def test__collocation_document():
bigrams_and_trigrams = _collect_bigrams_and_trigrams(sample_data, min_freqs=[2,2])
assert(_collocation_document(sample_data[0][1],bigrams_and_trigrams) == [
u'frank_swank', u'tank', u'walked', u'sassy', u'unicorn', u'brony',
u'prancercise', u'class', u'daily', u'prancercise', u'tremendously',
u'popular', u'pastime', u'sassy_unicorns', u'retirees', u'alike'
])
assert(_collocation_document(sample_data[1][1],bigrams_and_trigrams) == [
u'prancercise', u'form', u'art', u'fitniss', u'originally',
u'invented', u'sassy_unicorns', u'recently', u'popularized',
u'retired', u'celebrities', u'frank_swank', u'tank'
])
def test__collocation_document():
bigrams_and_trigrams = _collect_bigrams_and_trigrams(sample_data,
min_freqs=[2, 2])
assert (_collocation_document(sample_data[0][1], bigrams_and_trigrams) == [
u'frank_swank', u'tank', u'walked', u'sassy', u'unicorn', u'brony',
u'prancercise', u'class', u'daily', u'prancercise', u'tremendously',
u'popular', u'pastime', u'sassy_unicorns', u'retirees', u'alike'
])
assert (_collocation_document(sample_data[1][1], bigrams_and_trigrams) == [
u'prancercise', u'form', u'art', u'fitniss', u'originally',
u'invented', u'sassy_unicorns', u'recently', u'popularized',
u'retired', u'celebrities', u'frank_swank', u'tank'
])
def test__collect_bigrams_and_trigrams():
bigrams_and_trigrams = _collect_bigrams_and_trigrams(sample_data, min_freqs=[2,2])
assert(bigrams_and_trigrams[0].pattern == u'(frank swank|swank tank|sassy unicorns)')
assert(bigrams_and_trigrams[1].pattern == u'(frank swank tank)')
def test__collect_bigrams_and_trigrams():
bigrams_and_trigrams = _collect_bigrams_and_trigrams(sample_data,
min_freqs=[2, 2])
assert (bigrams_and_trigrams[0].pattern ==
u'(frank swank|swank tank|sassy unicorns)')
assert (bigrams_and_trigrams[1].pattern == u'(frank swank tank)')