computer_ling

whatisit.py

from nltk import word_tokenize, sent_tokenize
PATH = "text_for_test.txt"
text = open(PATH, encoding="utf8").read()
words3, words1 = 0, 0
for word in word_tokenize(text):
    if len(word) == 3:
        words3 += 1
    elif len(word) == 1:
        words1 += 1


maxsent = ''
maxlt = 0
for sent in sent_tokenize(text):
    if sent.lower().count(" в ") > maxlt:
        maxlt = sent.lower().count(" в ")
        maxsent = sent

print("a)", words3 / words1)
print("b)", maxsent, "(" + str(maxlt) + ")")