nlp/com.londogard.nlp.meachinelearning.vectorizer.count/CountVectorizer

CountVectorizer

public final class CountVectorizer<T extends Number> implements Vectorizer<T, Float>

Constructors

CountVectorizer

public CountVectorizer<T> CountVectorizer( PercentOrCount minDf, PercentOrCount maxDf, IntRange ngramRange)

Functions

public Unit fit(List<List<String>> input)

Does a fitTransform

public D2SparseArray fitTransform(List<List<String>> input)

public final PercentOrCount getMaxDf()

public final PercentOrCount getMinDf()

public final IntRange getNgramRange()

getVectorization

public final Map<String, Integer> getVectorization()

setVectorization

public final Unit setVectorization(Map<String, Integer> vectorization)

public D2SparseArray transform(List<List<String>> input)

Properties

private final PercentOrCount maxDf

private final PercentOrCount minDf

private final IntRange ngramRange

private Map<String, Integer> vectorization