import nltk
nltk.download('punkt')
nltk.download('stopwords')
from nltk.tokenize import sent_tokenize, word_tokenize
from nltk.probability import FreqDist
import matplotlib.pyplot as plt
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer
from nltk.stem.wordnet import WordNetLemmatizer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity


documents = (genetic_algorithm_text, life_text, programming_language_text)
tfidf_vectorizer = TfidfVectorizer()
tfidf_matrix = tfidf_vectorizer.fit_transform(documents)

# Cos pomiedzy genetycznym a zyciem oraz programowaniem:
cos = cosine_similarity(tfidf_matrix[0:3], tfidf_matrix)