def test_build_word_count_from_corpus_two_lines(self):
expected = [('of', 1), ('ebook', 1), ('carroll', 1), ('alice', 1),
('project', 1), ('gutenberg', 1), ('lewis', 1), ('in', 1),
('wonderland', 1), ('the', 1), ('by', 1)]
word_count = build_word_count_from_corpus(lines_max=2)
most_common = word_count.most_common()
self.assertEquals(most_common, expected)
def get_word_data():
"""
:return: dictionary that has word_count and fragment lookup
"""
word_count = build_word_count_from_corpus()
frequency_min = parameters['min_frequency_word_to_fragment']
word_count_smaller = {word: count for word, count in word_count.iteritems()
if count >= frequency_min}
fragment_lookup = word_list_to_fragment_lookup(word_count_smaller.keys())
word_data = {'word_count': word_count, 'fragment_lookup': fragment_lookup}
return word_data
def get_word_data():
"""
:return: dictionary that has word_count and fragment lookup
"""
word_count = build_word_count_from_corpus()
frequency_min = parameters['min_frequency_word_to_fragment']
word_count_smaller = {
word: count
for word, count in word_count.iteritems() if count >= frequency_min
}
fragment_lookup = word_list_to_fragment_lookup(word_count_smaller.keys())
word_data = {'word_count': word_count, 'fragment_lookup': fragment_lookup}
return word_data
def test_build_word_count_from_corpus_two_lines(self):
expected = [('of', 1),
('ebook', 1),
('carroll', 1),
('alice', 1),
('project', 1),
('gutenberg', 1),
('lewis', 1),
('in', 1),
('wonderland', 1),
('the', 1),
('by', 1)]
word_count = build_word_count_from_corpus(lines_max=2)
most_common = word_count.most_common()
self.assertEquals(most_common, expected)
