diff options
Diffstat (limited to 'numpy/lib/tests')
| -rw-r--r-- | numpy/lib/tests/test_function_base.py | 50 | ||||
| -rw-r--r-- | numpy/lib/tests/test_nanfunctions.py | 58 |
2 files changed, 108 insertions, 0 deletions
diff --git a/numpy/lib/tests/test_function_base.py b/numpy/lib/tests/test_function_base.py index c5b31ebf4..1bb4c4efa 100644 --- a/numpy/lib/tests/test_function_base.py +++ b/numpy/lib/tests/test_function_base.py @@ -25,6 +25,7 @@ from numpy.lib import ( i0, insert, interp, kaiser, meshgrid, msort, piecewise, place, rot90, select, setxor1d, sinc, trapz, trim_zeros, unwrap, unique, vectorize ) +from numpy.core.numeric import normalize_axis_tuple def get_mat(n): @@ -3331,6 +3332,32 @@ class TestPercentile: assert_equal(np.percentile(d, [1, 7], axis=(0, 3), keepdims=True).shape, (2, 1, 5, 7, 1)) + @pytest.mark.parametrize('q', [7, [1, 7]]) + @pytest.mark.parametrize( + argnames='axis', + argvalues=[ + None, + 1, + (1,), + (0, 1), + (-3, -1), + ] + ) + def test_keepdims_out(self, q, axis): + d = np.ones((3, 5, 7, 11)) + if axis is None: + shape_out = (1,) * d.ndim + else: + axis_norm = normalize_axis_tuple(axis, d.ndim) + shape_out = tuple( + 1 if i in axis_norm else d.shape[i] for i in range(d.ndim)) + shape_out = np.shape(q) + shape_out + + out = np.empty(shape_out) + result = np.percentile(d, q, axis=axis, keepdims=True, out=out) + assert result is out + assert_equal(result.shape, shape_out) + def test_out(self): o = np.zeros((4,)) d = np.ones((3, 4)) @@ -3843,6 +3870,29 @@ class TestMedian: assert_equal(np.median(d, axis=(0, 1, 3), keepdims=True).shape, (1, 1, 7, 1)) + @pytest.mark.parametrize( + argnames='axis', + argvalues=[ + None, + 1, + (1, ), + (0, 1), + (-3, -1), + ] + ) + def test_keepdims_out(self, axis): + d = np.ones((3, 5, 7, 11)) + if axis is None: + shape_out = (1,) * d.ndim + else: + axis_norm = normalize_axis_tuple(axis, d.ndim) + shape_out = tuple( + 1 if i in axis_norm else d.shape[i] for i in range(d.ndim)) + out = np.empty(shape_out) + result = np.median(d, axis=axis, keepdims=True, out=out) + assert result is out + assert_equal(result.shape, shape_out) + class TestAdd_newdoc_ufunc: diff --git a/numpy/lib/tests/test_nanfunctions.py b/numpy/lib/tests/test_nanfunctions.py index 733a077ea..64464edcc 100644 --- a/numpy/lib/tests/test_nanfunctions.py +++ b/numpy/lib/tests/test_nanfunctions.py @@ -3,6 +3,7 @@ import pytest import inspect import numpy as np +from numpy.core.numeric import normalize_axis_tuple from numpy.lib.nanfunctions import _nan_mask, _replace_nan from numpy.testing import ( assert_, assert_equal, assert_almost_equal, assert_raises, @@ -807,6 +808,33 @@ class TestNanFunctions_Median: res = np.nanmedian(d, axis=(0, 1, 3), keepdims=True) assert_equal(res.shape, (1, 1, 7, 1)) + @pytest.mark.parametrize( + argnames='axis', + argvalues=[ + None, + 1, + (1, ), + (0, 1), + (-3, -1), + ] + ) + def test_keepdims_out(self, axis): + d = np.ones((3, 5, 7, 11)) + # Randomly set some elements to NaN: + w = np.random.random((4, 200)) * np.array(d.shape)[:, None] + w = w.astype(np.intp) + d[tuple(w)] = np.nan + if axis is None: + shape_out = (1,) * d.ndim + else: + axis_norm = normalize_axis_tuple(axis, d.ndim) + shape_out = tuple( + 1 if i in axis_norm else d.shape[i] for i in range(d.ndim)) + out = np.empty(shape_out) + result = np.nanmedian(d, axis=axis, keepdims=True, out=out) + assert result is out + assert_equal(result.shape, shape_out) + def test_out(self): mat = np.random.rand(3, 3) nan_mat = np.insert(mat, [0, 2], np.nan, axis=1) @@ -982,6 +1010,36 @@ class TestNanFunctions_Percentile: res = np.nanpercentile(d, 90, axis=(0, 1, 3), keepdims=True) assert_equal(res.shape, (1, 1, 7, 1)) + @pytest.mark.parametrize('q', [7, [1, 7]]) + @pytest.mark.parametrize( + argnames='axis', + argvalues=[ + None, + 1, + (1,), + (0, 1), + (-3, -1), + ] + ) + def test_keepdims_out(self, q, axis): + d = np.ones((3, 5, 7, 11)) + # Randomly set some elements to NaN: + w = np.random.random((4, 200)) * np.array(d.shape)[:, None] + w = w.astype(np.intp) + d[tuple(w)] = np.nan + if axis is None: + shape_out = (1,) * d.ndim + else: + axis_norm = normalize_axis_tuple(axis, d.ndim) + shape_out = tuple( + 1 if i in axis_norm else d.shape[i] for i in range(d.ndim)) + shape_out = np.shape(q) + shape_out + + out = np.empty(shape_out) + result = np.nanpercentile(d, q, axis=axis, keepdims=True, out=out) + assert result is out + assert_equal(result.shape, shape_out) + def test_out(self): mat = np.random.rand(3, 3) nan_mat = np.insert(mat, [0, 2], np.nan, axis=1) |