Thanks to visit codestin.com
Credit goes to github.com

Skip to content

BUG: Fix string to bool cast regression #16068

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 12, 2020
Merged

BUG: Fix string to bool cast regression #16068

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e0bdf74
BUG: Fix string to bool cast regression
seberg Apr 24, 2020
09c294f
DOC: Release note for subtle C-API datetime cast fix
seberg May 12, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions doc/release/upcoming_changes/16068.compatibility.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
C-Level string to datetime casts changed
----------------------------------------
The C-level casts from strings were simplified. This changed
also fixes string to datetime and timedelta casts to behave
correctly (i.e. like Python casts using ``string_arr.astype("M8")``
while previously the cast would behave like
``string_arr.astype(np.int_).astype("M8")``.
This only affects code using low-level C-API to do manual casts
(not full array casts) of single scalar values or using e.g.
``PyArray_GetCastFunc``, and should thus not affect the vast majority
of users.
8 changes: 8 additions & 0 deletions numpy/core/src/multiarray/arraytypes.c.src
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1489,6 +1489,7 @@ OBJECT_to_@TOTYPE@(void *input, void *output, npy_intp n,
*
* #from = STRING*23, UNICODE*23, VOID*23#
* #fromtyp = npy_char*69#
* #is_string_to_bool = 1, 0*22, 1, 0*22, 0*23#
* #to = (BOOL,
* BYTE, UBYTE, SHORT, USHORT, INT, UINT,
* LONG, ULONG, LONGLONG, ULONGLONG,
Expand Down Expand Up @@ -1525,6 +1526,13 @@ static void
if (temp == NULL) {
return;
}
#if @is_string_to_bool@
/* Legacy behaviour converts strings to integers before going to bool */
Py_SETREF(temp, PyNumber_Long(temp));
if (temp == NULL) {
return;
}
#endif
if (@to@_setitem(temp, op, aop)) {
Py_DECREF(temp);
return;
Expand Down
28 changes: 28 additions & 0 deletions numpy/core/tests/test_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -278,6 +278,34 @@ def test_array_astype_warning(t):
a = np.array(10, dtype=np.complex_)
assert_warns(np.ComplexWarning, a.astype, t)

@pytest.mark.parametrize(["dtype", "out_dtype"],
[(np.bytes_, np.bool_),
(np.unicode, np.bool_),
(np.dtype("S10,S9"), np.dtype("?,?"))])
def test_string_to_boolean_cast(dtype, out_dtype):
"""
Currently, for `astype` strings are cast to booleans effectively by
calling `bool(int(string)`. This is not consistent (see gh-9875) and
will eventually be deprecated.
"""
arr = np.array(["10", "10\0\0\0", "0\0\0", "0"], dtype=dtype)
expected = np.array([True, True, False, False], dtype=out_dtype)
assert_array_equal(arr.astype(out_dtype), expected)

@pytest.mark.parametrize(["dtype", "out_dtype"],
[(np.bytes_, np.bool_),
(np.unicode, np.bool_),
(np.dtype("S10,S9"), np.dtype("?,?"))])
def test_string_to_boolean_cast_errors(dtype, out_dtype):
"""
These currently error out, since cast to integers fails, but should not
error out in the future.
"""
for invalid in ["False", "True", "", "\0", "non-empty"]:
arr = np.array([invalid], dtype=dtype)
with assert_raises(ValueError):
arr.astype(out_dtype)

def test_copyto_fromscalar():
a = np.arange(6, dtype='f4').reshape(2, 3)

Expand Down