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 test_chi2(self):
nrows, ncols = 500, 5
X = np.random.randint(4, size=(nrows, ncols))
y = 10 + (-3 * X[:, 1] + X[:, 3]) // 2
domain = Domain.from_numpy(X, y)
domain = Domain(domain.attributes,
DiscreteVariable('c', values=np.unique(y)))
table = Table(domain, X, y)
data = preprocess.Discretize()(table)
scorer = Chi2()
sc = [scorer(data, a) for a in range(ncols)]
self.assertTrue(np.argmax(sc) == 1)
def test_discrete_scores_on_continuous_features(self):
c = self.iris.columns
for method in (Gini(), Chi2()):
d1 = SelectBestFeatures(method=method)(self.iris)
expected = \
(c.petal_length, c.petal_width, c.sepal_length, c.sepal_width)
self.assertSequenceEqual(d1.domain.attributes, expected)
scores = method(d1)
self.assertEqual(len(scores), 4)
score = method(d1, c.petal_length)
self.assertIsInstance(score, float)