def token_link_text(text, distance=10):
'''Combine token frequency and token links together into a single JSON
format.'''
text = remove_punctuation(text)
token_list = stop_word_placeheld(text)
return link_op(token_list, distance=distance)
def test_freq_dist_dict_full(self):
with open('{}{}'.format(base_resources, '2011-1-19raw.txt'), 'r')\
as f:
text = f.read().decode('utf-8')
text = remove_punctuation(text)
stopped = stop_words(text)
ti = token_index(stopped)
#print(pformat(ti), file=stderr)
with open('{}{}'.format(target_out, '2011-1-19token_index'),\
'w') as out_file:
out_file.write(pformat(ti))
def test_freq_dist_dict_full(self):
with open('{}{}'.format(base_resources, '2011-1-19raw.txt'), 'r')\
as f:
text = f.read().decode('utf-8')
stopped = stop_words(text)
freq_dist = freq_dist_dict(stopped.split())
#print(pformat(freq_dist), file=stderr)
self.assertGreater(freq_dist[u'year'], 8)
self.assertLess(freq_dist[u'year'], 12)
text = remove_punctuation(text)
stopped = stop_words(text)
freq_dist = freq_dist_dict(stopped.split())
#print(pformat(freq_dist), file=stderr)
self.assertGreater(freq_dist[u'year'], 16)
with open('{}{}'.format(target_out, '2011-1-19freq_dist_dict'),\
'w') as out_file:
out_file.write(pformat(freq_dist))
def create_tokens(text):
text = remove_punctuation(text)
text = stop_word_placeheld(text)
return freq_dist_dict(text)
def test_punctuation_removal_unicode(self):
x = unicode(self.ick_str)
out = remove_punctuation(x, punct=self.punct)
self.assertEqual(out, unicode(self.good_str))