Created
January 18, 2019 05:54
-
-
Save MLWhiz/b3e15c91d772b08e1e1b87de06665bf4 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def create_glove(word_index,embeddings_index): | |
emb_mean,emb_std = -0.005838499,0.48782197 | |
all_embs = np.stack(embeddings_index.values()) | |
embed_size = all_embs.shape[1] | |
nb_words = min(max_features, len(word_index)) | |
embedding_matrix = np.random.normal(emb_mean, emb_std, (nb_words, embed_size)) | |
count_found = nb_words | |
for word, i in tqdm(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 | |
else: | |
if word.islower(): | |
# try to get the embedding of word in titlecase if lowercase is not present | |
embedding_vector = embeddings_index.get(word.capitalize()) | |
if embedding_vector is not None: | |
embedding_matrix[i] = embedding_vector | |
else: | |
count_found-=1 | |
else: | |
count_found-=1 | |
print("Got embedding for ",count_found," words.") | |
return embedding_matrix |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment