How to Compute a Mock BLEU Score with n-gram Overlap in Python

from collections import Counter

def bleu_score(reference, candidate, n=2):
    """
    Compute a simplified BLEU score with n-gram precision and brevity penalty.
    Mock demo using word-level n-grams.
    """
    ref_tokens = reference.lower().split()
    cand_tokens = candidate.lower().split()
    
    # Compute n-gram precision
    ref_ngrams = Counter(
        tuple(ref_tokens[i:i+n]) 
        for i in range(len(ref_tokens) - n + 1)
    )
    cand_ngrams = Counter(
        tuple(cand_tokens[i:i+n]) 
        for i in range(len(cand_tokens) - n + 1)
    )
    
    overlap = sum((cand_ngrams & ref_ngrams).values())
    total_cand_ngrams = max(sum(cand_ngrams.values()), 1)
    precision = overlap / total_cand_ngrams
    
    # Brevity penalty
    ref_len = len(ref_tokens)
    cand_len = len(cand_tokens)
    brevity_penalty = min(1.0, ref_len / cand_len) if cand_len > 0 else 0.0
    
    # Simplified BLEU (1-gram precision * brevity penalty)
    return precision * brevity_penalty

if __name__ == "__main__":
    reference_text = "the cat sat on the mat"
    candidate_text = "the cat sat on mat"
    print(f"BLEU score: {bleu_score(reference_text, candidate_text, n=2):.3f}")