gistfile1.py

from corpus_readers import AmazonReviewCorpusReader

def format_data(corpus_reader, label, feature_extraction_fn=None):
	
    if feature_extraction_fn is None: #If a feature extraction function is not provided, use simply the words of the review as features
        data = [(dict([(feature, True) for feature in review.words()]), label) for review in corpus_reader.reviews()]
    else:
        data = [(dict([(feature, True) for feature in feature_extraction_fn(review.raw())]), label) for review in corpus_reader.reviews()]
    return data

# Usage:

#A corpus reader pointing at dvd reviews
dvd_reader = AmazonReviewCorpusReader().category("dvd")

#Formatted positive and negative data
pos_data = format_data(dvd_reader.positive(), "pos") 
neg_data = format_data(dvd_reader.negative(), "neg")