def __call__(self, data):
method = self.method
# select default method according to the provided data
if method is None:
autoMethod = True
discr_ratio = (sum(a.is_discrete for a in data.domain.attributes) /
len(data.domain.attributes))
if data.domain.has_discrete_class:
if discr_ratio >= 0.5:
method = GainRatio()
else:
method = ANOVA()
else:
method = UnivariateLinearRegression()
features = data.domain.attributes
try:
scores = method(data)
except ValueError:
scores = self.score_only_nice_features(data, method)
best = sorted(zip(scores, features),
key=itemgetter(0),
reverse=self.decreasing)
if self.k:
best = best[:self.k]
if self.threshold:
pred = ((lambda x: x[0] >= self.threshold) if self.decreasing else
(lambda x: x[0] <= self.threshold))
best = takewhile(pred, best)
domain = Orange.data.Domain([f for s, f in best],
data.domain.class_vars, data.domain.metas)
return data.transform(domain)
def test_classless(self):
classless = Table(Domain(self.zoo.domain.attributes), self.zoo[:,
0:-1])
scorers = [Gini(), InfoGain(), GainRatio()]
for scorer in scorers:
with self.assertRaises(ValueError):
scorer(classless, 0)
def test_wrong_class_type(self):
scorers = [Gini(), InfoGain(), GainRatio()]
for scorer in scorers:
with self.assertRaises(ValueError):
scorer(self.housing, 0)
with self.assertRaises(ValueError):
Chi2()(self.housing, 0)
with self.assertRaises(ValueError):
ANOVA()(self.housing, 2)
UnivariateLinearRegression()(self.housing, 2)
def __call__(self, data):
method = self.method
# select default method according to the provided data
if method is None:
autoMethod = True
discr_ratio = (sum(a.is_discrete for a in data.domain.attributes) /
len(data.domain.attributes))
if data.domain.has_discrete_class:
if discr_ratio >= 0.5:
method = GainRatio()
else:
method = ANOVA()
else:
method = UnivariateLinearRegression()
if not isinstance(data.domain.class_var, method.class_type):
raise ValueError(
("Scoring method {} requires a class variable " +
"of type {}.").format((method if type(method) == type else
type(method)).__name__,
method.class_type.__name__))
features = data.domain.attributes
try:
scores = method(data)
except ValueError:
scores = self.score_only_nice_features(data, method)
best = sorted(zip(scores, features),
key=itemgetter(0),
reverse=self.decreasing)
if self.k:
best = best[:self.k]
if self.threshold:
pred = ((lambda x: x[0] >= self.threshold) if self.decreasing else
(lambda x: x[0] <= self.threshold))
best = takewhile(pred, best)
domain = Orange.data.Domain([f for s, f in best],
data.domain.class_vars, data.domain.metas)
return data.from_table(domain, data)
def test_gain_ratio(self):
scorer = GainRatio()
correct = [0.80351, 1.00000, 0.84754, 1.00000, 0.59376]
np.testing.assert_almost_equal([scorer(self.zoo, a) for a in range(5)],
correct,
decimal=5)