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_top_n_freqs():
'''Test the top n reqs method'''
ngram_freq = NgramFrequencies(1, '')
ngram_freq.dic_ngram["ab"] = 1
ngram_freq.dic_ngram["cd"] = 7
ngram_freq.dic_ngram["ef"] = 12
ngram_freq.total_count = 20
list_top_freq = ngram_freq.top_n_freqs(3)
assert list_top_freq[0][0] == "ef"
assert list_top_freq[1][0] == "cd"
assert list_top_freq[2][0] == "ab"
def main():
file_name = input('enter file name: ')
unigrams = NgramFrequencies(1, file_name)
bigrams = NgramFrequencies(2, file_name)
trigrams = NgramFrequencies(3, file_name)
print("\n Top 10 unigrams:")
unigrams.make_ngram()
print("", *unigrams.top_n_freqs(10),
sep="\n ")
print("\n Top 10 bigrams:")
bigrams.make_ngram()
print("", *bigrams.top_n_freqs(10),
sep="\n ")
print("\n Top 10 trigrams:")
trigrams.make_ngram()
print("", *trigrams.top_n_freqs(10), sep="\n ")
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)]