Skip to content

ENH Let csr_row_norms support multi-thread #25598

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 6 commits into from
Feb 28, 2023
Merged

ENH Let csr_row_norms support multi-thread #25598

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
75c4fff
ENH Let csr_row_norms support multi-thread
Feb 13, 2023
dc39a88
Update sklearn/utils/sparsefuncs_fast.pyx
ArturoAmorQ Feb 14, 2023
03fe459
Update sklearn/utils/sparsefuncs_fast.pyx
ArturoAmorQ Feb 14, 2023
f43f04d
Update sklearn/utils/sparsefuncs_fast.pyx
jeremiedbb Feb 14, 2023
3c42a6e
Update sklearn/utils/sparsefuncs_fast.pyx
ArturoAmorQ Feb 14, 2023
bfada88
Update sklearn/utils/sparsefuncs_fast.pyx
ArturoAmorQ Feb 14, 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
21 changes: 12 additions & 9 deletions sklearn/utils/sparsefuncs_fast.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,11 @@ from libc.math cimport fabs, sqrt
cimport numpy as cnp
import numpy as np
from cython cimport floating
from cython.parallel cimport prange
from numpy.math cimport isnan

from sklearn.utils._openmp_helpers import _openmp_effective_n_threads

cnp.import_array()

ctypedef fused integral:
Expand All @@ -27,13 +30,14 @@ def csr_row_norms(X):
"""Squared L2 norm of each row in CSR matrix X."""
if X.dtype not in [np.float32, np.float64]:
X = X.astype(np.float64)
return _csr_row_norms(X.data, X.indices, X.indptr)
n_threads = _openmp_effective_n_threads()
return _sqeuclidean_row_norms_sparse(X.data, X.indptr, n_threads)


def _csr_row_norms(
def _sqeuclidean_row_norms_sparse(
const floating[::1] X_data,
const integral[::1] X_indices,
const integral[::1] X_indptr,
int n_threads,
):
cdef:
integral n_samples = X_indptr.shape[0] - 1
Expand All @@ -42,14 +46,13 @@ def _csr_row_norms(

dtype = np.float32 if floating is float else np.float64

cdef floating[::1] norms = np.zeros(n_samples, dtype=dtype)
cdef floating[::1] squared_row_norms = np.zeros(n_samples, dtype=dtype)

with nogil:
for i in range(n_samples):
for j in range(X_indptr[i], X_indptr[i + 1]):
norms[i] += X_data[j] * X_data[j]
for i in prange(n_samples, schedule='static', nogil=True, num_threads=n_threads):
for j in range(X_indptr[i], X_indptr[i + 1]):
squared_row_norms[i] += X_data[j] * X_data[j]

return np.asarray(norms)
return np.asarray(squared_row_norms)


def csr_mean_variance_axis0(X, weights=None, return_sum_weights=False):
Expand Down