public abstract class Builder extends Object
Modifier and Type | Field and Description |
---|---|
protected int |
batchSize |
protected VocabCache |
cache |
protected boolean |
cleanup |
protected DocumentIterator |
docIter |
protected InvertedIndex |
index |
protected List<String> |
labels |
protected int |
minWordFrequency |
protected double |
sample |
protected SentenceIterator |
sentenceIterator |
protected boolean |
stem |
protected List<String> |
stopWords |
protected TokenizerFactory |
tokenizerFactory |
Constructor and Description |
---|
Builder() |
Modifier and Type | Method and Description |
---|---|
Builder |
batchSize(int batchSize) |
abstract TextVectorizer |
build() |
Builder |
cache(VocabCache cache) |
Builder |
cleanup(boolean cleanup) |
Builder |
index(InvertedIndex index) |
Builder |
iterate(DocumentIterator docIter) |
Builder |
iterate(SentenceIterator sentenceIterator) |
Builder |
labels(List<String> labels) |
Builder |
minWords(int minWordFrequency) |
Builder |
sample(double sample) |
Builder |
stem(boolean stem) |
Builder |
stopWords(List<String> stopWords) |
Builder |
tokenize(TokenizerFactory tokenizerFactory) |
protected VocabCache cache
protected TokenizerFactory tokenizerFactory
protected int minWordFrequency
protected DocumentIterator docIter
protected SentenceIterator sentenceIterator
protected InvertedIndex index
protected int batchSize
protected double sample
protected boolean stem
protected boolean cleanup
public Builder cleanup(boolean cleanup)
public Builder stem(boolean stem)
public Builder sample(double sample)
public Builder batchSize(int batchSize)
public Builder index(InvertedIndex index)
public Builder cache(VocabCache cache)
public Builder tokenize(TokenizerFactory tokenizerFactory)
public Builder minWords(int minWordFrequency)
public Builder iterate(DocumentIterator docIter)
public Builder iterate(SentenceIterator sentenceIterator)
public abstract TextVectorizer build()
Copyright © 2015. All rights reserved.