semeval_regression_quantification.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_quantification_regression(args.input, encoding='windows-1252')

    texts = list()
    labels = list()
    topics = list()
    for topic in data:
        topic_texts, topic_labels = data[topic]
        texts.extend(topic_texts)
        labels.extend(topic_labels)
        topics.extend([topic for _ in topic_labels])

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

    quantifier = RegressionQuantifier(pipeline)

    quantifier.fit(texts, labels, topics)

    quantification = quantifier.predict(test_texts, test_topics)

    sorted_topics = list(quantification)
    sorted_topics.sort()
    with open('%sc%f-k%i-plain-E.output' % (args.output, args.c, args.k), 'w', encoding='utf8') as plainfile, \
            open('%sc%f-k%i-corrected_train-E.output' % (args.output, args.c, args.k), 'w',
                 encoding='utf8') as corrected_trainfile, \
            open('%sc%f-k%i-corrected_test-E.output' % (args.output, args.c, args.k), 'w',
                 encoding='utf8') as corrected_testfile:
        for topic in sorted_topics:
            plain, corrected_train, corrected_test = quantification[topic]
            print(topic, *plain, sep='\t', file=plainfile)
            print(topic, *corrected_train, sep='\t', file=corrected_trainfile)
            print(topic, *corrected_test, sep='\t', file=corrected_testfile)