def test_class_distribution(self):
d = data.Table("zoo")
disc = distribution.class_distribution(d)
self.assertIsInstance(disc, np.ndarray)
self.assertIs(disc.variable, d.domain["type"])
self.assertEqual(disc.unknowns, 0)
np.testing.assert_array_equal(disc, [4.0, 20.0, 13.0, 8.0, 10.0, 41.0, 5.0])
def test_class_distribution(self):
d = data.Table("zoo")
disc = distribution.class_distribution(d)
self.assertIsInstance(disc, np.ndarray)
self.assertIs(disc.variable, d.domain["type"])
self.assertEqual(disc.unknowns, 0)
assert_dist_equal(disc, [4.0, 20.0, 13.0, 8.0, 10.0, 41.0, 5.0])
def test_indexing(self):
d = data.Table("zoo")
indamphibian = d.domain.class_var.to_val("amphibian")
disc = distribution.class_distribution(d)
self.assertEqual(len(disc), len(d.domain.class_var.values))
self.assertEqual(disc["mammal"], 41)
self.assertEqual(disc[indamphibian], 4)
disc["mammal"] = 100
self.assertEqual(disc[d.domain.class_var.to_val("mammal")], 100)
disc[indamphibian] = 33
self.assertEqual(disc["amphibian"], 33)
disc = distribution.class_distribution(d)
self.assertEqual(list(disc), self.freqs)
def test_indexing(self):
d = data.Table("zoo")
indamphibian = d.domain.class_var.to_val("amphibian")
disc = distribution.class_distribution(d)
self.assertEqual(len(disc), len(d.domain.class_var.values))
self.assertEqual(disc["mammal"], 41)
self.assertEqual(disc[indamphibian], 4)
disc["mammal"] = 100
self.assertEqual(disc[d.domain.class_var.to_val("mammal")], 100)
disc[indamphibian] = 33
self.assertEqual(disc["amphibian"], 33)
disc = distribution.class_distribution(d)
self.assertEqual(list(disc), self.freqs)
def test_multiple_target_variables(self):
d = data.Table.from_numpy(
data.Domain(
attributes=[data.ContinuousVariable("n1")],
class_vars=[
data.DiscreteVariable("c1", values=["r", "g", "b", "a"]),
data.DiscreteVariable("c2", values=["r", "g", "b", "a"]),
data.DiscreteVariable("c3", values=["r", "g", "b", "a"]),
],
),
X=np.array([range(5)]).T,
Y=np.array([[0, 1, 2, 3, 4], [0, 1, 2, 3, 4], [0, 1, 2, 3, 4]]).T,
)
dists = distribution.class_distribution(d)
self.assertEqual(len(dists), 3)
self.assertTrue(
all(isinstance(dist, distribution.Discrete) for dist in dists))
def test_multiple_target_variables(self):
d = data.Table.from_numpy(data.Domain(
attributes=[data.ContinuousVariable('n1')],
class_vars=[
data.DiscreteVariable('c1', values=('r', 'g', 'b', 'a')),
data.DiscreteVariable('c2', values=('r', 'g', 'b', 'a')),
data.DiscreteVariable('c3', values=('r', 'g', 'b', 'a')),
]),
X=np.array([range(5)]).T,
Y=np.array([
[0, 1, 2, 3, 4],
[0, 1, 2, 3, 4],
[0, 1, 2, 3, 4],
]).T)
dists = distribution.class_distribution(d)
self.assertEqual(len(dists), 3)
self.assertTrue(
all(isinstance(dist, distribution.Discrete) for dist in dists))
def test_multiple_target_variables(self):
d = data.Table.from_numpy(
data.Domain(
attributes=[data.ContinuousVariable('n1')],
class_vars=[
data.DiscreteVariable('c1', values=['r', 'g', 'b', 'a']),
data.DiscreteVariable('c2', values=['r', 'g', 'b', 'a']),
data.DiscreteVariable('c3', values=['r', 'g', 'b', 'a']),
]
),
X=np.array([range(5)]).T,
Y=np.array([
[0, 1, 2, 3, 4],
[0, 1, 2, 3, 4],
[0, 1, 2, 3, 4],
]).T
)
dists = distribution.class_distribution(d)
self.assertEqual(len(dists), 3)
self.assertTrue(all(isinstance(dist, distribution.Discrete) for dist in dists))
def test_from_table(self):
d = data.Table("zoo")
disc = distribution.Discrete(d, "type")
self.assertIsInstance(disc, np.ndarray)
self.assertIs(disc.variable, d.domain["type"])
self.assertEqual(disc.unknowns, 0)
assert_dist_equal(disc, self.freqs)
disc2 = distribution.Discrete(d, d.domain.class_var)
self.assertIsInstance(disc2, np.ndarray)
self.assertIs(disc2.variable, d.domain.class_var)
self.assertEqual(disc, disc2)
disc3 = distribution.Discrete(d, len(d.domain.attributes))
self.assertIsInstance(disc3, np.ndarray)
self.assertIs(disc3.variable, d.domain.class_var)
self.assertEqual(disc, disc3)
disc5 = distribution.class_distribution(d)
self.assertIsInstance(disc5, np.ndarray)
self.assertIs(disc5.variable, d.domain.class_var)
self.assertEqual(disc, disc5)
def test_from_table(self):
d = data.Table("zoo")
disc = distribution.Discrete(d, "type")
self.assertIsInstance(disc, np.ndarray)
self.assertIs(disc.variable, d.domain["type"])
self.assertEqual(disc.unknowns, 0)
np.testing.assert_array_equal(disc, self.freqs)
disc2 = distribution.Discrete(d, d.domain.class_var)
self.assertIsInstance(disc2, np.ndarray)
self.assertIs(disc2.variable, d.domain.class_var)
self.assertEqual(disc, disc2)
disc3 = distribution.Discrete(d, len(d.domain.attributes))
self.assertIsInstance(disc3, np.ndarray)
self.assertIs(disc3.variable, d.domain.class_var)
self.assertEqual(disc, disc3)
disc5 = distribution.class_distribution(d)
self.assertIsInstance(disc5, np.ndarray)
self.assertIs(disc5.variable, d.domain.class_var)
self.assertEqual(disc, disc5)
