8000 MAINT replace cnp.ndarray with memory views in _fast_dict by OmarManzoor · Pull Request #25754 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content
8000

MAINT replace cnp.ndarray with memory views in _fast_dict #25754

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
Mar 6, 2023
Merged

MAINT replace cnp.ndarray with memory views in _fast_dict #25754

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
c6e3938
MAINT replace cnp.ndarray with memory views in _fast_dict
OmarManzoor Mar 3, 2023
3d97554
Remove the method to_arrays which was not used anywhere
OmarManzoor Mar 3, 2023
e7946fd
Add the to_arrays method back, fix its return values and add a test
OmarManzoor Mar 3, 2023
6534ee1
Address PR suggestions
OmarManzoor Mar 4, 2023
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
20 changes: 7 additions & 13 deletions sklearn/utils/_fast_dict.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,13 +12,6 @@ from libcpp.map cimport map as cpp_map

import numpy as np

# Import the C-level symbols of numpy
cimport numpy as cnp

# Numpy must be initialized. When using numpy from C or Cython you must
# _always_ do that, or you will have segfaults
cnp.import_array()

#DTYPE = np.float64
#ctypedef cnp.float64_t DTYPE_t

Expand All @@ -35,8 +28,11 @@ cnp.import_array()

cdef class IntFloatDict:

def __init__(self, cnp.ndarray[ITYPE_t, ndim=1] keys,
cnp.ndarray[DTYPE_t, ndim=1] values):
def __init__(
self,
ITYPE_t[:] keys,
DTYPE_t[:] values,
):
cdef int i
cdef int size = values.size
# Should check that sizes for keys and values are equal, and
Expand Down Expand Up @@ -91,10 +87,8 @@ cdef class IntFloatDict:
The values of the data points
"""
cdef int size = self.my_map.size()
cdef cnp.ndarray[ITYPE_t, ndim=1] keys = np.empty(size,
dtype=np.intp)
cdef cnp.ndarray[DTYPE_t, ndim=1] values = np.empty(size,
dtype=np.float64)
keys = np.empty(size, dtype=np.intp)
values = np.empty(size, dtype=np.float64)
self._to_arrays(keys, values)
return keys, values

Expand Down
16 changes: 16 additions & 0 deletions sklearn/utils/tests/test_fast_dict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
""" Test fast_dict.
"""
import numpy as np
from numpy.testing import assert_array_equal, assert_allclose

from sklearn.utils._fast_dict import IntFloatDict, argmin

Expand Down Expand Up @@ -29,3 +30,18 @@ def test_int_float_dict_argmin():
values = np.arange(100, dtype=np.float64)
d = IntFloatDict(keys, values)
assert argmin(d) == (0, 0)


def test_to_arrays():
# Test that an IntFloatDict is converted into arrays
# of keys and values correctly
keys_in = np.array([1, 2, 3], dtype=np.intp)
values_in = np.array([4, 5, 6], dtype=np.float64)

d = IntFloatDict(keys_in, values_in)
keys_out, values_out = d.to_arrays()

assert keys_out.dtype == keys_in.dtype
assert values_in.dtype == values_out.dtype
assert_array_equal(keys_out, keys_in)
assert_allclose(values_out, values_in)
0