forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathtest_internals.py
348 lines (292 loc) · 14 KB
/
test_internals.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
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
from datetime import datetime
import numpy as np
import pytest
import pandas as pd
from pandas import NaT, Series, Timestamp
from pandas.core.internals.blocks import IntBlock
import pandas.util.testing as tm
from pandas.util.testing import assert_series_equal
class TestSeriesInternals:
def test_convert_objects(self):
s = Series([1., 2, 3], index=['a', 'b', 'c'])
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_dates=False,
convert_numeric=True)
assert_series_equal(result, s)
# force numeric conversion
r = s.copy().astype('O')
r['a'] = '1'
with tm.assert_produces_warning(FutureWarning):
result = r.convert_objects(convert_dates=False,
convert_numeric=True)
assert_series_equal(result, s)
r = s.copy().astype('O')
r['a'] = '1.'
with tm.assert_produces_warning(FutureWarning):
result = r.convert_objects(convert_dates=False,
convert_numeric=True)
assert_series_equal(result, s)
r = s.copy().astype('O')
r['a'] = 'garbled'
expected = s.copy()
expected['a'] = np.nan
with tm.assert_produces_warning(FutureWarning):
result = r.convert_objects(convert_dates=False,
convert_numeric=True)
assert_series_equal(result, expected)
# GH 4119, not converting a mixed type (e.g.floats and object)
s = Series([1, 'na', 3, 4])
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_numeric=True)
expected = Series([1, np.nan, 3, 4])
assert_series_equal(result, expected)
s = Series([1, '', 3, 4])
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_numeric=True)
expected = Series([1, np.nan, 3, 4])
assert_series_equal(result, expected)
# dates
s = Series([datetime(2001, 1, 1, 0, 0), datetime(2001, 1, 2, 0, 0),
datetime(2001, 1, 3, 0, 0)])
s2 = Series([datetime(2001, 1, 1, 0, 0), datetime(2001, 1, 2, 0, 0),
datetime(2001, 1, 3, 0, 0), 'foo', 1.0, 1,
Timestamp('20010104'), '20010105'],
dtype='O')
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_dates=True,
convert_numeric=False)
expected = Series([Timestamp('20010101'), Timestamp('20010102'),
Timestamp('20010103')], dtype='M8[ns]')
assert_series_equal(result, expected)
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_dates='coerce',
convert_numeric=False)
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_dates='coerce',
convert_numeric=True)
assert_series_equal(result, expected)
expected = Series([Timestamp('20010101'), Timestamp('20010102'),
Timestamp('20010103'),
NaT, NaT, NaT, Timestamp('20010104'),
Timestamp('20010105')], dtype='M8[ns]')
with tm.assert_produces_warning(FutureWarning):
result = s2.convert_objects(convert_dates='coerce',
convert_numeric=False)
assert_series_equal(result, expected)
with tm.assert_produces_warning(FutureWarning):
result = s2.convert_objects(convert_dates='coerce',
convert_numeric=True)
assert_series_equal(result, expected)
# preserver all-nans (if convert_dates='coerce')
s = Series(['foo', 'bar', 1, 1.0], dtype='O')
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_dates='coerce',
convert_numeric=False)
expected = Series([NaT] * 2 + [Timestamp(1)] * 2)
assert_series_equal(result, expected)
# preserver if non-object
s = Series([1], dtype='float32')
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_dates='coerce',
convert_numeric=False)
assert_series_equal(result, s)
# r = s.copy()
# r[0] = np.nan
# result = r.convert_objects(convert_dates=True,convert_numeric=False)
# assert result.dtype == 'M8[ns]'
# dateutil parses some single letters into today's value as a date
for x in 'abcdefghijklmnopqrstuvwxyz':
s = Series([x])
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_dates='coerce')
assert_series_equal(result, s)
s = Series([x.upper()])
with tm.assert_produces_warning(FutureWarning):
result = s.convert_objects(convert_dates='coerce')
assert_series_equal(result, s)
def test_convert_objects_preserve_bool(self):
s = Series([1, True, 3, 5], dtype=object)
with tm.assert_produces_warning(FutureWarning):
r = s.convert_objects(convert_numeric=True)
e = Series([1, 1, 3, 5], dtype='i8')
tm.assert_series_equal(r, e)
def test_convert_objects_preserve_all_bool(self):
s = Series([False, True, False, False], dtype=object)
with tm.assert_produces_warning(FutureWarning):
r = s.convert_objects(convert_numeric=True)
e = Series([False, True, False, False], dtype=bool)
tm.assert_series_equal(r, e)
# GH 10265
def test_convert(self):
# Tests: All to nans, coerce, true
# Test coercion returns correct type
s = Series(['a', 'b', 'c'])
results = s._convert(datetime=True, coerce=True)
expected = Series([NaT] * 3)
assert_series_equal(results, expected)
results = s._convert(numeric=True, coerce=True)
expected = Series([np.nan] * 3)
assert_series_equal(results, expected)
expected = Series([NaT] * 3, dtype=np.dtype('m8[ns]'))
results = s._convert(timedelta=True, coerce=True)
assert_series_equal(results, expected)
dt = datetime(2001, 1, 1, 0, 0)
td = dt - datetime(2000, 1, 1, 0, 0)
# Test coercion with mixed types
s = Series(['a', '3.1415', dt, td])
results = s._convert(datetime=True, coerce=True)
expected = Series([NaT, NaT, dt, NaT])
assert_series_equal(results, expected)
results = s._convert(numeric=True, coerce=True)
expected = Series([np.nan, 3.1415, np.nan, np.nan])
assert_series_equal(results, expected)
results = s._convert(timedelta=True, coerce=True)
expected = Series([NaT, NaT, NaT, td],
dtype=np.dtype('m8[ns]'))
assert_series_equal(results, expected)
# Test standard conversion returns original
results = s._convert(datetime=True)
assert_series_equal(results, s)
results = s._convert(numeric=True)
expected = Series([np.nan, 3.1415, np.nan, np.nan])
assert_series_equal(results, expected)
results = s._convert(timedelta=True)
assert_series_equal(results, s)
# test pass-through and non-conversion when other types selected
s = Series(['1.0', '2.0', '3.0'])
results = s._convert(datetime=True, numeric=True, timedelta=True)
expected = Series([1.0, 2.0, 3.0])
assert_series_equal(results, expected)
results = s._convert(True, False, True)
assert_series_equal(results, s)
s = Series([datetime(2001, 1, 1, 0, 0), datetime(2001, 1, 1, 0, 0)],
dtype='O')
results = s._convert(datetime=True, numeric=True, timedelta=True)
expected = Series([datetime(2001, 1, 1, 0, 0), datetime(2001, 1, 1, 0,
0)])
assert_series_equal(results, expected)
results = s._convert(datetime=False, numeric=True, timedelta=True)
assert_series_equal(results, s)
td = datetime(2001, 1, 1, 0, 0) - datetime(2000, 1, 1, 0, 0)
s = Series([td, td], dtype='O')
results = s._convert(datetime=True, numeric=True, timedelta=True)
expected = Series([td, td])
assert_series_equal(results, expected)
results = s._convert(True, True, False)
assert_series_equal(results, s)
s = Series([1., 2, 3], index=['a', 'b', 'c'])
result = s._convert(numeric=True)
assert_series_equal(result, s)
# force numeric conversion
r = s.copy().astype('O')
r['a'] = '1'
result = r._convert(numeric=True)
assert_series_equal(result, s)
r = s.copy().astype('O')
r['a'] = '1.'
result = r._convert(numeric=True)
assert_series_equal(result, s)
r = s.copy().astype('O')
r['a'] = 'garbled'
result = r._convert(numeric=True)
expected = s.copy()
expected['a'] = np.nan
assert_series_equal(result, expected)
# GH 4119, not converting a mixed type (e.g.floats and object)
s = Series([1, 'na', 3, 4])
result = s._convert(datetime=True, numeric=True)
expected = Series([1, np.nan, 3, 4])
assert_series_equal(result, expected)
s = Series([1, '', 3, 4])
result = s._convert(datetime=True, numeric=True)
assert_series_equal(result, expected)
# dates
s = Series([datetime(2001, 1, 1, 0, 0), datetime(2001, 1, 2, 0, 0),
datetime(2001, 1, 3, 0, 0)])
s2 = Series([datetime(2001, 1, 1, 0, 0), datetime(2001, 1, 2, 0, 0),
datetime(2001, 1, 3, 0, 0), 'foo', 1.0, 1,
Timestamp('20010104'), '20010105'], dtype='O')
result = s._convert(datetime=True)
expected = Series([Timestamp('20010101'), Timestamp('20010102'),
Timestamp('20010103')], dtype='M8[ns]')
assert_series_equal(result, expected)
result = s._convert(datetime=True, coerce=True)
assert_series_equal(result, expected)
expected = Series([Timestamp('20010101'), Timestamp('20010102'),
Timestamp('20010103'), NaT, NaT, NaT,
Timestamp('20010104'), Timestamp('20010105')],
dtype='M8[ns]')
result = s2._convert(datetime=True, numeric=False, timedelta=False,
coerce=True)
assert_series_equal(result, expected)
result = s2._convert(datetime=True, coerce=True)
assert_series_equal(result, expected)
s = Series(['foo', 'bar', 1, 1.0], dtype='O')
result = s._convert(datetime=True, coerce=True)
expected = Series([NaT] * 2 + [Timestamp(1)] * 2)
assert_series_equal(result, expected)
# preserver if non-object
s = Series([1], dtype='float32')
result = s._convert(datetime=True, coerce=True)
assert_series_equal(result, s)
# r = s.copy()
# r[0] = np.nan
# result = r._convert(convert_dates=True,convert_numeric=False)
# assert result.dtype == 'M8[ns]'
# dateutil parses some single letters into today's value as a date
expected = Series([NaT])
for x in 'abcdefghijklmnopqrstuvwxyz':
s = Series([x])
result = s._convert(datetime=True, coerce=True)
assert_series_equal(result, expected)
s = Series([x.upper()])
result = s._convert(datetime=True, coerce=True)
assert_series_equal(result, expected)
def test_convert_no_arg_error(self):
s = Series(['1.0', '2'])
msg = r"At least one of datetime, numeric or timedelta must be True\."
with pytest.raises(ValueError, match=msg):
s._convert()
def test_convert_preserve_bool(self):
s = Series([1, True, 3, 5], dtype=object)
r = s._convert(datetime=True, numeric=True)
e = Series([1, 1, 3, 5], dtype='i8')
tm.assert_series_equal(r, e)
def test_convert_preserve_all_bool(self):
s = Series([False, True, False, False], dtype=object)
r = s._convert(datetime=True, numeric=True)
e = Series([False, True, False, False], dtype=bool)
tm.assert_series_equal(r, e)
def test_constructor_no_pandas_array(self):
ser = pd.Series([1, 2, 3])
result = pd.Series(ser.array)
tm.assert_series_equal(ser, result)
assert isinstance(result._data.blocks[0], IntBlock)
def test_astype_no_pandas_dtype(self):
# https://github.com/pandas-dev/pandas/pull/24866
ser = pd.Series([1, 2], dtype="int64")
# Don't have PandasDtype in the public API, so we use `.array.dtype`,
# which is a PandasDtype.
result = ser.astype(ser.array.dtype)
tm.assert_series_equal(result, ser)
def test_from_array(self):
result = pd.Series(pd.array(['1H', '2H'], dtype='timedelta64[ns]'))
assert result._data.blocks[0].is_extension is False
result = pd.Series(pd.array(['2015'], dtype='datetime64[ns]'))
assert result._data.blocks[0].is_extension is False
def test_from_list_dtype(self):
result = pd.Series(['1H', '2H'], dtype='timedelta64[ns]')
assert result._data.blocks[0].is_extension is False
result = pd.Series(['2015'], dtype='datetime64[ns]')
assert result._data.blocks[0].is_extension is False
def test_hasnans_unchached_for_series():
# GH#19700
idx = pd.Index([0, 1])
assert idx.hasnans is False
assert 'hasnans' in idx._cache
ser = idx.to_series()
assert ser.hasnans is False
assert not hasattr(ser, '_cache')
ser.iloc[-1] = np.nan
assert ser.hasnans is True
assert Series.hasnans.__doc__ == pd.Index.hasnans.__doc__