/usr/lib/python2.7/dist-packages/pandas/tests/test_categorical.py is in python-pandas 0.13.1-2ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 | # pylint: disable=E1101,E1103,W0232
from datetime import datetime
from pandas.compat import range, lrange, u
import nose
import re
import numpy as np
from pandas.core.categorical import Categorical
from pandas.core.index import Index, Int64Index, MultiIndex
from pandas.core.frame import DataFrame
from pandas.util.testing import assert_almost_equal
import pandas.core.common as com
import pandas.util.testing as tm
class TestCategorical(tm.TestCase):
_multiprocess_can_split_ = True
def setUp(self):
self.factor = Categorical.from_array(['a', 'b', 'b', 'a',
'a', 'c', 'c', 'c'])
def test_getitem(self):
self.assertEqual(self.factor[0], 'a')
self.assertEqual(self.factor[-1], 'c')
subf = self.factor[[0, 1, 2]]
tm.assert_almost_equal(subf.labels, [0, 1, 1])
subf = self.factor[np.asarray(self.factor) == 'c']
tm.assert_almost_equal(subf.labels, [2, 2, 2])
def test_constructor_unsortable(self):
raise nose.SkipTest('skipping for now')
arr = np.array([1, 2, 3, datetime.now()], dtype='O')
# it works!
factor = Categorical.from_array(arr)
def test_factor_agg(self):
import pandas.core.frame as frame
arr = np.arange(len(self.factor))
f = np.sum
agged = frame.factor_agg(self.factor, arr, f)
labels = self.factor.labels
for i, idx in enumerate(self.factor.levels):
self.assertEqual(f(arr[labels == i]), agged[i])
def test_comparisons(self):
result = self.factor[self.factor == 'a']
expected = self.factor[np.asarray(self.factor) == 'a']
self.assert_(result.equals(expected))
result = self.factor[self.factor != 'a']
expected = self.factor[np.asarray(self.factor) != 'a']
self.assert_(result.equals(expected))
result = self.factor[self.factor < 'c']
expected = self.factor[np.asarray(self.factor) < 'c']
self.assert_(result.equals(expected))
result = self.factor[self.factor > 'a']
expected = self.factor[np.asarray(self.factor) > 'a']
self.assert_(result.equals(expected))
result = self.factor[self.factor >= 'b']
expected = self.factor[np.asarray(self.factor) >= 'b']
self.assert_(result.equals(expected))
result = self.factor[self.factor <= 'b']
expected = self.factor[np.asarray(self.factor) <= 'b']
self.assert_(result.equals(expected))
n = len(self.factor)
other = self.factor[np.random.permutation(n)]
result = self.factor == other
expected = np.asarray(self.factor) == np.asarray(other)
self.assert_(np.array_equal(result, expected))
result = self.factor == 'd'
expected = np.repeat(False, len(self.factor))
self.assert_(np.array_equal(result, expected))
def test_na_flags_int_levels(self):
# #1457
levels = lrange(10)
labels = np.random.randint(0, 10, 20)
labels[::5] = -1
cat = Categorical(labels, levels)
repr(cat)
self.assert_(np.array_equal(com.isnull(cat), labels == -1))
def test_levels_none(self):
factor = Categorical(['a', 'b', 'b', 'a',
'a', 'c', 'c', 'c'])
self.assert_(factor.equals(self.factor))
def test_describe(self):
# string type
desc = self.factor.describe()
expected = DataFrame.from_dict(dict(counts=[3, 2, 3],
freqs=[3/8., 2/8., 3/8.],
levels=['a', 'b', 'c'])
).set_index('levels')
tm.assert_frame_equal(desc, expected)
# check an integer one
desc = Categorical([1,2,3,1,2,3,3,2,1,1,1]).describe()
expected = DataFrame.from_dict(dict(counts=[5, 3, 3],
freqs=[5/11., 3/11., 3/11.],
levels=[1,2,3]
)
).set_index('levels')
tm.assert_frame_equal(desc, expected)
def test_print(self):
expected = [" a", " b", " b", " a", " a", " c", " c", " c",
"Levels (3): Index([a, b, c], dtype=object)"]
expected = "\n".join(expected)
# hack because array_repr changed in numpy > 1.6.x
actual = repr(self.factor)
pat = "Index\(\['a', 'b', 'c']"
sub = "Index([a, b, c]"
actual = re.sub(pat, sub, actual)
self.assertEquals(actual, expected)
def test_big_print(self):
factor = Categorical([0,1,2,0,1,2]*100, ['a', 'b', 'c'], name='cat')
expected = [" a", " b", " c", " a", " b", " c", " a", " b", " c",
" a", " b", " c", " a", "...", " c", " a", " b", " c",
" a", " b", " c", " a", " b", " c", " a", " b", " c",
"Levels (3): Index([a, b, c], dtype=object)",
"Name: cat, Length: 600" ]
expected = "\n".join(expected)
# hack because array_repr changed in numpy > 1.6.x
actual = repr(factor)
pat = "Index\(\['a', 'b', 'c']"
sub = "Index([a, b, c]"
actual = re.sub(pat, sub, actual)
self.assertEquals(actual, expected)
def test_empty_print(self):
factor = Categorical([], ["a","b","c"], name="cat")
expected = ("Categorical([], Name: cat, Levels (3): "
"Index([a, b, c], dtype=object)")
# hack because array_repr changed in numpy > 1.6.x
actual = repr(factor)
pat = "Index\(\['a', 'b', 'c']"
sub = "Index([a, b, c]"
actual = re.sub(pat, sub, actual)
self.assertEqual(actual, expected)
factor = Categorical([], ["a","b","c"])
expected = ("Categorical([], Levels (3): "
"Index([a, b, c], dtype=object)")
# hack because array_repr changed in numpy > 1.6.x
actual = repr(factor)
pat = "Index\(\['a', 'b', 'c']"
sub = "Index([a, b, c]"
actual = re.sub(pat, sub, actual)
self.assertEqual(actual, expected)
factor = Categorical([], [])
expected = ("Categorical([], Levels (0): "
"Index([], dtype=object)")
self.assertEqual(repr(factor), expected)
if __name__ == '__main__':
import nose
nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
# '--with-coverage', '--cover-package=pandas.core'],
exit=False)
|