gistfile1.py

from sussex_nltk.corpus_readers import AmazonReviewCorpusReader

def get_training_testing(category, feature_extractor=None, split=0.7):
    '''
    Helper function. Splits data evenly across positive and negative, and then formats it
    ready for naive bayes. You can also optionally pass in your custom feature extractor 
    (see next section), and a custom split ratio.
    '''
    arcr = AmazonReviewCorpusReader()
    pos_train, pos_test = split_data(arcr.positive().category(category).documents(), split)
    neg_train, neg_test = split_data(arcr.negative().category(category).documents(), split)
    training_data = format_data(pos_train, "pos", feature_extractor) + format_data(neg_train, "neg", feature_extractor)
    testing_data  = format_data(pos_test, "pos", feature_extractor) + format_data(neg_test, "neg", feature_extractor)
    return testing_data, training_data

dvd_test, dvd_training   = get_training_testing("dvd")
book_test, book_training = get_training_testing("book")
kitchen_test, kitchen_training  = get_training_testing("kitchen")
electronics_test, electronics_training = get_training_testing("electronics") 

source_1 = electronics_training
target_1 = electronics_test

source_2 = dvd_training + book_training + kitchen_training
target_2 = electronics_test

source_3 = dvd_training + book_training + kitchen_training + electronics_training
target_3 = electronics_test