word_frequency.py

import nltk
nltk.download('punkt')
nltk.download('stopwords')
from nltk.tokenize import sent_tokenize,word_tokenize

sent_tokens = sent_tokenize(cleaned_data)
word_tokens = word_tokenize(cleaned_data)
word_frequency = {}
stopwords =  set(stopwords.words("english"))

for word in word_tokens:
    if word not in stopwords:
        if word not in word_frequency.keys():
            word_frequency[word]=1
        else:
            word_frequency[word] +=1
for word in word_frequency.keys():
    word_frequency[word] = (word_frequency[word]/maximum_frequency)