SE1_setup.py

import nltk
nltk.download('punkt')
from nltk.tokenize import word_tokenize
import numpy as np

SE2_sentences.py

sentences = ["I ate dinner.", 
       "We had a three-course meal.", 
       "Brad came to dinner with us.",
       "He loves fish tacos.",
       "In the end, we all felt like we ate too much.",
       "We all agreed; it was a magnificent evening."]

SE3_tokenize.py

# Tokenization of each document
tokenized_sent = []
for s in sentences:
    tokenized_sent.append(word_tokenize(s.lower()))
tokenized_sent

SE4_cosine.py

def cosine(u, v):
    return np.dot(u, v) / (np.linalg.norm(u) * np.linalg.norm(v))