semeval_classification.py 文件源码

def main():
    sys.stdout = codecs.getwriter('utf8')(sys.stdout.buffer)
    parser = argparse.ArgumentParser(description='')
    parser.add_argument('-i', '--input', help='Input file', required=True)
    parser.add_argument('-b', '--binary',
                        help='Polarity classification, i.e., posivitive vs negative (default: posivitive/negative/neutral classification)',
                        action='store_true')
    parser.add_argument('-t', '--test', help='Test file', required=True)
    parser.add_argument('-o', '--output', help='Output filename prefix', required=True)
    parser.add_argument('-c', '--c', help='C value for SVM', type=float, default=1.0)
    parser.add_argument('-k', '--k', help='Number of features to keep', type=int, default=1000)
    args = parser.parse_args()

    data = read_semeval_classification(args.input, encoding='windows-1252')
    if args.binary:
        data = filter_polarity_classification(data)

    analyzer = get_rich_analyzer(word_ngrams=[2, 3], char_ngrams=[4])

    pipeline = Pipeline([
        ('vect', CountVectorizer(analyzer=analyzer)),
        ('tfidf', TfidfTransformer()),
        ('sel', SelectKBest(chi2, k=args.k)),
        ('clf', LinearSVC(C=args.c)),
    ])

    pipeline.fit(data[0], data[1])

    test = read_test_data(args.test, args.binary, encoding='windows-1252', topic=args.binary)

    classifier = pipeline.fit(data[0], data[1])

    y = classifier.predict(test[1])

    if args.binary:
        task = 'B'
    else:
        task = 'A'

    with open('%sc%f-k%i-%s.output' % (args.output, args.c, args.k, task), 'w', encoding='utf8') as outfile:
        if args.binary:
            for id_, topic, label in zip(test[0], test[2], y):
                print(id_, topic, label, sep='\t', file=outfile)
        else:
            for id_, label in zip(test[0], y):
                print(id_, label, sep='\t', file=outfile)