/**
* Writes the word vectors to the given path. Note that this assumes an in memory cache
*
* @param vec the word2vec to write
* @param path the path to write
* @throws IOException
*/
public static void writeWordVectors(Word2Vec vec, String path) throws IOException {
BufferedWriter write = new BufferedWriter(new FileWriter(new File(path), false));
int words = 0;
for (String word : vec.vocab().words()) {
if (word == null) {
continue;
}
StringBuilder sb = new StringBuilder();
sb.append(word.replaceAll(" ", "_"));
sb.append(" ");
INDArray wordVector = vec.getWordVectorMatrix(word);
for (int j = 0; j < wordVector.length(); j++) {
sb.append(wordVector.getDouble(j));
if (j < wordVector.length() - 1) {
sb.append(" ");
}
}
sb.append("\n");
write.write(sb.toString());
words++;
}
log.info("Wrote " + words + " with size of " + vec.lookupTable().layerSize());
write.flush();
write.close();
}
/**
* Write the tsne format
*
* @param vec the word vectors to use for labeling
* @param tsne the tsne array to write
* @param csv the file to use
* @throws Exception
*/
public static void writeTsneFormat(Word2Vec vec, INDArray tsne, File csv) throws Exception {
BufferedWriter write = new BufferedWriter(new FileWriter(csv));
int words = 0;
InMemoryLookupCache l = (InMemoryLookupCache) vec.vocab();
for (String word : vec.vocab().words()) {
if (word == null) {
continue;
}
StringBuilder sb = new StringBuilder();
INDArray wordVector = tsne.getRow(l.wordFor(word).getIndex());
for (int j = 0; j < wordVector.length(); j++) {
sb.append(wordVector.getDouble(j));
if (j < wordVector.length() - 1) {
sb.append(",");
}
}
sb.append(",");
sb.append(word);
sb.append(" ");
sb.append("\n");
write.write(sb.toString());
}
log.info("Wrote " + words + " with size of " + vec.lookupTable().layerSize());
write.flush();
write.close();
}
public Builder setFeatureVectors(Word2Vec vec) {
vocabCache = vec.vocab();
return setFeatureVectors(vec.lookupTable());
}
