wordcount.py

import re
from collections import Counter


def term_frequency_featurization(texts):
    for text in texts:
        words = re.findall(r'\w+', text.lower())
        yield dict(Counter(words))

def main():
    result = term_frequency_featurization(["He likes my dog", "Dog likes cat", "My cat   cat"])
    print(list(result))

if __name__ == '__main__':
    main()