-
Notifications
You must be signed in to change notification settings - Fork 52
/
Copy pathset_functions.py
183 lines (126 loc) · 11.1 KB
/
set_functions.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
__all__ = ["unique_all", "unique_counts", "unique_inverse", "unique_values"]
from ._types import Tuple, array
def unique_all(x: array, /) -> Tuple[array, array, array, array]:
"""
Returns the unique elements of an input array ``x``, the first occurring indices for each unique element in ``x``, the indices from the set of unique elements that reconstruct ``x``, and the corresponding counts for each unique element in ``x``.
.. admonition:: Data-dependent output shape
:class: important
The shapes of two of the output arrays for this function depend on the data values in the input array; hence, array libraries which build computation graphs (e.g., JAX, Dask, etc.) may find this function difficult to implement without knowing array values. Accordingly, such libraries may choose to omit this function. See :ref:`data-dependent-output-shapes` section for more details.
.. note::
Uniqueness should be determined based on value equality (see :func:`~array_api.equal`). For input arrays having floating-point data types, value-based equality implies the following behavior.
- As ``nan`` values compare as ``False``, ``nan`` values should be considered distinct.
- As complex floating-point values having at least one ``nan`` component compare as ``False``, complex floating-point values having ``nan`` components should be considered distinct.
- As ``-0`` and ``+0`` compare as ``True``, signed zeros should not be considered distinct, and the corresponding unique element will be implementation-dependent (e.g., an implementation could choose to return ``-0`` if ``-0`` occurs before ``+0``).
As signed zeros are not distinct, using ``inverse_indices`` to reconstruct the input array is not guaranteed to return an array having the exact same values.
Each ``nan`` value and each complex floating-point value having a ``nan`` component should have a count of one, while the counts for signed zeros should be aggregated as a single count.
Parameters
----------
x: array
input array. If ``x`` has more than one dimension, the function must flatten ``x`` and return the unique elements of the flattened array.
Returns
-------
out: Tuple[array, array, array, array]
a namedtuple ``(values, indices, inverse_indices, counts)`` whose
- first element must have the field name ``values`` and must be a one-dimensional array containing the unique elements of ``x``. The array must have the same data type as ``x``.
- second element must have the field name ``indices`` and must be an array containing the indices (first occurrences) of a flattened ``x`` that result in ``values``. The array must have the same shape as ``values`` and must have the default array index data type.
- third element must have the field name ``inverse_indices`` and must be an array containing the indices of ``values`` that reconstruct ``x``. The array must have the same shape as ``x`` and must have the default array index data type.
- fourth element must have the field name ``counts`` and must be an array containing the number of times each unique element occurs in ``x``. The order of the returned counts must match the order of ``values``, such that a specific element in ``counts`` corresponds to the respective unique element in ``values``. The returned array must have same shape as ``values`` and must have the default array index data type.
.. note::
The order of unique elements is not specified and may vary between implementations.
Notes
-----
.. versionchanged:: 2022.12
Added complex data type support.
.. versionchanged:: 2023.12
Clarified flattening behavior and required the order of ``counts`` match the order of ``values``.
"""
def unique_counts(x: array, /) -> Tuple[array, array]:
"""
Returns the unique elements of an input array ``x`` and the corresponding counts for each unique element in ``x``.
.. admonition:: Data-dependent output shape
:class: important
The shapes of two of the output arrays for this function depend on the data values in the input array; hence, array libraries which build computation graphs (e.g., JAX, Dask, etc.) may find this function difficult to implement without knowing array values. Accordingly, such libraries may choose to omit this function. See :ref:`data-dependent-output-shapes` section for more details.
.. note::
Uniqueness should be determined based on value equality (see :func:`~array_api.equal`). For input arrays having floating-point data types, value-based equality implies the following behavior.
- As ``nan`` values compare as ``False``, ``nan`` values should be considered distinct.
- As complex floating-point values having at least one ``nan`` component compare as ``False``, complex floating-point values having ``nan`` components should be considered distinct.
- As ``-0`` and ``+0`` compare as ``True``, signed zeros should not be considered distinct, and the corresponding unique element will be implementation-dependent (e.g., an implementation could choose to return ``-0`` if ``-0`` occurs before ``+0``).
Each ``nan`` value and each complex floating-point value having a ``nan`` component should have a count of one, while the counts for signed zeros should be aggregated as a single count.
Parameters
----------
x: array
input array. If ``x`` has more than one dimension, the function must flatten ``x`` and return the unique elements of the flattened array.
Returns
-------
out: Tuple[array, array]
a namedtuple `(values, counts)` whose
- first element must have the field name ``values`` and must be a one-dimensional array containing the unique elements of ``x``. The array must have the same data type as ``x``.
- second element must have the field name `counts` and must be an array containing the number of times each unique element occurs in ``x``. The order of the returned counts must match the order of ``values``, such that a specific element in ``counts`` corresponds to the respective unique element in ``values``. The returned array must have same shape as ``values`` and must have the default array index data type.
.. note::
The order of unique elements is not specified and may vary between implementations.
Notes
-----
.. versionchanged:: 2022.12
Added complex data type support.
.. versionchanged:: 2023.12
Clarified flattening behavior and required the order of ``counts`` match the order of ``values``.
"""
def unique_inverse(x: array, /) -> Tuple[array, array]:
"""
Returns the unique elements of an input array ``x`` and the indices from the set of unique elements that reconstruct ``x``.
.. admonition:: Data-dependent output shape
:class: important
The shapes of two of the output arrays for this function depend on the data values in the input array; hence, array libraries which build computation graphs (e.g., JAX, Dask, etc.) may find this function difficult to implement without knowing array values. Accordingly, such libraries may choose to omit this function. See :ref:`data-dependent-output-shapes` section for more details.
.. note::
Uniqueness should be determined based on value equality (see :func:`~array_api.equal`). For input arrays having floating-point data types, value-based equality implies the following behavior.
- As ``nan`` values compare as ``False``, ``nan`` values should be considered distinct.
- As complex floating-point values having at least one ``nan`` component compare as ``False``, complex floating-point values having ``nan`` components should be considered distinct.
- As ``-0`` and ``+0`` compare as ``True``, signed zeros should not be considered distinct, and the corresponding unique element will be implementation-dependent (e.g., an implementation could choose to return ``-0`` if ``-0`` occurs before ``+0``).
As signed zeros are not distinct, using ``inverse_indices`` to reconstruct the input array is not guaranteed to return an array having the exact same values.
Parameters
----------
x: array
input array. If ``x`` has more than one dimension, the function must flatten ``x`` and return the unique elements of the flattened array.
Returns
-------
out: Tuple[array, array]
a namedtuple ``(values, inverse_indices)`` whose
- first element must have the field name ``values`` and must be a one-dimensional array containing the unique elements of ``x``. The array must have the same data type as ``x``.
- second element must have the field name ``inverse_indices`` and must be an array containing the indices of ``values`` that reconstruct ``x``. The array must have the same shape as ``x`` and have the default array index data type.
.. note::
The order of unique elements is not specified and may vary between implementations.
Notes
-----
.. versionchanged:: 2022.12
Added complex data type support.
.. versionchanged:: 2023.12
Clarified flattening behavior.
"""
def unique_values(x: array, /) -> array:
"""
Returns the unique elements of an input array ``x``.
.. admonition:: Data-dependent output shape
:class: important
The shapes of two of the output arrays for this function depend on the data values in the input array; hence, array libraries which build computation graphs (e.g., JAX, Dask, etc.) may find this function difficult to implement without knowing array values. Accordingly, such libraries may choose to omit this function. See :ref:`data-dependent-output-shapes` section for more details.
.. note::
Uniqueness should be determined based on value equality (see :func:`~array_api.equal`). For input arrays having floating-point data types, value-based equality implies the following behavior.
- As ``nan`` values compare as ``False``, ``nan`` values should be considered distinct.
- As complex floating-point values having at least one ``nan`` component compare as ``False``, complex floating-point values having ``nan`` components should be considered distinct.
- As ``-0`` and ``+0`` compare as ``True``, signed zeros should not be considered distinct, and the corresponding unique element will be implementation-dependent (e.g., an implementation could choose to return ``-0`` if ``-0`` occurs before ``+0``).
Parameters
----------
x: array
input array. If ``x`` has more than one dimension, the function must flatten ``x`` and return the unique elements of the flattened array.
Returns
-------
out: array
a one-dimensional array containing the set of unique elements in ``x``. The returned array must have the same data type as ``x``.
.. note::
The order of unique elements is not specified and may vary between implementations.
Notes
-----
.. versionchanged:: 2022.12
Added complex data type support.
.. versionchanged:: 2023.12
Required that the output array must be one-dimensional.
"""