1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
|
# Test methods with long descriptive names can omit docstrings
# pylint: disable=missing-docstring
import unittest
import numpy as np
from Orange.data import Table
from Orange.classification import MajorityLearner
from Orange.tests import test_filename
class TestMajorityLearner(unittest.TestCase):
@classmethod
def setUpClass(cls):
cls.iris = Table('iris')
cls.learn = MajorityLearner()
def test_majority(self):
nrows = 1000
ncols = 10
x = np.random.randint(1, 4, (nrows, ncols))
y = np.random.randint(1, 4, (nrows, 1)) // 2
t = Table.from_numpy(None, x, y)
clf = self.learn(t)
x2 = np.random.randint(1, 4, (nrows, ncols))
y2 = clf(x2)
self.assertEqual(y2.all(), 1)
def test_weights(self):
nrows = 100
ncols = 10
x = np.random.randint(1, 5, (nrows, ncols))
y = np.array(70*[0] + 30*[1]).reshape((nrows, 1))
heavy_class = 1
w = (y == heavy_class) * 2 + 1
t = Table.from_numpy(None, x, y, W=w)
clf = self.learn(t)
y2 = clf(x)
self.assertEqual(y2.all(), heavy_class)
def test_empty(self):
clf = self.learn(self.iris[:0])
y = clf(self.iris[0], clf.Probs)
self.assertTrue(np.allclose(y, y.sum() / y.size))
def test_missing(self):
iris = Table('iris')
learn = MajorityLearner()
sub_table = iris[: len(iris) // 2: 2].copy()
with sub_table.unlocked():
for e in sub_table:
e.set_class("?")
clf = learn(iris)
y = clf(iris)
self.assertTrue((y == 2).all())
with iris.unlocked():
for e in iris:
e.set_class("?")
clf = learn(iris)
y = clf(iris)
self.assertEqual(y.all(), 1)
def test_continuous(self):
autompg = Table(test_filename('datasets/imports-85.tab'))
learn = MajorityLearner()
self.assertRaises(ValueError, learn, autompg)
def test_returns_random_class(self):
iris = self.iris
train = np.ones((150,), dtype='bool')
train[0] = False
majority = MajorityLearner()(iris[train])
pred1 = majority(iris[0])
self.assertIn(pred1, [1, 2])
for i in range(1, 50):
train[i] = train[50 + i] = train[100 + i] = False
majority = MajorityLearner()(iris[train])
pred2 = majority(iris[0])
self.assertIn(pred2, [1, 2])
if pred1 != pred2:
break
else:
self.fail("Majority always returns the same value.")
def test_supports_weights(self):
self.assertFalse(MajorityLearner().supports_weights)
|
