remove unnecessary files after extraction

Author: MartinXPN

preprocessing.py

@@ -4,6 +4,7 @@
 
 import numpy as np
 import json
+import os
 import argparse
 import cPickle as pickle
 
@@ -40,7 +41,8 @@ def word2vec(word2vec_path):
     if not path.exists(word2vec_path):
         glove_file_path = get_glove_file_path()
         print('Converting Glove to word2vec...', end='')
-        glove2word2vec(glove_file_path, word2vec_path)
+        glove2word2vec(glove_file_path, word2vec_path)  # Convert glove to word2vec
+        os.remove(glove_file_path)                      # Remove glove file and keep only word2vec
         print('Done')
 
     print('Reading word2vec data... ', end='')

utils.py

@@ -2,6 +2,7 @@
 from __future__ import print_function
 from __future__ import division
 
+import os
 from os import path
 from keras.utils.data_utils import get_file
 
@@ -33,10 +34,13 @@ def get_glove_file_path():
     origin = '{server}{version}.zip'.format(server=SERVER, version=VERSION)
     cache_dir = path.join(path.abspath(path.dirname(__file__)), 'data')
 
-    get_file('/tmp/glove.zip',
+    fname = '/tmp/glove.zip'
+    get_file(fname,
              origin=origin,
              cache_dir=cache_dir,
              cache_subdir='',
              extract=True)
 
+    # Remove unnecessary .zip file and keep only extracted .txt version
+    os.remove(fname)
     return path.join(cache_dir, VERSION) + '.txt'