tfidf.py

import math
from collections import Counter

def tf(word, doc):
  word_counter = Counter(doc.split())
  return word_counter(word) / sum(word_counter.values())
  
def idf(word, corpus):
  return math.log(len(corpus) / (1 + sum(1 for doc in corpus if word in doc)))
  
def tfidf(word, doc, corpus):
  return tf(word, doc) * idf(word, corpus)