Начиная со своего, вы можете считать слова или буквы.Верните их как диктовку.Их суммируют, сколько всего и сколько такого рода произошло & print:
import re
def tokenize(string):
return re.compile('\w+').findall(string)
from collections import Counter
def word_freq(string):
text = tokenize(string.lower())
c = Counter(text) # count the words
d = Counter(''.join(text)) # count all letters
return (dict(c),dict(d)) # return a tuple of counted words and letters
data = "This is a text, it contains dupes and more dupes and dupes of dupes and lkkk."
words, letters = word_freq(data) # count and get dicts with counts
sumWords = sum(words.values()) # sum total words
sumLetters = sum(letters.values()) # sum total letters
# calc / print probability of word
for w in words:
print("Probability of '{}': {}".format(w,words[w]/sumWords))
# calc / print probability of letter
for l in letters:
print("Probability of '{}': {}".format(l,letters[l]/sumLetters))
Чтобы изменить ваш диктат на вероятности, просто замените значения диктов на вычисленную вероятность:
# update the counts to propabilities:
for w in words:
words[w] = words[w]/sumWords
print ( words)
Вывод:
# words
Probability of 'this': 0.0625
Probability of 'is': 0.0625
Probability of 'a': 0.0625
Probability of 'text': 0.0625
Probability of 'it': 0.0625
Probability of 'contains': 0.0625
Probability of 'dupes': 0.25
Probability of 'and': 0.1875
Probability of 'more': 0.0625
Probability of 'of': 0.0625
Probability of 'lkkk': 0.0625
# letters
Probability of 't': 0.08333333333333333
Probability of 'h': 0.016666666666666666
Probability of 'i': 0.06666666666666667
# [....] snipped some for brevity
Probability of 'f': 0.016666666666666666
Probability of 'l': 0.016666666666666666
Probability of 'k': 0.05
После повторного вычисления значений words
:
{'this': 0.0625, 'is': 0.0625, 'a': 0.0625, 'text': 0.0625, 'it': 0.0625,
'contains': 0.0625, 'dupes': 0.25, 'and': 0.1875, 'more': 0.0625,
'of': 0.0625, 'lkkk': 0.0625}