public class WeightedDataset<L,F> extends Dataset<L,F>
Modifier and Type | Field and Description |
---|---|
protected float[] |
weights |
data, featureIndex, labelIndex, labels, size
Constructor and Description |
---|
WeightedDataset() |
WeightedDataset(Index<L> labelIndex,
int[] labels,
Index<F> featureIndex,
int[][] data,
int size,
float[] weights) |
WeightedDataset(int initSize) |
Modifier and Type | Method and Description |
---|---|
void |
add(java.util.Collection<F> features,
L label) |
void |
add(java.util.Collection<F> features,
L label,
float weight) |
void |
add(Datum<L,F> d) |
void |
add(Datum<L,F> d,
float weight) |
protected void |
ensureSize() |
float[] |
getFeatureCounts()
Get the total count (over all data instances) of each feature
|
float[] |
getWeights() |
void |
randomize(int randomSeed)
Randomizes the data array in place
Needs to be redefined here because we need to randomize the weights as well
|
add, add, addFeatureIndices, addFeatures, addFeatures, addLabel, addLabelIndex, applyFeatureCountThreshold, changeFeatureIndex, changeLabelIndex, getDatum, getFeatureCounter, getInformationGains, getL1NormalizedTFIDFDataset, getL1NormalizedTFIDFDatum, getRandomSubDataset, getRVFDatum, getValuesArray, initialize, printFullFeatureMatrix, printSparseFeatureMatrix, printSparseFeatureMatrix, printSVMLightFormat, readSVMLightFormat, readSVMLightFormat, readSVMLightFormat, readSVMLightFormat, selectFeatures, selectFeaturesBinaryInformationGain, split, split, summaryStatistics, svmLightLineToDatum, toString, toSummaryStatistics, toSummaryString, updateLabels
addAll, applyFeatureCountThreshold, applyFeatureMaxCountThreshold, clear, clear, featureIndex, getDataArray, getLabelsArray, iterator, labelIndex, labelIterator, makeSvmLabelMap, mapDataset, mapDataset, mapDatum, numClasses, numDatumsPerLabel, numFeatures, numFeatureTokens, numFeatureTypes, printSVMLightFormat, printSVMLightFormat, sampleDataset, size, trimData, trimLabels, trimToSize, trimToSize, trimToSize
public WeightedDataset(Index<L> labelIndex, int[] labels, Index<F> featureIndex, int[][] data, int size, float[] weights)
public WeightedDataset()
public WeightedDataset(int initSize)
public float[] getWeights()
public float[] getFeatureCounts()
GeneralDataset
getFeatureCounts
in class GeneralDataset<L,F>
protected void ensureSize()
ensureSize
in class Dataset<L,F>
public void randomize(int randomSeed)
randomize
in class GeneralDataset<L,F>