ch.epfl.bbp.uima.word2vec

Class Word2Vec

java.lang.Object

ch.epfl.bbp.uima.word2vec.Word2Vec

Direct Known Subclasses:

Word2VecMore

public class Word2Vec
extends Object

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Word2Vec.WordEntry

Field Summary

Fields

Modifier and Type	Field and Description
protected int	topNSize
protected int	vectorSize
protected int	vocabSize
protected HashMap<String,float[]>	vocabulary

Constructor Summary

Constructors

Constructor and Description
Word2Vec()

Method Summary

Methods

Modifier and Type	Method and Description
TreeSet<Word2Vec.WordEntry>	analogy(String query)
TreeSet<Word2Vec.WordEntry>	analogy(String word0, String word1, String word2)
Set<Word2Vec.WordEntry>	distance(String word)
protected static float	getFloat(byte[] b)
List<Integer>	getMostFrequentTopics(String word, float threshold)
int	getSize()
int	getTopNSize()
int	getVocabSize()
HashMap<String,float[]>	getWordMap()
float[]	getWordVector(String word)
protected void	insertTopN(String name, float score, List<Word2Vec.WordEntry> wordsEntrys)
static HashMap<String,Integer>	loadClassModel(String path)
Word2Vec	loadModel(String path)
protected static float	readFloat(InputStream is)
protected static String	readString(DataInputStream dis)
void	setTopNSize(int topNSize)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

vocabulary

protected HashMap<String,float[]> vocabulary

vocabSize

protected int vocabSize

vectorSize

protected int vectorSize

topNSize

protected int topNSize

Constructor Detail

Word2Vec

public Word2Vec()

Method Detail

loadModel

public Word2Vec loadModel(String path)
                   throws IOException

Throws:

IOException

distance

public Set<Word2Vec.WordEntry> distance(String word)

analogy

public TreeSet<Word2Vec.WordEntry> analogy(String word0,
                                  String word1,
                                  String word2)

analogy

public TreeSet<Word2Vec.WordEntry> analogy(String query)

insertTopN

protected void insertTopN(String name,
              float score,
              List<Word2Vec.WordEntry> wordsEntrys)

getWordVector

public float[] getWordVector(String word)

readFloat

protected static float readFloat(InputStream is)
                          throws IOException

Throws:

IOException

getFloat

protected static float getFloat(byte[] b)

readString

protected static String readString(DataInputStream dis)
                            throws IOException

Throws:

IOException

getTopNSize

public int getTopNSize()

setTopNSize

public void setTopNSize(int topNSize)

getWordMap

public HashMap<String,float[]> getWordMap()

getVocabSize

public int getVocabSize()

getSize

public int getSize()

getMostFrequentTopics

public List<Integer> getMostFrequentTopics(String word,
                                  float threshold)

loadClassModel

public static HashMap<String,Integer> loadClassModel(String path)
                                              throws IOException

Throws:

IOException