def train():
"""
Builds the SVM based on training data.
"""
features, labels = __init__.load_data('train')
vectorizer = text.CountVectorizer(decode_error='ignore',
stop_words='english')
transformer = text.TfidfTransformer()
classifier = linear_model.SGDClassifier(loss='hinge',
penalty='l2',
alpha=1e-3,
tol=1e-3,
random_state=42)
# Serializes the processing steps that would be required of the above.
text_clf = pipeline.Pipeline(
steps=[('vect', vectorizer), ('tfidf',
transformer), ('clf-sgdc', classifier)])
start = time.time()
text_clf.fit(features, labels)
print 'Training time:\t%1.4f seconds' % (time.time() - start)
__init__.evaluate(text_clf, features, labels)
return text_clf
def train():
"""Builds the random forest based on training data."""
features, labels = __init__.load_data('train')
vectorizer = text.CountVectorizer(decode_error='ignore',
stop_words='english')
transformer = text.TfidfTransformer()
classifier = ensemble.RandomForestClassifier(n_estimators=10)
text_clf = pipeline.Pipeline(
steps=[('vect', vectorizer), ('tfidf',
transformer), ('clf-rf', classifier)])
start = time.time()
text_clf.fit(features, labels)
print 'Training time:\t%1.4f seconds' % (time.time() - start)
__init__.evaluate(text_clf, features, labels)
return text_clf
def train():
"""
Builds the classifier based on training data.
"""
features, labels = __init__.load_data('train')
vectorizer = text.CountVectorizer(decode_error='ignore', stop_words='english')
transformer = text.TfidfTransformer()
classifier = linear_model.LogisticRegression(solver='lbfgs')
# Serializes the processing steps that would be required of the above.
text_clf = pipeline.Pipeline(steps=[('vect', vectorizer),
('tfidf', transformer),
('clf-lr', classifier)])
start = time.time()
text_clf.fit(features, labels)
print 'Training time:\t%1.4f seconds' % (time.time() - start)
__init__.evaluate(text_clf, features, labels)
return text_clf
def train():
"""
Builds the SVM based on training data.
"""
features, labels = __init__.load_data('train')
vectorizer = text.CountVectorizer(decode_error='ignore',
stop_words='english')
transformer = text.TfidfTransformer()
classifier = svm.SVR(kernel='sigmoid', gamma='scale')
# Serializes the processing steps that would be required of the above.
text_clf = pipeline.Pipeline(
steps=[('vect', vectorizer), ('tfidf',
transformer), ('clf-svr', classifier)])
start = time.time()
text_clf.fit(features, labels)
print 'Training time:\t%1.4f seconds' % (time.time() - start)
__init__.evaluate(text_clf, features, labels)
return text_clf
def test(model):
"""Tests the classifier based on test data."""
features, labels = __init__.load_data('test')
__init__.evaluate(model, features, labels)
def dev(model):
"""Tests the classifier based on dev data."""
features, labels = __init__.load_data('dev')
__init__.evaluate(model, features, labels)
def test(model):
"""Tests the random forest based on test data."""
features, labels = __init__.load_data('test')
__init__.evaluate(model, features, labels)
def dev(model):
"""Tests the random forest based on dev data."""
features, labels = __init__.load_data('dev')
__init__.evaluate(model, features, labels)
def test_str(self):
self.assertEqual(prose.evaluate(prose.read(STR)), prose.read(STR))
def test_var(self):
prose.variables[VAR] = prose.evaluate(prose.read(INT))
self.assertEqual(prose.evaluate(prose.read(VAR)), prose.read(INT))
del prose.variables[VAR]
def test_int(self):
self.assertEqual(prose.evaluate(prose.read(INT)), prose.read(INT))
def test_empty_list(self):
self.assertEqual(prose.evaluate(prose.read(())), prose.read(()))
