forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_datetime_values.py
424 lines (348 loc) · 17.1 KB
/
test_datetime_values.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
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
# coding=utf-8
# pylint: disable-msg=E1101,W0612
from datetime import datetime, date
import numpy as np
import pandas as pd
from pandas.types.common import is_integer_dtype, is_list_like
from pandas import (Index, Series, DataFrame, bdate_range,
date_range, period_range, timedelta_range)
from pandas.tseries.period import PeriodIndex
from pandas.tseries.index import Timestamp, DatetimeIndex
from pandas.tseries.tdi import TimedeltaIndex
import pandas.core.common as com
from pandas.util.testing import assert_series_equal
import pandas.util.testing as tm
from .common import TestData
class TestSeriesDatetimeValues(TestData, tm.TestCase):
_multiprocess_can_split_ = True
def test_dt_namespace_accessor(self):
# GH 7207, 11128
# test .dt namespace accessor
ok_for_base = ['year', 'month', 'day', 'hour', 'minute', 'second',
'weekofyear', 'week', 'dayofweek', 'weekday',
'dayofyear', 'quarter', 'freq', 'days_in_month',
'daysinmonth', 'is_leap_year']
ok_for_period = ok_for_base + ['qyear', 'start_time', 'end_time']
ok_for_period_methods = ['strftime', 'to_timestamp', 'asfreq']
ok_for_dt = ok_for_base + ['date', 'time', 'microsecond', 'nanosecond',
'is_month_start', 'is_month_end',
'is_quarter_start', 'is_quarter_end',
'is_year_start', 'is_year_end', 'tz',
'weekday_name']
ok_for_dt_methods = ['to_period', 'to_pydatetime', 'tz_localize',
'tz_convert', 'normalize', 'strftime', 'round',
'floor', 'ceil', 'weekday_name']
ok_for_td = ['days', 'seconds', 'microseconds', 'nanoseconds']
ok_for_td_methods = ['components', 'to_pytimedelta', 'total_seconds',
'round', 'floor', 'ceil']
def get_expected(s, name):
result = getattr(Index(s._values), prop)
if isinstance(result, np.ndarray):
if is_integer_dtype(result):
result = result.astype('int64')
elif not is_list_like(result):
return result
return Series(result, index=s.index, name=s.name)
def compare(s, name):
a = getattr(s.dt, prop)
b = get_expected(s, prop)
if not (is_list_like(a) and is_list_like(b)):
self.assertEqual(a, b)
else:
tm.assert_series_equal(a, b)
# datetimeindex
cases = [Series(date_range('20130101', periods=5), name='xxx'),
Series(date_range('20130101', periods=5, freq='s'),
name='xxx'),
Series(date_range('20130101 00:00:00', periods=5, freq='ms'),
name='xxx')]
for s in cases:
for prop in ok_for_dt:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.tz_localize('US/Eastern')
exp_values = DatetimeIndex(s.values).tz_localize('US/Eastern')
expected = Series(exp_values, index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
tz_result = result.dt.tz
self.assertEqual(str(tz_result), 'US/Eastern')
freq_result = s.dt.freq
self.assertEqual(freq_result, DatetimeIndex(s.values,
freq='infer').freq)
# let's localize, then convert
result = s.dt.tz_localize('UTC').dt.tz_convert('US/Eastern')
exp_values = (DatetimeIndex(s.values).tz_localize('UTC')
.tz_convert('US/Eastern'))
expected = Series(exp_values, index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
# round
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.round('D')
expected = Series(pd.to_datetime(['2012-01-02', '2012-01-02',
'2012-01-01']), name='xxx')
tm.assert_series_equal(result, expected)
# round with tz
result = (s.dt.tz_localize('UTC')
.dt.tz_convert('US/Eastern')
.dt.round('D'))
exp_values = pd.to_datetime(['2012-01-01', '2012-01-01',
'2012-01-01']).tz_localize('US/Eastern')
expected = Series(exp_values, name='xxx')
tm.assert_series_equal(result, expected)
# floor
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.floor('D')
expected = Series(pd.to_datetime(['2012-01-01', '2012-01-01',
'2012-01-01']), name='xxx')
tm.assert_series_equal(result, expected)
# ceil
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.ceil('D')
expected = Series(pd.to_datetime(['2012-01-02', '2012-01-02',
'2012-01-02']), name='xxx')
tm.assert_series_equal(result, expected)
# datetimeindex with tz
s = Series(date_range('20130101', periods=5, tz='US/Eastern'),
name='xxx')
for prop in ok_for_dt:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.tz_convert('CET')
expected = Series(s._values.tz_convert('CET'),
index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
tz_result = result.dt.tz
self.assertEqual(str(tz_result), 'CET')
freq_result = s.dt.freq
self.assertEqual(freq_result, DatetimeIndex(s.values,
freq='infer').freq)
# timedeltaindex
cases = [Series(timedelta_range('1 day', periods=5),
index=list('abcde'), name='xxx'),
Series(timedelta_range('1 day 01:23:45', periods=5,
freq='s'), name='xxx'),
Series(timedelta_range('2 days 01:23:45.012345', periods=5,
freq='ms'), name='xxx')]
for s in cases:
for prop in ok_for_td:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_td_methods:
getattr(s.dt, prop)
result = s.dt.components
self.assertIsInstance(result, DataFrame)
tm.assert_index_equal(result.index, s.index)
result = s.dt.to_pytimedelta()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.total_seconds()
self.assertIsInstance(result, pd.Series)
self.assertTrue(result.dtype == 'float64')
freq_result = s.dt.freq
self.assertEqual(freq_result, TimedeltaIndex(s.values,
freq='infer').freq)
# both
index = date_range('20130101', periods=3, freq='D')
s = Series(date_range('20140204', periods=3, freq='s'),
index=index, name='xxx')
exp = Series(np.array([2014, 2014, 2014], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.year, exp)
exp = Series(np.array([2, 2, 2], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.month, exp)
exp = Series(np.array([0, 1, 2], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.second, exp)
exp = pd.Series([s[0]] * 3, index=index, name='xxx')
tm.assert_series_equal(s.dt.normalize(), exp)
# periodindex
cases = [Series(period_range('20130101', periods=5, freq='D'),
name='xxx')]
for s in cases:
for prop in ok_for_period:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_period_methods:
getattr(s.dt, prop)
freq_result = s.dt.freq
self.assertEqual(freq_result, PeriodIndex(s.values).freq)
# test limited display api
def get_dir(s):
results = [r for r in s.dt.__dir__() if not r.startswith('_')]
return list(sorted(set(results)))
s = Series(date_range('20130101', periods=5, freq='D'), name='xxx')
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_dt + ok_for_dt_methods))))
s = Series(period_range('20130101', periods=5,
freq='D', name='xxx').asobject)
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_period + ok_for_period_methods))))
# 11295
# ambiguous time error on the conversions
s = Series(pd.date_range('2015-01-01', '2016-01-01',
freq='T'), name='xxx')
s = s.dt.tz_localize('UTC').dt.tz_convert('America/Chicago')
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_dt + ok_for_dt_methods))))
exp_values = pd.date_range('2015-01-01', '2016-01-01', freq='T',
tz='UTC').tz_convert('America/Chicago')
expected = Series(exp_values, name='xxx')
tm.assert_series_equal(s, expected)
# no setting allowed
s = Series(date_range('20130101', periods=5, freq='D'), name='xxx')
with tm.assertRaisesRegexp(ValueError, "modifications"):
s.dt.hour = 5
# trying to set a copy
with pd.option_context('chained_assignment', 'raise'):
def f():
s.dt.hour[0] = 5
self.assertRaises(com.SettingWithCopyError, f)
def test_dt_accessor_no_new_attributes(self):
# https://github.com/pydata/pandas/issues/10673
s = Series(date_range('20130101', periods=5, freq='D'))
with tm.assertRaisesRegexp(AttributeError,
"You cannot add any new attribute"):
s.dt.xlabel = "a"
def test_strftime(self):
# GH 10086
s = Series(date_range('20130101', periods=5))
result = s.dt.strftime('%Y/%m/%d')
expected = Series(['2013/01/01', '2013/01/02', '2013/01/03',
'2013/01/04', '2013/01/05'])
tm.assert_series_equal(result, expected)
s = Series(date_range('2015-02-03 11:22:33.4567', periods=5))
result = s.dt.strftime('%Y/%m/%d %H-%M-%S')
expected = Series(['2015/02/03 11-22-33', '2015/02/04 11-22-33',
'2015/02/05 11-22-33', '2015/02/06 11-22-33',
'2015/02/07 11-22-33'])
tm.assert_series_equal(result, expected)
s = Series(period_range('20130101', periods=5))
result = s.dt.strftime('%Y/%m/%d')
expected = Series(['2013/01/01', '2013/01/02', '2013/01/03',
'2013/01/04', '2013/01/05'])
tm.assert_series_equal(result, expected)
s = Series(period_range(
'2015-02-03 11:22:33.4567', periods=5, freq='s'))
result = s.dt.strftime('%Y/%m/%d %H-%M-%S')
expected = Series(['2015/02/03 11-22-33', '2015/02/03 11-22-34',
'2015/02/03 11-22-35', '2015/02/03 11-22-36',
'2015/02/03 11-22-37'])
tm.assert_series_equal(result, expected)
s = Series(date_range('20130101', periods=5))
s.iloc[0] = pd.NaT
result = s.dt.strftime('%Y/%m/%d')
expected = Series(['NaT', '2013/01/02', '2013/01/03', '2013/01/04',
'2013/01/05'])
tm.assert_series_equal(result, expected)
datetime_index = date_range('20150301', periods=5)
result = datetime_index.strftime("%Y/%m/%d")
expected = np.array(['2015/03/01', '2015/03/02', '2015/03/03',
'2015/03/04', '2015/03/05'], dtype=np.object_)
# dtype may be S10 or U10 depending on python version
self.assert_numpy_array_equal(result, expected, check_dtype=False)
period_index = period_range('20150301', periods=5)
result = period_index.strftime("%Y/%m/%d")
expected = np.array(['2015/03/01', '2015/03/02', '2015/03/03',
'2015/03/04', '2015/03/05'], dtype='<U10')
self.assert_numpy_array_equal(result, expected)
s = Series([datetime(2013, 1, 1, 2, 32, 59), datetime(2013, 1, 2, 14,
32, 1)])
result = s.dt.strftime('%Y-%m-%d %H:%M:%S')
expected = Series(["2013-01-01 02:32:59", "2013-01-02 14:32:01"])
tm.assert_series_equal(result, expected)
s = Series(period_range('20130101', periods=4, freq='H'))
result = s.dt.strftime('%Y/%m/%d %H:%M:%S')
expected = Series(["2013/01/01 00:00:00", "2013/01/01 01:00:00",
"2013/01/01 02:00:00", "2013/01/01 03:00:00"])
s = Series(period_range('20130101', periods=4, freq='L'))
result = s.dt.strftime('%Y/%m/%d %H:%M:%S.%l')
expected = Series(["2013/01/01 00:00:00.000",
"2013/01/01 00:00:00.001",
"2013/01/01 00:00:00.002",
"2013/01/01 00:00:00.003"])
tm.assert_series_equal(result, expected)
def test_valid_dt_with_missing_values(self):
from datetime import date, time
# GH 8689
s = Series(date_range('20130101', periods=5, freq='D'))
s.iloc[2] = pd.NaT
for attr in ['microsecond', 'nanosecond', 'second', 'minute', 'hour',
'day']:
expected = getattr(s.dt, attr).copy()
expected.iloc[2] = np.nan
result = getattr(s.dt, attr)
tm.assert_series_equal(result, expected)
result = s.dt.date
expected = Series(
[date(2013, 1, 1), date(2013, 1, 2), np.nan, date(2013, 1, 4),
date(2013, 1, 5)], dtype='object')
tm.assert_series_equal(result, expected)
result = s.dt.time
expected = Series(
[time(0), time(0), np.nan, time(0), time(0)], dtype='object')
tm.assert_series_equal(result, expected)
def test_dt_accessor_api(self):
# GH 9322
from pandas.tseries.common import (CombinedDatetimelikeProperties,
DatetimeProperties)
self.assertIs(Series.dt, CombinedDatetimelikeProperties)
s = Series(date_range('2000-01-01', periods=3))
self.assertIsInstance(s.dt, DatetimeProperties)
for s in [Series(np.arange(5)), Series(list('abcde')),
Series(np.random.randn(5))]:
with tm.assertRaisesRegexp(AttributeError,
"only use .dt accessor"):
s.dt
self.assertFalse(hasattr(s, 'dt'))
def test_sub_of_datetime_from_TimeSeries(self):
from pandas.tseries.timedeltas import to_timedelta
from datetime import datetime
a = Timestamp(datetime(1993, 0o1, 0o7, 13, 30, 00))
b = datetime(1993, 6, 22, 13, 30)
a = Series([a])
result = to_timedelta(np.abs(a - b))
self.assertEqual(result.dtype, 'timedelta64[ns]')
def test_between(self):
s = Series(bdate_range('1/1/2000', periods=20).asobject)
s[::2] = np.nan
result = s[s.between(s[3], s[17])]
expected = s[3:18].dropna()
assert_series_equal(result, expected)
result = s[s.between(s[3], s[17], inclusive=False)]
expected = s[5:16].dropna()
assert_series_equal(result, expected)
def test_date_tz(self):
# GH11757
rng = pd.DatetimeIndex(['2014-04-04 23:56',
'2014-07-18 21:24',
'2015-11-22 22:14'], tz="US/Eastern")
s = Series(rng)
expected = Series([date(2014, 4, 4),
date(2014, 7, 18),
date(2015, 11, 22)])
assert_series_equal(s.dt.date, expected)
assert_series_equal(s.apply(lambda x: x.date()), expected)