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))
Пример #2
0
def create_tokens(text):
    text = remove_punctuation(text)
    text = stop_word_placeheld(text)
    return freq_dist_dict(text)