Skip to content

MAINT Remove -Wcpp warnings when compiling sklearn.utils.murmurhash #24958

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 4 commits into from
Nov 24, 2022
Merged

MAINT Remove -Wcpp warnings when compiling sklearn.utils.murmurhash #24958

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a5ea4a9
first commit maggle
Vincent-Maladiere Nov 16, 2022
a8928f7
apply suggestions
Vincent-Maladiere Nov 23, 2022
cc31776
Update sklearn/utils/murmurhash.pyx
jeremiedbb Nov 24, 2022
d683b65
Update sklearn/utils/murmurhash.pyx
jeremiedbb Nov 24, 2022
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
1 change: 1 addition & 0 deletions setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,6 +110,7 @@
"sklearn.utils._sorting",
"sklearn.utils._vector_sentinel",
"sklearn.utils._isfinite",
"sklearn.utils.murmurhash",
"sklearn.svm._newrand",
"sklearn._isotonic",
)
Expand Down
32 changes: 19 additions & 13 deletions sklearn/utils/murmurhash.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,26 +54,32 @@ cpdef cnp.int32_t murmurhash3_bytes_s32(bytes key, unsigned int seed):
return out


cpdef cnp.ndarray[cnp.uint32_t, ndim=1] murmurhash3_bytes_array_u32(
cnp.ndarray[cnp.int32_t] key, unsigned int seed):
def _murmurhash3_bytes_array_u32(
const cnp.int32_t[:] key,
unsigned int seed,
):
"""Compute 32bit murmurhash3 hashes of a key int array at seed."""
# TODO make it possible to pass preallocated output array
cdef cnp.ndarray[cnp.uint32_t, ndim=1] out = np.zeros(key.size, np.uint32)
cdef Py_ssize_t i
cdef:
cnp.uint32_t[:] out = np.zeros(key.size, np.uint32)
Py_ssize_t i
for i in range(key.shape[0]):
out[i] = murmurhash3_int_u32(key[i], seed)
return out
return np.asarray(out)


cpdef cnp.ndarray[cnp.int32_t, ndim=1] murmurhash3_bytes_array_s32(
cnp.ndarray[cnp.int32_t] key, unsigned int seed):
def _murmurhash3_bytes_array_s32(
const cnp.int32_t[:] key,
unsigned int seed,
):
"""Compute 32bit murmurhash3 hashes of a key int array at seed."""
# TODO make it possible to pass preallocated output array
cdef cnp.ndarray[cnp.int32_t, ndim=1] out = np.zeros(key.size, np.int32)
cdef Py_ssize_t i
cdef:
cnp.int32_t[:] out = np.zeros(key.size, np.int32)
Py_ssize_t i
for i in range(key.shape[0]):
out[i] = murmurhash3_int_s32(key[i], seed)
return out
return np.asarray(out)


def murmurhash3_32(key, seed=0, positive=False):
Expand Down Expand Up @@ -113,15 +119,15 @@ def murmurhash3_32(key, seed=0, positive=False):
return murmurhash3_int_u32(<cnp.int32_t>key, seed)
else:
return murmurhash3_int_s32(<cnp.int32_t>key, seed)
elif isinstance(key, cnp.ndarray):
elif isinstance(key, np.ndarray):
if key.dtype != np.int32:
raise TypeError(
"key.dtype should be int32, got %s" % key.dtype)
if positive:
return murmurhash3_bytes_array_u32(key.ravel(),
return _murmurhash3_bytes_array_u32(key.ravel(),
seed).reshape(key.shape)
else:
return murmurhash3_bytes_array_s32(key.ravel(),
return _murmurhash3_bytes_array_s32(key.ravel(),
seed).reshape(key.shape)
else:
raise TypeError(
Expand Down