Models:
Philip Bordner
philipB/
medical-entity-extraction
0
Downloads: 1
[349d16]: / code / data_preprocessing / embed_words.py

Download this file

19 lines (15 with data), 665 Bytes 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
import numpy as np

from gensim.models.keyedvectors import KeyedVectors



word2vec_path_bin = '/media/ramkabir/PC Data/ASU Data/Semester 3/BMNLP/Projects/Medical Data/embeddings/bio_embedding_extrinsic.bin'

word2vec_path_txt = '/media/ramkabir/PC Data/ASU Data/Semester 3/BMNLP/Projects/Medical Data/embeddings/bio_embedding_extrinsic.txt'



counter = 0

limit = 10



# model = KeyedVectors.load_word2vec_format(word2vec_path_bin, binary=True)

# model.save_word2vec_format(word2vec_path_txt, binary=False)



with open(word2vec_path_txt) as f:

    for line in f:

        if counter == limit:

            break

        else:

            print(line)

            counter += 1