def test_ridge_scorer_feature(self):
data = Table('housing')
learner = RidgeRegressionLearner()
scores = learner.score_data(data)
for i, attr in enumerate(data.domain.attributes):
score = learner.score_data(data, attr)
self.assertEqual(score, scores[i])
def test_ridge_scorer_feature(self):
data = Table('housing')
learner = RidgeRegressionLearner()
scores = learner.score_data(data)
for i, attr in enumerate(data.domain.attributes):
score = learner.score_data(data, attr)
self.assertEqual(score, scores[i])
def test_deprecated_normalize(self):
""" When this test starts to fail:
- remove normalize=False kwargs from Orange.regression.
- remove _remove_deprecated_normalize and its calls
- remove this test
"""
import Orange # pylint: disable=import-outside-toplevel
self.assertLess(Orange.__version__, "3.33")
with self.assertWarns(OrangeDeprecationWarning):
RidgeRegressionLearner(normalize=True)
def test_scorer_feature(self):
learners = [LinearRegressionLearner(),
RidgeRegressionLearner(),
LassoRegressionLearner(alpha=0.01),
ElasticNetLearner(alpha=0.01)]
for learner in learners:
scores = learner.score_data(self.housing)
for i, attr in enumerate(self.housing.domain.attributes):
score = learner.score_data(self.housing, attr)
self.assertEqual(score, scores[i])
def test_scorer(self):
learners = [LinearRegressionLearner(),
RidgeRegressionLearner(),
LassoRegressionLearner(alpha=0.01),
ElasticNetLearner(alpha=0.01)]
for learner in learners:
scores = learner.score_data(self.housing)
self.assertEqual('LSTAT',
self.housing.domain.attributes[np.argmax(scores)].name)
self.assertEqual(len(scores), len(self.housing.domain.attributes))
def test_Regression(self):
ridge = RidgeRegressionLearner()
lasso = LassoRegressionLearner()
elastic = ElasticNetLearner()
elasticCV = ElasticNetCVLearner()
mean = MeanLearner()
learners = [ridge, lasso, elastic, elasticCV, mean]
res = CrossValidation(self.housing, learners, k=2)
rmse = RMSE(res)
for i in range(len(learners) - 1):
self.assertLess(rmse[i], rmse[-1])
def test_scorer(self):
data = Table('housing')
learners = [
LinearRegressionLearner(),
RidgeRegressionLearner(),
LassoRegressionLearner(alpha=0.01),
ElasticNetLearner(alpha=0.01)
]
for learner in learners:
scores = learner.score_data(data)
self.assertEqual('NOX',
data.domain.attributes[np.argmax(scores)].name)
self.assertEqual(len(scores), len(data.domain.attributes))
def __init__(self,
learners,
aggregate=RidgeRegressionLearner(),
k=5,
preprocessors=None):
super().__init__(learners, aggregate, k=k, preprocessors=preprocessors)
def test_ridge_scorer(self):
data = Table('housing')
learner = RidgeRegressionLearner()
scores = learner.score_data(data)
self.assertEqual(len(scores), len(data.domain.attributes))
def test_ridge_scorer(self):
data = Table('housing')
learner = RidgeRegressionLearner()
scores = learner.score_data(data)
self.assertEqual(len(scores), len(data.domain.attributes))
def __init__(self, learners, aggregate=RidgeRegressionLearner(), k=5):
super().__init__(learners=learners, aggregate=aggregate, k=k)