def topic_dimen_reduce(words, word2vec):
dictionary, matrix = terms_analysis.get_words_matrix(words, word2vec)
pca = PCA(n_components=50)
pca_matrix = pca.fit_transform(matrix)
tsne = TSNE(n_components=2)
t_matrix = tsne.fit_transform(pca_matrix)
return dictionary, t_matrix
def w2v_dimen_reduce(word2vec_fn):
word2vec = models.Word2Vec.load(word2vec_fn)
vocab = word2vec.vocab.keys()
dictionary, matrix = terms_analysis.get_words_matrix(vocab, word2vec)
# t_matrix = tsne.tsne(matrix[:10000], 2, 50, 20.0)
# return t_matrix
del vocab
pca = PCA(n_components=50)
pca_matrix = pca.fit_transform(matrix[:5000])
del matrix
tsne = TSNE(n_components=2)
t_matrix = tsne.fit_transform(pca_matrix)
return dictionary[:5000], t_matrix
