def test_select_1(self):
gini = Gini()
s = SelectBestFeatures(method=gini, k=1)
data2 = s(self.titanic)
best = max((gini(self.titanic, f), f)
for f in self.titanic.domain.attributes)[1]
self.assertEqual(data2.domain.attributes[0], best)
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_select_2(self):
gini = Gini()
# 100th percentile = selection of top1 attribute
sel1 = SelectBestFeatures(method=gini, k=1.0)
data2 = sel1(self.titanic)
best = max((gini(self.titanic, f), f)
for f in self.titanic.domain.attributes)[1]
self.assertEqual(data2.domain.attributes[0], best)
# no k and no threshold, select all attributes
sel2 = SelectBestFeatures(method=gini, k=0)
data2 = sel2(self.titanic)
self.assertEqual(len(data2.domain.attributes),
len(self.titanic.domain.attributes))
# 31% = selection of top (out of 3) attributes
sel3 = SelectBestFeatures(method=gini, k=0.31)
data2 = sel3(self.titanic)
self.assertEqual(len(data2.domain.attributes), 1)
# 35% = selection of top (out of 3) attributes
sel3 = SelectBestFeatures(method=gini, k=0.35)
data2 = sel3(self.titanic)
self.assertEqual(len(data2.domain.attributes), 1)
# 1% = select one (out of 3) attributes
sel3 = SelectBestFeatures(method=gini, k=0.01)
data2 = sel3(self.titanic)
self.assertEqual(len(data2.domain.attributes), 1)
# number of selected attrs should be relative to number of current input attrs
sel3 = SelectBestFeatures(method=gini, k=1.0)
data2 = sel3(self.heart_disease)
self.assertEqual(len(data2.domain.attributes), 13)
def test_select_1(self):
data = Table('titanic')
gini = Gini()
s = SelectBestFeatures(method=gini, k=1)
data2 = s(data)
best = max((gini(data, f), f) for f in data.domain.attributes)[1]
self.assertEqual(data2.domain.attributes[0], best)
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_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)
def test_gini(self):
scorer = Gini()
correct = [0.23786, 0.20855, 0.26235, 0.29300, 0.11946]
np.testing.assert_almost_equal([scorer(self.zoo, a) for a in range(5)],
correct,
decimal=5)
def test_gini(self):
scorer = Gini()
correct = [0.11893, 0.10427, 0.13117, 0.14650, 0.05973]
np.testing.assert_almost_equal([scorer(self.zoo, a) for a in range(5)],
correct,
decimal=5)