def test_NaiveBayes(self):
table = SqlTable(
connection_params(),
"iris",
type_hints=Domain(
[],
DiscreteVariable("iris",
values=[
"Iris-setosa", "Iris-virginica",
"Iris-versicolor"
]),
),
)
table = preprocess.Discretize(table)
bayes = nb.NaiveBayesLearner()
clf = bayes(table)
# Single instance prediction
self.assertEqual(clf(table[0]), table[0].get_class())
# Table prediction
pred = clf(table)
actual = array([ins.get_class() for ins in table])
ca = pred == actual
ca = ca.sum() / len(ca)
self.assertGreater(ca, 0.95)
self.assertLess(ca, 1.0)
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.Discretize()(Table(X, y))
scorer = score.Chi2()
sc = [scorer(data, a) for a in range(ncols)]
self.assertTrue(np.argmax(sc) == 1)
def createinstance(params):
params = dict(params)
method = params.pop("method", DiscretizeEditor.EqualFreq)
method, defaults = DiscretizeEditor.Discretizers[method]
if method is None:
return None
resolved = dict(defaults)
# update only keys in defaults?
resolved.update(params)
return preprocess.Discretize(method(**params), remove_const=False)
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_NaiveBayes(self):
table = SqlTable(dict(host='localhost', database='test'), 'iris',
type_hints=Domain([], DiscreteVariable("iris",
values=['Iris-setosa', 'Iris-virginica',
'Iris-versicolor'])))
table = preprocess.Discretize(table)
bayes = nb.NaiveBayesLearner()
clf = bayes(table)
# Single instance prediction
self.assertEqual(clf(table[0]), table[0].get_class())
# Table prediction
pred = clf(table)
actual = array([ins.get_class() for ins in table])
ca = pred == actual
ca = ca.sum() / len(ca)
self.assertGreater(ca, 0.95)
self.assertLess(ca, 1.)
def test_NaiveBayes(self):
iris_v = ['Iris-setosa', 'Iris-virginica', 'Iris-versicolor']
table = SqlTable(self.conn,
self.iris,
type_hints=Domain([],
DiscreteVariable("iris",
values=iris_v)))
disc = preprocess.Discretize()
table = disc(table)
bayes = nb.NaiveBayesLearner()
clf = bayes(table)
# Single instance prediction
self.assertEqual(clf(table[0]), table[0].get_class())
# Table prediction
pred = clf(table)
actual = array([ins.get_class() for ins in table])
ca = pred == actual
ca = ca.sum() / len(ca)
self.assertGreater(ca, 0.95)
self.assertLess(ca, 1.)
