def test_chi2(self):
nrows, ncols = 500, 5
X = np.random.randint(4, size=(nrows, ncols))
y = 10 + (-3 * X[:, 1] + X[:, 3]) // 2
data = preprocess.DiscretizeTable(Table(X, y))
scorer = score.Chi2()
sc = [scorer(a, data) for a in range(ncols)]
self.assertTrue(np.argmax(sc) == 1)
def test_wrong_class_type(self):
scorers = [score.Gini(), score.InfoGain(), score.GainRatio()]
for scorer in scorers:
with self.assertRaises(ValueError):
scorer(0, self.housing)
with self.assertRaises(ValueError):
score.Chi2(2, self.housing)
with self.assertRaises(ValueError):
score.ANOVA(2, self.housing)
score.UnivariateLinearRegression(2, self.housing)
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 = score.Chi2()
sc = [scorer(data, a) for a in range(ncols)]
self.assertTrue(np.argmax(sc) == 1)