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)
def __init__(self, pipeline=None):
if pipeline is None:
self._pipeline = BinaryTreeRegressor(base_estimator=LinearSVC(C=100.0))
else:
self._pipeline = pipeline
class RegressionQuantifier(object):
def __init__(self, pipeline=None):
if pipeline is None:
self._pipeline = BinaryTreeRegressor(base_estimator=LinearSVC(C=100.0))
else:
self._pipeline = pipeline
def fit(self, X, y, groups):
self._true_global_prevalences = defaultdict(float)
self._values = list(set(y))
self._values.sort()
for rate in self._values:
self._true_global_prevalences[rate] = y.count(rate) / len(y)
self._estimated_global_prevalences = defaultdict(float)
for group in set(groups):
group_X = [atext for atext, agroup in zip(X, groups) if agroup == group]
notgroup_X = [atext for atext, agroup in zip(X, groups) if agroup != group]
notgroup_y = [alabel for alabel, agroup in zip(y, groups) if agroup != group]
pipclone = clone(self._pipeline)
model = pipclone.fit(notgroup_X, notgroup_y)
predictions = model.predict(group_X)
for rate in self._values:
self._estimated_global_prevalences[rate] += predictions.count(rate)
for rate in self._values:
self._estimated_global_prevalences[rate] /= len(y)
self._model = self._pipeline.fit(X, y)
def predict(self, X, groups):
predictions = self._model.predict(X)
quantifications = dict()
test_global_prevalences = defaultdict(float)
for rate in self._values:
test_global_prevalences[rate] = predictions.count(rate) / len(X)
for group in set(groups):
group_predictions = [prediction for prediction, agroup in zip(predictions, groups) if agroup == group]
simple_prevanlences = list()
corrected_prevalences = list()
test_corrected_prevalences = list()
for rate in self._values:
prevalence = group_predictions.count(rate) / len(group_predictions)
simple_prevanlences.append(prevalence)
if self._estimated_global_prevalences[rate] != 0:
corrected_prevalences.append(
prevalence * self._true_global_prevalences[rate] / self._estimated_global_prevalences[rate])
else:
corrected_prevalences.append(prevalence)
if test_global_prevalences[rate] != 0:
test_corrected_prevalences.append(
prevalence * self._true_global_prevalences[rate] / test_global_prevalences[rate])
else:
test_corrected_prevalences.append(prevalence)
cumulative = sum(corrected_prevalences)
corrected_prevalences = [corrected_prevalence / cumulative for corrected_prevalence in
corrected_prevalences]
cumulative = sum(test_corrected_prevalences)
test_corrected_prevalences = [test_corrected_prevalence / cumulative for test_corrected_prevalence in
test_corrected_prevalences]
quantifications[group] = (simple_prevanlences, corrected_prevalences, test_corrected_prevalences)
return quantifications
def __init__(self, pipeline=None):
if pipeline is None:
self._pipeline = BinaryTreeRegressor(base_estimator=LinearSVC(
C=100.0))
else:
self._pipeline = pipeline
class RegressionQuantifier(object):
def __init__(self, pipeline=None):
if pipeline is None:
self._pipeline = BinaryTreeRegressor(base_estimator=LinearSVC(
C=100.0))
else:
self._pipeline = pipeline
def fit(self, X, y, groups):
self._true_global_prevalences = defaultdict(float)
self._values = list(set(y))
self._values.sort()
for rate in self._values:
self._true_global_prevalences[rate] = y.count(rate) / len(y)
self._estimated_global_prevalences = defaultdict(float)
for group in set(groups):
group_X = [
atext for atext, agroup in zip(X, groups) if agroup == group
]
notgroup_X = [
atext for atext, agroup in zip(X, groups) if agroup != group
]
notgroup_y = [
alabel for alabel, agroup in zip(y, groups) if agroup != group
]
pipclone = clone(self._pipeline)
model = pipclone.fit(notgroup_X, notgroup_y)
predictions = model.predict(group_X)
for rate in self._values:
self._estimated_global_prevalences[rate] += predictions.count(
rate)
for rate in self._values:
self._estimated_global_prevalences[rate] /= len(y)
self._model = self._pipeline.fit(X, y)
def predict(self, X, groups):
predictions = self._model.predict(X)
quantifications = dict()
test_global_prevalences = defaultdict(float)
for rate in self._values:
test_global_prevalences[rate] = predictions.count(rate) / len(X)
for group in set(groups):
group_predictions = [
prediction for prediction, agroup in zip(predictions, groups)
if agroup == group
]
simple_prevanlences = list()
corrected_prevalences = list()
test_corrected_prevalences = list()
for rate in self._values:
prevalence = group_predictions.count(rate) / len(
group_predictions)
simple_prevanlences.append(prevalence)
if self._estimated_global_prevalences[rate] != 0:
corrected_prevalences.append(
prevalence * self._true_global_prevalences[rate] /
self._estimated_global_prevalences[rate])
else:
corrected_prevalences.append(prevalence)
if test_global_prevalences[rate] != 0:
test_corrected_prevalences.append(
prevalence * self._true_global_prevalences[rate] /
test_global_prevalences[rate])
else:
test_corrected_prevalences.append(prevalence)
cumulative = sum(corrected_prevalences)
corrected_prevalences = [
corrected_prevalence / cumulative
for corrected_prevalence in corrected_prevalences
]
cumulative = sum(test_corrected_prevalences)
test_corrected_prevalences = [
test_corrected_prevalence / cumulative
for test_corrected_prevalence in test_corrected_prevalences
]
quantifications[group] = (simple_prevanlences,
corrected_prevalences,
test_corrected_prevalences)
return quantifications
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)
