read_corpus.py

def read_corpus(corpus_file, binary):
    """Read input document and return the textual reviews and the sentiment or genre."""
    documents = []
    labels = []
    with open(corpus_file, 'r', encoding='utf-8') as f:
        for line in f:
            tokens = line.strip().split()

            documents.append(tokens[3:])

            if binary:
                # 2-class problem: positive vs negative
                labels.append(tokens[1])
            else:
                # 6-class problem: books, camera, dvd, health, music, software
                labels.append(tokens[0])

    return documents, labels