4d8cca40654deb641809bf8fb376afd9b1633d52,nlp_architect/data/cdc_resources/gen_scripts/create_word_embed_glove_dump.py,,load_glove_for_vocab,#Any#Any#,39

Before Change

    embeddings = np.asarray(embd, dtype=float)
    word_to_ix = {}
    for word in vocab:
        word_to_ix[word] = len(word_to_ix)

    return word_to_ix, embeddings


def glove_dump():

After Change

def load_glove_for_vocab(glove_filename, vocabulary):
    vocab = []
    embd = []
    with open(glove_filename) as glove_file:
        for line in glove_file:
            row = line.strip().split(" ")
            word = row[0]
            if word in vocabulary:
                vocab.append(word)
                embd.append(row[1:])
    logger.info("Loaded GloVe!")

    embeddings = np.asarray(embd, dtype=float)
    word_to_ix = {word: i for i, word in enumerate(vocab)}

Instances