def test_add_items():
"""test adding a n-gram"""
ngrams = NgramFrequencies()
assert "the" not in ngrams.unigrams_dic
ngrams.add_item("the", ngrams.unigrams_dic)
assert ngrams.unigrams_dic["the"] == 1
ngrams.add_item("the", ngrams.unigrams_dic)
assert ngrams.unigrams_dic["the"] == 2
assert ngrams.unigrams_dic["COUNT"] == 2
def main(filename):
tc = TextCleaner("corpse_bride.txt")
list_of_sentences = tc.read_file()
RANK = 10
unigram = NgramFrequencies(RANK)
bigram = NgramFrequencies(RANK)
trigram = NgramFrequencies(RANK)
for sentence in list_of_sentences:
words = sentence.split()
for i in range(len(words)):
unigram.add_item(words[i])
if i < len(words) - 1:
bigram.add_item(words[i] + "_" + words[i + 1])
if i < len(words) - 2:
trigram.add_item(words[i] + "_" + words[i + 1] + "_" +
words[i + 2])
print("Top 10 unigrams:")
print(unigram.top_n_freqs())
print("Top 10 bigrams:")
print(bigram.top_n_freqs())
print("Top 10 trigrams:")
print(trigram.top_n_freqs())
def test_ngram_frequencies():
nf = NgramFrequencies(2)
assert nf.add_item("He_is") == 1
assert nf.add_item("He_is") == 2
assert nf.add_item("He_is") == 3
assert nf.add_item("I_am") == 1
assert nf.add_item("I_am") == 2
assert nf.add_item("I_am") == 3
assert nf.add_item("I_am") == 4
assert nf.add_item("I_am") == 5
assert nf.add_item("I_am") == 6
assert nf.add_item("They_are") == 1
assert nf.frequency("They_are") == 0.1
assert nf.top_n_counts() == [("I_am", 6), ("He_is", 3)]
assert nf.top_n_freqs() == [("I_am", 0.6), ("He_is", 0.3)]
def test_add_item():
'''Test the add item method'''
ngram_freq = NgramFrequencies(1, '')
ngram_freq.add_item('ab')
assert ngram_freq.dic_ngram['ab'] == 1