gistfile1.py

from corpus_readers import AmazonReviewCorpusReader
arcr = AmazonReviewCorpusReader()

#Format some dvd data ready for the NB classifier
dvd_pos_formatted = format_data(arcr.positive().category("dvd").documents(),"pos")
dvd_neg_formatted = format_data(arcr.negative().category("dvd").documents(),"neg")
dvd_formatted = dvd_pos_formatted + dvd_neg_formatted

book_pos_formatted = format_data(arcr.positive().category("book").documents(),"pos")
book_neg_formatted = format_data(arcr.negative().category("book").documents(),"neg")
book_formatted = book_pos_formatted + book_neg_formatted

kitchen_pos_formatted = format_data(arcr.positive().category("kitchen").documents(),"pos")
kitchen_neg_formatted = format_data(arcr.negative().category("kitchen").documents(),"neg")
kitchen_formatted = kitchen_pos_formatted + kitchen_neg_formatted

electronics_pos_formatted = format_data(arcr.positive().category("electronics").documents(),"pos")
electronics_neg_formatted = format_data(arcr.negative().category("electronics").documents(),"neg")
electronics_formatted = electronics_pos_formatted + electronics_neg_formatted

#split the formatted data, in order to avoid testing on training data
train_electronics_formatted, test_electronics_formatted = split_data(electronics_formatted)

#three alternative combinations of source and target domain
source_1 = train_electronics_formatted
target_1 = test_electronics_formatted

source_2 = dvd_formatted + book_formatted + kitchen_formatted
target_2 = test_electronics_formatted

source_3 = dvd_formatted + book_formatted + kitchen_formatted + train_electronics_formatted
target_3 = test_electronics_formatted

#notice that in source_3 and target_3 we have electronics reviews. This is why the data had to be split.