def load_w2v2(w2vdim, simple_run = True, base_path = '../data/emory_w2v/'):
if simple_run:
return {'a': np.array([np.float32(0.0)] * w2vdim)}
else:
model_path = base_path + 'w2v-%d.bin' % w2vdim
model = Word2Vec.load_word2vec_format(model_path, binary=True)
print("The vocabulary size is: " + str(len(model.vocab)))
return model
def load_w2v(w2vdim, simple_run=True, source="twitter"):
if simple_run:
return {'a': np.array([np.float32(0.0)] * w2vdim)}
else:
if source == "twitter":
model_path = '../data/emory_w2v/w2v-%d.bin' % w2vdim
elif source == "amazon":
model_path = '../data/emory_w2v/w2v-%d-%s.bin' % (w2vdim, source)
model = Word2Vec.load_word2vec_format(model_path, binary=True)
print("The vocabulary size is: " + str(len(model.vocab)))
return model
def load_w2v(w2vdim, simple_run=True, source="twitter"):
if simple_run:
return {'a': np.array([np.float32(0.0)] * w2vdim)}
else:
if source == "twitter":
model_path = '../data/emory_w2v/w2v-%d.bin' % w2vdim
elif source == "amazon":
model_path = '../data/emory_w2v/w2v-%d-%s.bin' % (w2vdim, source)
model = Word2Vec.load_word2vec_format(model_path, binary=True)
print("The vocabulary size is: " + str(len(model.vocab)))
return model
def load_w2v_withpath(model_path):
model = Word2Vec.load_word2vec_format(model_path, binary=True)
print("The vocabulary size is: " + str(len(model.vocab)))
return model
def load_w2v_withpath(model_path):
model = Word2Vec.load_word2vec_format(model_path, binary=True)
print("The vocabulary size is: " + str(len(model.vocab)))
return model