def test_freq_dist(self): with open('{}{}'.format(base_resources, 'lebowskiIpsum'), 'r')\ as f: text = f.read().decode('utf-8') #print(text, file=stderr) stopped = stop_words(text) freq_dist = freq_dist_count(stopped.split()) #print(pformat(freq_dist), file=stderr) self.assertGreater(len(freq_dist), 50)
def test_freq_dist_full(self): with open('{}{}'.format(base_resources, '2011-1-19raw.txt'), 'r')\ as f: text = f.read().decode('utf-8') assert type(text) == unicode stopped = stop_words(text) freq_dist = freq_dist_count(stopped.split()) #print(pformat(freq_dist), file=stderr) with open('{}{}'.format(target_out, '2011-1-19freq_dist_count'), 'w')\ as out_file: out_file.write(pformat(freq_dist))