gistfile1.py

from sussex_nltk.corpus_readers import AmazonReviewCorpusReader

def format_data(reviews, 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 reviews]
    else:
        data = [(dict([(feature, True) for feature in feature_extraction_fn(review)]), label) for review in reviews]
    return data

#After you've split the data up as shown earlier, you can use the split data like this:
#Format the positive and negative separately
formatted_pos_training = format_data(pos_training_data, "pos") 
formatted_neg_training = format_data(neg_training_data, "neg") 
#Combine them
formatted_training_data = formatted_pos_training + formatted_neg_training

#Same again but for the testing data
formatted_pos_testing = format_data(pos_testing_data, "pos") 
formatted_neg_testing = format_data(neg_testing_data, "neg") 
#Combine them
formatted_testing_data = formatted_pos_testing + formatted_neg_testing