Codepy - Python Online

import random
import math
import nltk
import collections
from nltk.corpus import stopwords
import numpy as np
from typing import List

file = open('shakespeare.txt', encoding="utf8")
nltk.download('stopwords')
# stopwords
stop_words = set(stopwords.words('english'))
# create data structure here.
wordcount = {}
total_count = 0
# Instantiate a dictionary, and for every word in the file, add to 
# the dictionary if it doesn't exist. If it does, increase the count.
# Iterating through each word to store in dictionary
WORDS = []
for word in file.read().lower().split():
    word = word.replace(".", "")
    word = word.replace(",", "")
    word = word.replace("\"", "")
    word = word.replace("“", "")
    word = word.replace("?", "")
    word = word.replace(";", "")
    word = word.replace("!", "")
    word = word.replace("-", "")
    word = word.replace("[", "")
    word = word.replace("]", "")
    word = word.replace(":", "")
    word = word.replace("(", "")
    word = word.replace(")", "")

# if we are seeing a word first time assign the value 1
    WORDS.append(word)
    if word not in stop_words:
        if word not in wordcount:
            wordcount[word] = 1
            # wordcount[word] = float(1/2)

# if the word already exists in dictionary increment the frequency of word
        else:
            wordcount[word] += 1
            total_count += 1

# This is to calculate the count of all words:
total_words = sum(wordcount.values())
# print(total_count)
# probab = wordcount[word] / total_words
# print(probab)
# after building your wordcount, you can then sort it and return the first
# n words.
d = collections.Counter(wordcount)
max_repeated_word = d.most_common(20)

counter_value = []
# This is used to get the probability of each word.
for times in range(4):
    # print(f"Round:{times}")
    for word1, count1 in d.most_common(20):
        count = 0
        for i in WORDS:

k = 1
            if i == word1:
                prob = random.randint(0, int(math.pow(8, k)))
                # print(prob)
                k += 1
                if prob == 0:
                    count += 1
        counter_value.append(count)
        # print(count, word1)
    times += 1
    print(f"Round:{times}")

# assert np.allclose(r1, r2)
    # print("\nMean: ", r1)
    # probability = (count1 / total_words)*100
    # print(word1 + ": " + str(f"count {count1}") + ": " + str(probability) + "\n")
    # print(word, ": ", count)

Share this code with others