diff options
| author | Filip Trojan <f.trojan@centrum.cz> | 2021-02-12 17:47:55 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2021-02-12 09:47:55 -0700 |
| commit | 7dcd29aaafe1ab8be4be04d3c793e5bcaf17459f (patch) | |
| tree | d2dcbe5a6834d5f900e66ef50c660b412571d90c /numpy/lib/arraysetops.py | |
| parent | a5dc2b5b917fc50575e10bbe139a0c78e43a1c1c (diff) | |
| download | numpy-7dcd29aaafe1ab8be4be04d3c793e5bcaf17459f.tar.gz | |
BUG: Fix unique handling of nan entries. (#18070)
* benchmark bench_lib.Unique added
* extended test_unique_1d
* modify _unique1d
* extend test with return_index, return_inverse and return_counts parameters
* documentation updated
* Update numpy/lib/arraysetops.py
Co-authored-by: Bas van Beek <43369155+BvB93@users.noreply.github.com>
* full coverage of nan types
Co-authored-by: Bas van Beek <43369155+BvB93@users.noreply.github.com>
* added tests for the datetime like dtypes
* nan as vector of length 1
* use aux[-1] as nan, ..versionchanged, release note
* for complex arrays all NaN values are considered equivalent
Co-authored-by: filip_trojan <Tarantula2018>
Co-authored-by: Bas van Beek <43369155+BvB93@users.noreply.github.com>
Diffstat (limited to 'numpy/lib/arraysetops.py')
| -rw-r--r-- | numpy/lib/arraysetops.py | 21 |
1 files changed, 20 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: |