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)
评论列表
文章目录