sample=downsampling)
# To make the model memory efficient
model.init_sims(replace=True)
model.train(sentences, total_examples=1, epochs=150)
# Saving the model for later use. Can be loaded using Word2Vec.load()
model_name = gdrive+"glove1.h5"
model.save(model_name)
# model.wv.most_similar("dog")
# model.wv.wmdistance('hot', 'popular')
model = glove
numpy.dot(model['spain'], model['france'])/(numpy.linalg.norm(model['spain'])* numpy.linalg.norm(model['france']))
model.accuracy('/tmp/questions-words.txt')
D = np.zeros((len(docs), len(docs)))
for i in range(len(docs)):
for j in range(len(docs)):
if i == j:
continue # self-distance is 0.0
if i > j:
D[i, j] = D[j, i] # re-use earlier calc
D[i, j] = model.wmdistance(docs[i], docs[j])
sen =['sen1','sen2','point']
# model.accuracy(SEMEVAL_FOUR)
# sentences = readData(SEMEVAL_FOUR)
# model = Word2Vec(sentences, size=200)
model.__contains__("")
