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
92
93
94
95
96
97
|
# Test methods with long descriptive names can omit docstrings
# pylint: disable=missing-docstring
import functools
import os
import tempfile
import unittest
import numpy as np
from Orange.data.io import BasketReader
def with_file(s):
def fle_decorator(f, s=s):
@functools.wraps(f)
def decorated(self, s=s):
fle = tempfile.NamedTemporaryFile(delete=False)
fle.write(s.encode("utf-8"))
fle.close()
fname = fle.name
try:
return f(self, fname)
finally:
os.remove(fname)
return decorated
return fle_decorator
def read_basket(filename):
return BasketReader(filename).read()
class TestBasketReader(unittest.TestCase):
@with_file("""a=1,b=2,c=3""")
def test_read_variable_is_value_syntax(self, fname):
table = read_basket(fname)
self.assertEqual(len(table.domain.variables), 3)
self.assertEqual(["a", "b", "c"],
list(map(lambda x: x.name, table.domain.variables)))
np.testing.assert_almost_equal(table.X.todense(),
np.array([[1, 2, 3]]))
@with_file("""a,b,c,d,e""")
def test_read_variable_only_syntax(self, fname):
table = read_basket(fname)
self.assertEqual(len(table.domain.variables), 5)
np.testing.assert_almost_equal(table.X.todense(),
np.array([[1, 1, 1, 1, 1]]))
@with_file("""a=1, b=2, c=3""")
def test_handles_spaces_between_variables(self, fname):
table = read_basket(fname)
self.assertEqual(len(table.domain.variables), 3)
self.assertEqual(set(x for x in table[0]), {1, 2, 3})
@with_file("""a=1, b=2\na=1, b=4""")
def test_variables_can_be_listed_in_any_order(self, fname):
table = read_basket(fname)
self.assertEqual(len(table.domain.variables), 2)
np.testing.assert_almost_equal(table.X.todense(),
np.array([[1, 2], [1, 4]]))
@with_file("""a,b\nc,b,a""")
def test_variables_can_be_listed_in_any_order(self, fname):
table = read_basket(fname)
self.assertEqual(len(table.domain.variables), 3)
np.testing.assert_almost_equal(table.X.todense(),
np.array([[1, 1, 0], [1, 1, 1]]))
@with_file("""č,š,ž""")
def test_handles_unicode(self, fname):
table = read_basket(fname)
self.assertEqual(len(table.domain.variables), 3)
np.testing.assert_almost_equal(table.X.todense(),
np.array([[1, 1, 1]]))
@with_file("""a=4,"x"=1.0,"y"=2.0,b=5\n"x"=1.0""")
def test_handles_quote(self, fname):
table = read_basket(fname)
self.assertEqual(len(table.domain.variables), 4)
@with_file("""a,a,b\nb=2,b=3,c""")
def test_sums_duplicates(self, fname):
table = read_basket(fname)
np.testing.assert_array_equal(table.X.toarray(), [[2, 1, 0.],
[0, 5, 1]])
def test_data_name(self):
filename = os.path.join(os.path.dirname(__file__),
'datasets/iris_basket.basket')
self.assertEqual(read_basket(filename).name, 'iris_basket')
if __name__ == "__main__":
unittest.main()
|
