forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_pickle.py
232 lines (185 loc) · 8.09 KB
/
test_pickle.py
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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
# pylint: disable=E1101,E1103,W0232
""" manage legacy pickle tests """
import nose
import os
from distutils.version import LooseVersion
import pandas as pd
from pandas import Index
from pandas.compat import u, is_platform_little_endian
import pandas
import pandas.util.testing as tm
from pandas.tseries.offsets import Day, MonthEnd
class TestPickle():
"""
How to add pickle tests:
1. Install pandas version intended to output the pickle.
2. Execute "generate_legacy_storage_files.py" to create the pickle.
$ python generate_legacy_storage_files.py <output_dir> pickle
3. Move the created pickle to "data/legacy_pickle/<version>" directory.
NOTE: TestPickle can't be a subclass of tm.Testcase to use test generator.
http://stackoverflow.com/questions/6689537/
nose-test-generators-inside-class
"""
_multiprocess_can_split_ = True
def setUp(self):
from pandas.io.tests.generate_legacy_storage_files import (
create_pickle_data)
self.data = create_pickle_data()
self.path = u('__%s__.pickle' % tm.rands(10))
def compare_element(self, result, expected, typ, version=None):
if isinstance(expected, Index):
tm.assert_index_equal(expected, result)
return
if typ.startswith('sp_'):
comparator = getattr(tm, "assert_%s_equal" % typ)
comparator(result, expected, exact_indices=False)
else:
comparator = getattr(tm, "assert_%s_equal" %
typ, tm.assert_almost_equal)
comparator(result, expected)
def compare(self, vf, version):
# py3 compat when reading py2 pickle
try:
data = pandas.read_pickle(vf)
except (ValueError) as e:
if 'unsupported pickle protocol:' in str(e):
# trying to read a py3 pickle in py2
return
else:
raise
for typ, dv in data.items():
for dt, result in dv.items():
try:
expected = self.data[typ][dt]
except (KeyError):
if version in ('0.10.1', '0.11.0') and dt == 'reg':
break
else:
raise
# use a specific comparator
# if available
comparator = "compare_{typ}_{dt}".format(typ=typ, dt=dt)
comparator = getattr(self, comparator, self.compare_element)
comparator(result, expected, typ, version)
return data
def compare_series_ts(self, result, expected, typ, version):
# GH 7748
tm.assert_series_equal(result, expected)
tm.assert_equal(result.index.freq, expected.index.freq)
tm.assert_equal(result.index.freq.normalize, False)
tm.assert_series_equal(result > 0, expected > 0)
# GH 9291
freq = result.index.freq
tm.assert_equal(freq + Day(1), Day(2))
res = freq + pandas.Timedelta(hours=1)
tm.assert_equal(isinstance(res, pandas.Timedelta), True)
tm.assert_equal(res, pandas.Timedelta(days=1, hours=1))
res = freq + pandas.Timedelta(nanoseconds=1)
tm.assert_equal(isinstance(res, pandas.Timedelta), True)
tm.assert_equal(res, pandas.Timedelta(days=1, nanoseconds=1))
def compare_series_dt_tz(self, result, expected, typ, version):
# 8260
# dtype is object < 0.17.0
if LooseVersion(version) < '0.17.0':
expected = expected.astype(object)
tm.assert_series_equal(result, expected)
else:
tm.assert_series_equal(result, expected)
def compare_series_cat(self, result, expected, typ, version):
# Categorical dtype is added in 0.15.0
# ordered is changed in 0.16.0
if LooseVersion(version) < '0.15.0':
tm.assert_series_equal(result, expected, check_dtype=False,
check_categorical=False)
elif LooseVersion(version) < '0.16.0':
tm.assert_series_equal(result, expected, check_categorical=False)
else:
tm.assert_series_equal(result, expected)
def compare_frame_dt_mixed_tzs(self, result, expected, typ, version):
# 8260
# dtype is object < 0.17.0
if LooseVersion(version) < '0.17.0':
expected = expected.astype(object)
tm.assert_frame_equal(result, expected)
else:
tm.assert_frame_equal(result, expected)
def compare_frame_cat_onecol(self, result, expected, typ, version):
# Categorical dtype is added in 0.15.0
# ordered is changed in 0.16.0
if LooseVersion(version) < '0.15.0':
tm.assert_frame_equal(result, expected, check_dtype=False,
check_categorical=False)
elif LooseVersion(version) < '0.16.0':
tm.assert_frame_equal(result, expected, check_categorical=False)
else:
tm.assert_frame_equal(result, expected)
def compare_frame_cat_and_float(self, result, expected, typ, version):
self.compare_frame_cat_onecol(result, expected, typ, version)
def compare_index_period(self, result, expected, typ, version):
tm.assert_index_equal(result, expected)
tm.assertIsInstance(result.freq, MonthEnd)
tm.assert_equal(result.freq, MonthEnd())
tm.assert_equal(result.freqstr, 'M')
tm.assert_index_equal(result.shift(2), expected.shift(2))
def read_pickles(self, version):
if not is_platform_little_endian():
raise nose.SkipTest("known failure on non-little endian")
pth = tm.get_data_path('legacy_pickle/{0}'.format(str(version)))
n = 0
for f in os.listdir(pth):
vf = os.path.join(pth, f)
data = self.compare(vf, version)
if data is None:
continue
n += 1
assert n > 0, 'Pickle files are not tested'
def test_pickles(self):
pickle_path = tm.get_data_path('legacy_pickle')
n = 0
for v in os.listdir(pickle_path):
pth = os.path.join(pickle_path, v)
if os.path.isdir(pth):
yield self.read_pickles, v
n += 1
assert n > 0, 'Pickle files are not tested'
def test_round_trip_current(self):
try:
import cPickle as c_pickle
def c_pickler(obj, path):
with open(path, 'wb') as fh:
c_pickle.dump(obj, fh, protocol=-1)
def c_unpickler(path):
with open(path, 'rb') as fh:
fh.seek(0)
return c_pickle.load(fh)
except:
c_pickler = None
c_unpickler = None
import pickle as python_pickle
def python_pickler(obj, path):
with open(path, 'wb') as fh:
python_pickle.dump(obj, fh, protocol=-1)
def python_unpickler(path):
with open(path, 'rb') as fh:
fh.seek(0)
return python_pickle.load(fh)
for typ, dv in self.data.items():
for dt, expected in dv.items():
for writer in [pd.to_pickle, c_pickler, python_pickler]:
if writer is None:
continue
with tm.ensure_clean(self.path) as path:
# test writing with each pickler
writer(expected, path)
# test reading with each unpickler
result = pd.read_pickle(path)
self.compare_element(result, expected, typ)
if c_unpickler is not None:
result = c_unpickler(path)
self.compare_element(result, expected, typ)
result = python_unpickler(path)
self.compare_element(result, expected, typ)
if __name__ == '__main__':
nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
# '--with-coverage', '--cover-package=pandas.core'],
exit=False)