diff options
Diffstat (limited to 'numpy/lib')
| -rw-r--r-- | numpy/lib/arraysetops.py | 21 | ||||
| -rw-r--r-- | numpy/lib/tests/test_arraysetops.py | 46 |
2 files changed, 66 insertions, 1 deletions
diff --git a/numpy/lib/arraysetops.py b/numpy/lib/arraysetops.py index eb5c488e4..7600e17be 100644 --- a/numpy/lib/arraysetops.py +++ b/numpy/lib/arraysetops.py @@ -209,6 +209,16 @@ def unique(ar, return_index=False, return_inverse=False, flattened subarrays are sorted in lexicographic order starting with the first element. + .. versionchanged: NumPy 1.21 + If nan values are in the input array, a single nan is put + to the end of the sorted unique values. + + Also for complex arrays all NaN values are considered equivalent + (no matter whether the NaN is in the real or imaginary part). + As the representant for the returned array the smallest one in the + lexicographical order is chosen - see np.sort for how the lexicographical + order is defined for complex arrays. + Examples -------- >>> np.unique([1, 1, 2, 2, 3, 3]) @@ -324,7 +334,16 @@ def _unique1d(ar, return_index=False, return_inverse=False, aux = ar mask = np.empty(aux.shape, dtype=np.bool_) mask[:1] = True - mask[1:] = aux[1:] != aux[:-1] + if aux.shape[0] > 0 and aux.dtype.kind in "cfmM" and np.isnan(aux[-1]): + if aux.dtype.kind == "c": # for complex all NaNs are considered equivalent + aux_firstnan = np.searchsorted(np.isnan(aux), True, side='left') + else: + aux_firstnan = np.searchsorted(aux, aux[-1], side='left') + mask[1:aux_firstnan] = (aux[1:aux_firstnan] != aux[:aux_firstnan - 1]) + mask[aux_firstnan] = True + mask[aux_firstnan + 1:] = False + else: + mask[1:] = aux[1:] != aux[:-1] ret = (aux[mask],) if return_index: diff --git a/numpy/lib/tests/test_arraysetops.py b/numpy/lib/tests/test_arraysetops.py index de2ef255c..d62da9efb 100644 --- a/numpy/lib/tests/test_arraysetops.py +++ b/numpy/lib/tests/test_arraysetops.py @@ -564,6 +564,52 @@ class TestUnique: assert_equal(a3_idx.dtype, np.intp) assert_equal(a3_inv.dtype, np.intp) + # test for ticket 2111 - float + a = [2.0, np.nan, 1.0, np.nan] + ua = [1.0, 2.0, np.nan] + ua_idx = [2, 0, 1] + ua_inv = [1, 2, 0, 2] + ua_cnt = [1, 1, 2] + assert_equal(np.unique(a), ua) + assert_equal(np.unique(a, return_index=True), (ua, ua_idx)) + assert_equal(np.unique(a, return_inverse=True), (ua, ua_inv)) + assert_equal(np.unique(a, return_counts=True), (ua, ua_cnt)) + + # test for ticket 2111 - complex + a = [2.0-1j, np.nan, 1.0+1j, complex(0.0, np.nan), complex(1.0, np.nan)] + ua = [1.0+1j, 2.0-1j, complex(0.0, np.nan)] + ua_idx = [2, 0, 3] + ua_inv = [1, 2, 0, 2, 2] + ua_cnt = [1, 1, 3] + assert_equal(np.unique(a), ua) + assert_equal(np.unique(a, return_index=True), (ua, ua_idx)) + assert_equal(np.unique(a, return_inverse=True), (ua, ua_inv)) + assert_equal(np.unique(a, return_counts=True), (ua, ua_cnt)) + + # test for ticket 2111 - datetime64 + nat = np.datetime64('nat') + a = [np.datetime64('2020-12-26'), nat, np.datetime64('2020-12-24'), nat] + ua = [np.datetime64('2020-12-24'), np.datetime64('2020-12-26'), nat] + ua_idx = [2, 0, 1] + ua_inv = [1, 2, 0, 2] + ua_cnt = [1, 1, 2] + assert_equal(np.unique(a), ua) + assert_equal(np.unique(a, return_index=True), (ua, ua_idx)) + assert_equal(np.unique(a, return_inverse=True), (ua, ua_inv)) + assert_equal(np.unique(a, return_counts=True), (ua, ua_cnt)) + + # test for ticket 2111 - timedelta + nat = np.timedelta64('nat') + a = [np.timedelta64(1, 'D'), nat, np.timedelta64(1, 'h'), nat] + ua = [np.timedelta64(1, 'h'), np.timedelta64(1, 'D'), nat] + ua_idx = [2, 0, 1] + ua_inv = [1, 2, 0, 2] + ua_cnt = [1, 1, 2] + assert_equal(np.unique(a), ua) + assert_equal(np.unique(a, return_index=True), (ua, ua_idx)) + assert_equal(np.unique(a, return_inverse=True), (ua, ua_inv)) + assert_equal(np.unique(a, return_counts=True), (ua, ua_cnt)) + def test_unique_axis_errors(self): assert_raises(TypeError, self._run_axis_tests, object) assert_raises(TypeError, self._run_axis_tests, |