word2vec_glove.py

def get_coefs(word,*arr): 
    return word, np.asarray(arr, dtype='float32')
  
embeddings_index = dict(get_coefs(*o.strip().split()) for o in open(EMBEDDING_FILE, encoding="utf8"))

all_embs = np.stack(embeddings_index.values())
emb_mean,emb_std = all_embs.mean(), all_embs.std()
emb_mean,emb_std
word_index = tokenizer.word_index

nb_words = min(max_features, len(word_index))
embedding_matrix = np.random.normal(emb_mean, emb_std, (nb_words, embed_size))

for word, i in word_index.items():
    if i >= max_features:
        continue
    embedding_vector = embeddings_index.get(word)
    if embedding_vector is not None: embedding_matrix[i] = embedding_vector