def main(we_file, w2i_file, n_files=50):
cc_matrix = "cc_matrix_%s.npy" % n_files
# hacky way of checking if we need to re-load the raw data or not
# remember, only the co-occurrence matrix is needed for training
if os.path.exists(cc_matrix):
with open(w2i_file) as f:
word2idx = json.load(f)
sentences = [] # dummy - we won't actually use it
else:
sentences, word2idx = get_wikipedia_data(n_files=n_files, n_vocab=2000)
with open(w2i_file, 'w') as f:
json.dump(word2idx, f)
V = len(word2idx)
model = Glove(80, V, 10)
# model.fit(sentences, cc_matrix=cc_matrix, epochs=20) # coordinate descent
model.fit(
sentences,
cc_matrix=cc_matrix,
learning_rate=3*10e-5,
reg=0.01,
epochs=2000,
gd=True,
use_theano=False
) # gradient descent
model.save(we_file)
def main(we_file, w2i_file, n_files=50):
cc_matrix = "cc_matrix_%s.npy" % n_files
# hacky way of checking if we need to re-load the raw data or not
# remember, only the co-occurrence matrix is needed for training
if os.path.exists(cc_matrix):
with open(w2i_file) as f:
word2idx = json.load(f)
sentences = [] # dummy - we won't actually use it
else:
sentences, word2idx = get_wikipedia_data(n_files=n_files, n_vocab=2000)
with open(w2i_file, 'w') as f:
json.dump(word2idx, f)
V = len(word2idx)
model = Glove(80, V, 10)
# model.fit(sentences, cc_matrix=cc_matrix, epochs=20) # coordinate descent
model.fit(sentences,
cc_matrix=cc_matrix,
learning_rate=3 * 10e-5,
reg=0.01,
epochs=2000,
gd=True,
use_theano=False) # gradient descent
model.save(we_file)
def main(we_file, w2i_file, use_brown=True, n_files=50):
if use_brown:
cc_matrix = "cc_matrix_brown.npy"
else:
cc_matrix = "cc_matrix_%s.npy" % n_files
# hacky way of checking if we need to re-load the raw data or not
# remember, only the co-occurrence matrix is needed for training
if os.path.exists(cc_matrix):
with open(w2i_file) as f:
word2idx = json.load(f)
sentences = [] # dummy - we won't actually use it
else:
if use_brown:
keep_words = set([
'king', 'man', 'woman',
'france', 'paris', 'london', 'rome', 'italy', 'britain', 'england',
'french', 'english', 'japan', 'japanese', 'chinese', 'italian',
'australia', 'australian', 'december', 'november', 'june',
'january', 'february', 'march', 'april', 'may', 'july', 'august',
'september', 'october',
])
sentences, word2idx = get_sentences_with_word2idx_limit_vocab(n_vocab=5000, keep_words=keep_words)
else:
sentences, word2idx = get_wikipedia_data(n_files=n_files, n_vocab=2000)
with open(w2i_file, 'w') as f:
json.dump(word2idx, f)
V = len(word2idx)
def main(we_file, w2i_file, use_brown=True, n_files=50):
if use_brown:
cc_matrix = "cc_matrix_brown.npy"
else:
cc_matrix = "cc_matrix_%s.npy" % n_files
# hacky way of checking if we need to re-load the raw data or not
# remember, only the co-occurrence matrix is needed for training
if os.path.exists(cc_matrix):
with open(w2i_file) as f:
word2idx = json.load(f)
sentences = [] # dummy - we won't actually use it
else:
if use_brown:
keep_words = set([
'king', 'man', 'woman',
'france', 'paris', 'london', 'rome', 'italy', 'britain', 'england',
'french', 'english', 'japan', 'japanese', 'chinese', 'italian',
'australia', 'australian', 'december', 'november', 'june',
'january', 'february', 'march', 'april', 'may', 'july', 'august',
'september', 'october',
])
sentences, word2idx = get_sentences_with_word2idx_limit_vocab(n_vocab=5000, keep_words=keep_words)
else:
sentences, word2idx = get_wikipedia_data(n_files=n_files, n_vocab=2000)
with open(w2i_file, 'w') as f:
json.dump(word2idx, f)
V = len(word2idx)
model = Glove(80, V, 10)
# model.fit(sentences, cc_matrix=cc_matrix, epochs=20) # ALS
model.fit(
sentences,
cc_matrix=cc_matrix,
learning_rate=3*10e-5,
reg=0.01,
epochs=500,
gd=True,
use_theano=False,
use_tensorflow=True,
)
model.save(we_file)
def main(we_file, w2i_file, n_files=50):
cc_matrix = 'cc_matrix_%s.npy' % n_files
if os.path.exists(cc_matrix):
with open(w2i_file) as f:
word2idx = json.load(f)
sentences = []
else:
sentences, word2idx = get_wikipedia_data(n_files=n_files, n_vocab=2000)
with open(w2i_file) as f:
json.dump(word2idx, f)
V = len(word2idx)
model = Glove(80, V, 10)
model.fit(sentences=sentences,
cc_matrix=cc_matrix,
learning_rate=3 * 10e-5,
reg=0.01,
epochs=2000,
gd=True,
use_theano=False)
model.save(we_file)
