forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathaccessors.py
330 lines (262 loc) · 10.7 KB
/
accessors.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
"""
datetimelike delegation
"""
import numpy as np
from pandas.core.dtypes.generic import ABCSeries
from pandas.core.dtypes.common import (
is_period_arraylike,
is_datetime_arraylike, is_integer_dtype,
is_datetime64_dtype, is_datetime64tz_dtype,
is_timedelta64_dtype, is_categorical_dtype,
is_list_like)
from pandas.core.accessor import PandasDelegate, delegate_names
from pandas.core.base import NoNewAttributesMixin, PandasObject
from pandas.core.indexes.datetimes import DatetimeIndex
from pandas.core.indexes.period import PeriodArray
from pandas.core.indexes.timedeltas import TimedeltaIndex
from pandas.core.algorithms import take_1d
class Properties(PandasDelegate, PandasObject, NoNewAttributesMixin):
def __init__(self, data, orig):
if not isinstance(data, ABCSeries):
raise TypeError("cannot convert an object of type {0} to a "
"datetimelike index".format(type(data)))
self._parent = data
self.orig = orig
self.name = getattr(data, 'name', None)
self.index = getattr(data, 'index', None)
self._freeze()
def _get_values(self):
data = self._parent
if is_datetime64_dtype(data.dtype):
return DatetimeIndex(data, copy=False, name=self.name)
elif is_datetime64tz_dtype(data.dtype):
return DatetimeIndex(data, copy=False, name=self.name)
elif is_timedelta64_dtype(data.dtype):
return TimedeltaIndex(data, copy=False, name=self.name)
else:
if is_period_arraylike(data):
# TODO: use to_period_array
return PeriodArray(data, copy=False)
if is_datetime_arraylike(data):
return DatetimeIndex(data, copy=False, name=self.name)
raise TypeError("cannot convert an object of type {0} to a "
"datetimelike index".format(type(data)))
def _delegate_property_get(self, name):
from pandas import Series
values = self._get_values()
result = getattr(values, name)
# maybe need to upcast (ints)
if isinstance(result, np.ndarray):
if is_integer_dtype(result):
result = result.astype('int64')
elif not is_list_like(result):
return result
result = np.asarray(result)
# blow up if we operate on categories
if self.orig is not None:
result = take_1d(result, self.orig.cat.codes)
index = self.orig.index
else:
index = self.index
# return the result as a Series, which is by definition a copy
result = Series(result, index=index, name=self.name)
# setting this object will show a SettingWithCopyWarning/Error
result._is_copy = ("modifications to a property of a datetimelike "
"object are not supported and are discarded. "
"Change values on the original.")
return result
def _delegate_property_set(self, name, value, *args, **kwargs):
raise ValueError("modifications to a property of a datetimelike "
"object are not supported. Change values on the "
"original.")
def _delegate_method(self, name, *args, **kwargs):
from pandas import Series
values = self._get_values()
method = getattr(values, name)
result = method(*args, **kwargs)
if not is_list_like(result):
return result
result = Series(result, index=self.index, name=self.name)
# setting this object will show a SettingWithCopyWarning/Error
result._is_copy = ("modifications to a method of a datetimelike "
"object are not supported and are discarded. "
"Change values on the original.")
return result
@delegate_names(delegate=DatetimeIndex,
accessors=DatetimeIndex._datetimelike_ops,
typ="property")
@delegate_names(delegate=DatetimeIndex,
accessors=DatetimeIndex._datetimelike_methods,
typ="method")
class DatetimeProperties(Properties):
"""
Accessor object for datetimelike properties of the Series values.
Examples
--------
>>> s.dt.hour
>>> s.dt.second
>>> s.dt.quarter
Returns a Series indexed like the original Series.
Raises TypeError if the Series does not contain datetimelike values.
"""
def to_pydatetime(self):
"""
Return the data as an array of native Python datetime objects
Timezone information is retained if present.
.. warning::
Python's datetime uses microsecond resolution, which is lower than
pandas (nanosecond). The values are truncated.
Returns
-------
numpy.ndarray
object dtype array containing native Python datetime objects.
See Also
--------
datetime.datetime : Standard library value for a datetime.
Examples
--------
>>> s = pd.Series(pd.date_range('20180310', periods=2))
>>> s
0 2018-03-10
1 2018-03-11
dtype: datetime64[ns]
>>> s.dt.to_pydatetime()
array([datetime.datetime(2018, 3, 10, 0, 0),
datetime.datetime(2018, 3, 11, 0, 0)], dtype=object)
pandas' nanosecond precision is truncated to microseconds.
>>> s = pd.Series(pd.date_range('20180310', periods=2, freq='ns'))
>>> s
0 2018-03-10 00:00:00.000000000
1 2018-03-10 00:00:00.000000001
dtype: datetime64[ns]
>>> s.dt.to_pydatetime()
array([datetime.datetime(2018, 3, 10, 0, 0),
datetime.datetime(2018, 3, 10, 0, 0)], dtype=object)
"""
return self._get_values().to_pydatetime()
@property
def freq(self):
return self._get_values().inferred_freq
@delegate_names(delegate=TimedeltaIndex,
accessors=TimedeltaIndex._datetimelike_ops,
typ="property")
@delegate_names(delegate=TimedeltaIndex,
accessors=TimedeltaIndex._datetimelike_methods,
typ="method")
class TimedeltaProperties(Properties):
"""
Accessor object for datetimelike properties of the Series values.
Examples
--------
>>> s.dt.hours
>>> s.dt.seconds
Returns a Series indexed like the original Series.
Raises TypeError if the Series does not contain datetimelike values.
"""
def to_pytimedelta(self):
"""
Return an array of native `datetime.timedelta` objects.
Python's standard `datetime` library uses a different representation
timedelta's. This method converts a Series of pandas Timedeltas
to `datetime.timedelta` format with the same length as the original
Series.
Returns
-------
a : numpy.ndarray
1D array containing data with `datetime.timedelta` type.
Examples
--------
>>> s = pd.Series(pd.to_timedelta(np.arange(5), unit='d'))
>>> s
0 0 days
1 1 days
2 2 days
3 3 days
4 4 days
dtype: timedelta64[ns]
>>> s.dt.to_pytimedelta()
array([datetime.timedelta(0), datetime.timedelta(1),
datetime.timedelta(2), datetime.timedelta(3),
datetime.timedelta(4)], dtype=object)
See Also
--------
datetime.timedelta
"""
return self._get_values().to_pytimedelta()
@property
def components(self):
"""
Return a Dataframe of the components of the Timedeltas.
Returns
-------
DataFrame
Examples
--------
>>> s = pd.Series(pd.to_timedelta(np.arange(5), unit='s'))
>>> s
0 00:00:00
1 00:00:01
2 00:00:02
3 00:00:03
4 00:00:04
dtype: timedelta64[ns]
>>> s.dt.components
days hours minutes seconds milliseconds microseconds nanoseconds
0 0 0 0 0 0 0 0
1 0 0 0 1 0 0 0
2 0 0 0 2 0 0 0
3 0 0 0 3 0 0 0
4 0 0 0 4 0 0 0
""" # noqa: E501
return self._get_values().components.set_index(self.index)
@property
def freq(self):
return self._get_values().inferred_freq
@delegate_names(delegate=PeriodArray,
accessors=PeriodArray._datetimelike_ops,
typ="property")
@delegate_names(delegate=PeriodArray,
accessors=PeriodArray._datetimelike_methods,
typ="method")
class PeriodProperties(Properties):
"""
Accessor object for datetimelike properties of the Series values.
Examples
--------
>>> s.dt.hour
>>> s.dt.second
>>> s.dt.quarter
Returns a Series indexed like the original Series.
Raises TypeError if the Series does not contain datetimelike values.
"""
class CombinedDatetimelikeProperties(DatetimeProperties, TimedeltaProperties):
def __new__(cls, data):
# CombinedDatetimelikeProperties isn't really instantiated. Instead
# we need to choose which parent (datetime or timedelta) is
# appropriate. Since we're checking the dtypes anyway, we'll just
# do all the validation here.
from pandas import Series
if not isinstance(data, Series):
raise TypeError("cannot convert an object of type {0} to a "
"datetimelike index".format(type(data)))
orig = data if is_categorical_dtype(data) else None
if orig is not None:
data = Series(orig.values.categories,
name=orig.name,
copy=False)
try:
if is_datetime64_dtype(data.dtype):
return DatetimeProperties(data, orig)
elif is_datetime64tz_dtype(data.dtype):
return DatetimeProperties(data, orig)
elif is_timedelta64_dtype(data.dtype):
return TimedeltaProperties(data, orig)
else:
if is_period_arraylike(data):
return PeriodProperties(data, orig)
if is_datetime_arraylike(data):
return DatetimeProperties(data, orig)
except Exception:
pass # we raise an attribute error anyway
raise AttributeError("Can only use .dt accessor with datetimelike "
"values")