classification!");
}
IMinimizer <IDiffFunction> minim;
LogisticObjectiveFunction lof = null;
if (data is Dataset <object, object> )
{
lof = new LogisticObjectiveFunction(data.NumFeatureTypes(), data.GetDataArray(), data.GetLabelsArray(), new LogPrior(LogPrior.LogPriorType.Quadratic), dataWeights);
}
else
{
if (data is RVFDataset <object, object> )
{
lof = new LogisticObjectiveFunction(data.NumFeatureTypes(), data.GetDataArray(), data.GetValuesArray(), data.GetLabelsArray(), new LogPrior(LogPrior.LogPriorType.Quadratic), dataWeights);
}
}
minim = new QNMinimizer(lof);
weights = minim.Minimize(lof, 1e-4, new double[data.NumFeatureTypes()]);
featureIndex = data.featureIndex;
classes[0] = data.labelIndex.Get(0);
classes[1] = data.labelIndex.Get(1);
return(new LogisticClassifier <L, F>(weights, featureIndex, classes));
}
public BiasedLogConditionalObjectiveFunction(GeneralDataset <object, object> dataset, double[][] confusionMatrix, LogPrior prior)
: this(dataset.NumFeatures(), dataset.NumClasses(), dataset.GetDataArray(), dataset.GetLabelsArray(), confusionMatrix, prior)
{
}
public virtual void TrainWeightedData(GeneralDataset <L, F> data, float[] dataWeights)
{
//Use LogisticClassifierFactory to train instead.
if (data.labelIndex.Size() != 2)
{
throw new Exception("LogisticClassifier is only for binary classification!");
}
IMinimizer <IDiffFunction> minim;
LogisticObjectiveFunction lof = null;
if (data is Dataset <object, object> )
{
lof = new LogisticObjectiveFunction(data.NumFeatureTypes(), data.GetDataArray(), data.GetLabelsArray(), prior, dataWeights);
}
else
{
if (data is RVFDataset <object, object> )
{
lof = new LogisticObjectiveFunction(data.NumFeatureTypes(), data.GetDataArray(), data.GetValuesArray(), data.GetLabelsArray(), prior, dataWeights);
}
}
minim = new QNMinimizer(lof);
weights = minim.Minimize(lof, 1e-4, new double[data.NumFeatureTypes()]);
featureIndex = data.featureIndex;
classes[0] = data.labelIndex.Get(0);
classes[1] = data.labelIndex.Get(1);
}
// amount of add-k smoothing of evidence
// fudge to keep nonzero
protected internal override double[][] TrainWeights(GeneralDataset <L, F> data)
{
return(TrainWeights(data.GetDataArray(), data.GetLabelsArray()));
}