def use_glove(sentences, index2word, model_file='glove_model/glove_50_iter2900.model',emb_dim=50):
glove.logger.setLevel(logging.INFO)
vocab = glove.build_vocab(sentences)
# cooccur = glove.build_cooccur(vocab, sentences, window_size=10)
# id2word = evaluate.make_id2word(vocab)
W = glove.load_model(model_file)
embeddings = []
for index,word in enumerate(index2word):
if word in vocab:
word_id = vocab[word][0]
vec = W[word_id]
else:
vec = np.zeros(shape=(W.shape[1],))
embeddings.append(vec)
embeddings = np.asarray(embeddings)
return embeddings
def train_glove(sentences, emb_dim=50):
glove.logger.setLevel(logging.INFO)
vocab = glove.build_vocab(sentences)
cooccur = glove.build_cooccur(vocab, sentences, window_size=10)
id2word = evaluate.make_id2word(vocab)
def evaluate_word(W):
words = ['good', 'movie', 'bad', 'worth', 'dog']
for word in words:
print evaluate.most_similar(W, vocab, id2word, word)
def save_per(W,i):
if i % 100 == 0 and i >= 100:
filename = "log/glove_%d_iter%d.model" % (emb_dim, i)
W = evaluate.merge_main_context(W)
glove.save_model(W, filename)
evaluate_word(W)
W = glove.train_glove(vocab, cooccur, vector_size=emb_dim, iterations=3000, iter_callback=save_per)
def use_glove(sentences,
index2word,
model_file='glove_model/glove_50_iter2900.model',
emb_dim=50):
glove.logger.setLevel(logging.INFO)
vocab = glove.build_vocab(sentences)
# cooccur = glove.build_cooccur(vocab, sentences, window_size=10)
# id2word = evaluate.make_id2word(vocab)
W = glove.load_model(model_file)
embeddings = []
for index, word in enumerate(index2word):
if word in vocab:
word_id = vocab[word][0]
vec = W[word_id]
else:
vec = np.zeros(shape=(W.shape[1], ))
embeddings.append(vec)
embeddings = np.asarray(embeddings)
return embeddings
def train_glove(sentences, emb_dim=50):
glove.logger.setLevel(logging.INFO)
vocab = glove.build_vocab(sentences)
cooccur = glove.build_cooccur(vocab, sentences, window_size=10)
id2word = evaluate.make_id2word(vocab)
def evaluate_word(W):
words = ['good', 'movie', 'bad', 'worth', 'dog']
for word in words:
print evaluate.most_similar(W, vocab, id2word, word)
def save_per(W, i):
if i % 100 == 0 and i >= 100:
filename = "log/glove_%d_iter%d.model" % (emb_dim, i)
W = evaluate.merge_main_context(W)
glove.save_model(W, filename)
evaluate_word(W)
W = glove.train_glove(vocab,
cooccur,
vector_size=emb_dim,
iterations=3000,
iter_callback=save_per)
test_corpus = ("""human interface computer
survey user computer system response time
eps user interface system
system human system eps
user response time
trees
graph trees
graph minors trees
graph minors survey
I like graph and stuff
I like trees and stuff
Sometimes I build a graph
Sometimes I build trees""").split("\n")
glove.logger.setLevel(logging.ERROR)
vocab = glove.build_vocab(test_corpus)
cooccur = glove.build_cooccur(vocab, test_corpus, window_size=10)
id2word = evaluate.make_id2word(vocab)
W = glove.train_glove(vocab, cooccur, vector_size=10, iterations=500)
# Merge and normalize word vectors
W = evaluate.merge_main_context(W)
def test_similarity():
similar = evaluate.most_similar(W, vocab, id2word, 'graph')
logging.debug(similar)
assert_equal('trees', similar[0])
with open(path) as f:
return f.read().split("\n")
print("Loading corpus and lexica")
#test_corpus = read_lines("../../datasets/snli_1.0/snli_sentenceA_72k_train.txt")
synonyms = read_lines("../../datasets/antonym_synonym/synonym_200.txt")
antonyms = read_lines("../../datasets/antonym_synonym/antonym_200.txt")
glove.logger.setLevel(logging.ERROR)
print("Building Vocab")
vocab = glove.build_vocab(test_corpus, synonyms, antonyms)
synonyms = glove.build_syncab(synonyms, vocab)
antonyms = glove.build_antcab(antonyms, vocab)
print("Building Cooccur")
cooccur = glove.build_cooccur(vocab, test_corpus, window_size=1)
id2word = evaluate.make_id2word(vocab)
print("Training vectors...")
W = glove.train_glove(vocab,
synonyms,
antonyms,
cooccur,
test_corpus = ("""human interface computer
survey user computer system response time
eps user interface system
system human system eps
user response time
trees
graph trees
graph minors trees
graph minors survey
I like graph and stuff
I like trees and stuff
Sometimes I build a graph
Sometimes I build trees""").split("\n")
glove.logger.setLevel(logging.ERROR)
vocab = glove.build_vocab(test_corpus)
cooccur = glove.build_cooccur(vocab, test_corpus, window_size=10)
id2word = evaluate.make_id2word(vocab)
W = glove.train_glove(vocab, cooccur, vector_size=10, iterations=500)
# Merge and normalize word vectors
W = evaluate.merge_main_context(W)
def test_similarity():
similar = evaluate.most_similar(W, vocab, id2word, 'graph')
logging.debug(similar)
assert_equal('trees', similar[0])