semeval_regression.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('-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_regression(args.input, encoding='windows-1252')

    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', BinaryTreeRegressor(base_estimator=LinearSVC(C=args.c), verbose=False)),
    ])

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

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

    y = regressor.predict(test[2])

    with open('%sc%f-k%i-C.output' % (args.output, args.c, args.k), 'w', encoding='utf8') as outfile:
        for id_, topic, rate in zip(test[0], test[1], y):
            print(id_, topic, rate, sep='\t', file=outfile)