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
| """
| masked_reductions.py is for reduction algorithms using a mask-based approach
| for missing values.
| """
| from __future__ import annotations
|
| from typing import Callable
| import warnings
|
| import numpy as np
|
| from pandas._libs import missing as libmissing
| from pandas._typing import (
| AxisInt,
| npt,
| )
|
| from pandas.core.nanops import check_below_min_count
|
|
| def _reductions(
| func: Callable,
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| min_count: int = 0,
| axis: AxisInt | None = None,
| **kwargs,
| ):
| """
| Sum, mean or product for 1D masked array.
|
| Parameters
| ----------
| func : np.sum or np.prod
| values : np.ndarray
| Numpy array with the values (can be of any dtype that support the
| operation).
| mask : np.ndarray[bool]
| Boolean numpy array (True values indicate missing values).
| skipna : bool, default True
| Whether to skip NA.
| min_count : int, default 0
| The required number of valid values to perform the operation. If fewer than
| ``min_count`` non-NA values are present the result will be NA.
| axis : int, optional, default None
| """
| if not skipna:
| if mask.any(axis=axis) or check_below_min_count(values.shape, None, min_count):
| return libmissing.NA
| else:
| return func(values, axis=axis, **kwargs)
| else:
| if check_below_min_count(values.shape, mask, min_count) and (
| axis is None or values.ndim == 1
| ):
| return libmissing.NA
|
| return func(values, where=~mask, axis=axis, **kwargs)
|
|
| def sum(
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| min_count: int = 0,
| axis: AxisInt | None = None,
| ):
| return _reductions(
| np.sum, values=values, mask=mask, skipna=skipna, min_count=min_count, axis=axis
| )
|
|
| def prod(
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| min_count: int = 0,
| axis: AxisInt | None = None,
| ):
| return _reductions(
| np.prod, values=values, mask=mask, skipna=skipna, min_count=min_count, axis=axis
| )
|
|
| def _minmax(
| func: Callable,
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| axis: AxisInt | None = None,
| ):
| """
| Reduction for 1D masked array.
|
| Parameters
| ----------
| func : np.min or np.max
| values : np.ndarray
| Numpy array with the values (can be of any dtype that support the
| operation).
| mask : np.ndarray[bool]
| Boolean numpy array (True values indicate missing values).
| skipna : bool, default True
| Whether to skip NA.
| axis : int, optional, default None
| """
| if not skipna:
| if mask.any() or not values.size:
| # min/max with empty array raise in numpy, pandas returns NA
| return libmissing.NA
| else:
| return func(values)
| else:
| subset = values[~mask]
| if subset.size:
| return func(subset)
| else:
| # min/max with empty array raise in numpy, pandas returns NA
| return libmissing.NA
|
|
| def min(
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| axis: AxisInt | None = None,
| ):
| return _minmax(np.min, values=values, mask=mask, skipna=skipna, axis=axis)
|
|
| def max(
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| axis: AxisInt | None = None,
| ):
| return _minmax(np.max, values=values, mask=mask, skipna=skipna, axis=axis)
|
|
| def mean(
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| axis: AxisInt | None = None,
| ):
| if not values.size or mask.all():
| return libmissing.NA
| return _reductions(np.mean, values=values, mask=mask, skipna=skipna, axis=axis)
|
|
| def var(
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| axis: AxisInt | None = None,
| ddof: int = 1,
| ):
| if not values.size or mask.all():
| return libmissing.NA
|
| with warnings.catch_warnings():
| warnings.simplefilter("ignore", RuntimeWarning)
| return _reductions(
| np.var, values=values, mask=mask, skipna=skipna, axis=axis, ddof=ddof
| )
|
|
| def std(
| values: np.ndarray,
| mask: npt.NDArray[np.bool_],
| *,
| skipna: bool = True,
| axis: AxisInt | None = None,
| ddof: int = 1,
| ):
| if not values.size or mask.all():
| return libmissing.NA
|
| with warnings.catch_warnings():
| warnings.simplefilter("ignore", RuntimeWarning)
| return _reductions(
| np.std, values=values, mask=mask, skipna=skipna, axis=axis, ddof=ddof
| )
|
|
