From ff2e2a1e7eea29d925063b13922e096d14331222 Mon Sep 17 00:00:00 2001 From: Aaron Meurer Date: Fri, 12 Nov 2021 08:07:23 -0700 Subject: MAINT: A few updates to the array_api (#20066) * Allow casting in the array API asarray() * Restrict multidimensional indexing in the array API namespace The spec has recently been updated to only require multiaxis (i.e., tuple) indices in the case where every axis is indexed, meaning there are either as many indices as axes or the index has an ellipsis. * Fix type promotion for numpy.array_api.where where does value-based promotion for 0-dimensional arrays, so we use the same trick as in the Array operators to avoid this. * Print empty array_api arrays using empty() Printing behavior isn't required by the spec. This is just to make things easier to understand, especially with the array API test suite. * Fix an incorrect slice bounds guard in the array API * Disallow multiple different dtypes in the input to np.array_api.meshgrid * Remove DLPack support from numpy.array_api.asarray() from_dlpack() should be used to create arrays using DLPack. * Remove __len__ from the array API array object * Add astype() to numpy.array_api * Update the unique_* functions in numpy.array_api unique() in the array API was replaced with three separate functions, unique_all(), unique_inverse(), and unique_values(), in order to avoid polymorphic return types. Additionally, it should be noted that these functions to not currently conform to the spec with respect to NaN behavior. The spec requires multiple NaNs to be returned, but np.unique() returns a single NaN. Since this is currently an open issue in NumPy to possibly revert, I have not yet worked around this. See https://github.com/numpy/numpy/issues/20326. * Add the stream argument to the array API to_device method This does nothing in NumPy, and is just present so that the signature is valid according to the spec. * Use the NamedTuple classes for the type signatures * Add unique_counts to the array API namespace * Remove some unused imports * Update the array_api indexing restrictions The "multiaxis indexing must index every axis explicitly or use an ellipsis" was supposed to include any type of index, not just tuple indices. * Use a simpler type annotation for the array API to_device method * Fix a test failure in the array_api submodule The array_api cannot use the NumPy testing functions because array_api arrays do not mix with NumPy arrays, and also NumPy testing functions may use APIs that aren't supported in the array API. * Add dlpack support to the array_api submodule --- numpy/array_api/_set_functions.py | 89 +++++++++++++++++++++++++++++++++------ 1 file changed, 75 insertions(+), 14 deletions(-) (limited to 'numpy/array_api/_set_functions.py') diff --git a/numpy/array_api/_set_functions.py b/numpy/array_api/_set_functions.py index 357f238f5..05ee7e555 100644 --- a/numpy/array_api/_set_functions.py +++ b/numpy/array_api/_set_functions.py @@ -2,19 +2,82 @@ from __future__ import annotations from ._array_object import Array -from typing import Tuple, Union +from typing import NamedTuple import numpy as np +# Note: np.unique() is split into four functions in the array API: +# unique_all, unique_counts, unique_inverse, and unique_values (this is done +# to remove polymorphic return types). -def unique( - x: Array, - /, - *, - return_counts: bool = False, - return_index: bool = False, - return_inverse: bool = False, -) -> Union[Array, Tuple[Array, ...]]: +# Note: The various unique() functions are supposed to return multiple NaNs. +# This does not match the NumPy behavior, however, this is currently left as a +# TODO in this implementation as this behavior may be reverted in np.unique(). +# See https://github.com/numpy/numpy/issues/20326. + +# Note: The functions here return a namedtuple (np.unique() returns a normal +# tuple). + +class UniqueAllResult(NamedTuple): + values: Array + indices: Array + inverse_indices: Array + counts: Array + + +class UniqueCountsResult(NamedTuple): + values: Array + counts: Array + + +class UniqueInverseResult(NamedTuple): + values: Array + inverse_indices: Array + + +def unique_all(x: Array, /) -> UniqueAllResult: + """ + Array API compatible wrapper for :py:func:`np.unique `. + + See its docstring for more information. + """ + res = np.unique( + x._array, + return_counts=True, + return_index=True, + return_inverse=True, + ) + + return UniqueAllResult(*[Array._new(i) for i in res]) + + +def unique_counts(x: Array, /) -> UniqueCountsResult: + res = np.unique( + x._array, + return_counts=True, + return_index=False, + return_inverse=False, + ) + + return UniqueCountsResult(*[Array._new(i) for i in res]) + + +def unique_inverse(x: Array, /) -> UniqueInverseResult: + """ + Array API compatible wrapper for :py:func:`np.unique `. + + See its docstring for more information. + """ + res = np.unique( + x._array, + return_counts=False, + return_index=False, + return_inverse=True, + ) + return UniqueInverseResult(*[Array._new(i) for i in res]) + + +def unique_values(x: Array, /) -> Array: """ Array API compatible wrapper for :py:func:`np.unique `. @@ -22,10 +85,8 @@ def unique( """ res = np.unique( x._array, - return_counts=return_counts, - return_index=return_index, - return_inverse=return_inverse, + return_counts=False, + return_index=False, + return_inverse=False, ) - if isinstance(res, tuple): - return tuple(Array._new(i) for i in res) return Array._new(res) -- cgit v1.2.1