Compute N-Gram

ngram.py

#!/usr/bin/env python
# -*- coding: utf-8 -*- 

"""
Jednoduchá realizace n-gramu.
"""

def ngrams(words, n):
    return zip(*[words[i:] for i in range(n)])


def bigrams(words):
    return ngrams(words, 2)


def trigrams(words):
    return ngrams(words, 3)


def fourgrams(words):
    return ngrams(words, 4)


def fivegrams(words):
    return ngrams(words, 5)


if __name__ == '__main__':
    
    words = "The quick brown fox jumps over the lazy dog".split(" ")
    
    print("bigrams")
    for item in list(bigrams(words)): print(item)
    
    print("trigrams")
    for item in list(trigrams(words)): print(item)

    print("fourgrams")
    for item in list(fourgrams(words)): print(item)

    print("fivegrams")
    for item in list(fivegrams(words)): print(item)