truecasing_bleu.py

with open("path/to/yelp_academic_dataset_review_small.json") as f:
  reviews = f.readlines()
  
orig_reviews = [json.loads(r)['text'].replace('\n','') for r in reviews] 
lowercase_reviews = [r.lower() for r in orig_reviews] 
truecase_reviews = [truecasing(r) for r in lowercase_reviews] 
bleu_scores = [get_bleu([ro], [rt]) for ro, rt in zip(orig_reviews, truecase_reviews)] 

round(sum(bleu_scores)/len(bleu_scores), 2)