def export_vocab(tweets, vocab_size, export=True):
words = []
for tweet in tweets:
words.extend(tweet)
vocab = Word2Vec.vocab_to_num(words, vocab_size)
if export:
np.save('./data/vocab.npy', vocab)
return vocab
def export_vocab(comments, categories, vocab_size, export=True):
words = []
for key in comments:
words.extend(list(itertools.chain.from_iterable(comments[key])))
for key in categories:
words.extend(list(itertools.chain.from_iterable(categories[key])))
vocab = Word2Vec.vocab_to_num(words, vocab_size)
if export:
with open("../resources/vocab.json", "w") as f:
json.dump(vocab, f, indent=2)
return vocab
