Skip to content

ENH csr_row_norms optimization #24426

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 9 commits into from
Jan 27, 2023
Merged

ENH csr_row_norms optimization #24426

Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
7870080
ENH csr_row_norms optimization
Sep 12, 2022
f4ff936
Apply suggestions from code review
ArturoAmorQ Sep 12, 2022
496c6cc
Update sklearn/utils/sparsefuncs_fast.pyx
ArturoAmorQ Sep 12, 2022
5e84dad
Apply suggestions from code review
ArturoAmorQ Jan 19, 2023
cdb7449
Merge branch 'main' of https://github.com/scikit-learn/scikit-learn i…
Jan 19, 2023
a4fa7ec
Apply suggestions from code review
ArturoAmorQ Jan 23, 2023
92316b3
Apply suggestions from code review
ArturoAmorQ Jan 26, 2023
036a887
Apply suggestion from code review
Jan 27, 2023
65ace7e
Merge branch 'main' into sparsfuncs_cython
jjerphan Jan 27, 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
34 changes: 17 additions & 17 deletions sklearn/utils/sparsefuncs_fast.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,32 +24,32 @@ ctypedef cnp.float64_t DOUBLE


def csr_row_norms(X):
"""L2 norm of each row in CSR matrix 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.shape, X.indices, X.indptr)
return _csr_row_norms(X.data, X.indices, X.indptr)


def _csr_row_norms(cnp.ndarray[floating, ndim=1, mode="c"] X_data,
shape,
cnp.ndarray[integral, ndim=1, mode="c"] X_indices,
cnp.ndarray[integral, ndim=1, mode="c"] X_indptr):
def _csr_row_norms(
const floating[::1] X_data,
const integral[::1] X_indices,
const integral[::1] X_indptr,
):
cdef:
unsigned long long n_samples = shape[0]
unsigned long long i
integral j
integral n_samples = X_indptr.shape[0] - 1
integral i, j
double sum_

norms = np.empty(n_samples, dtype=X_data.dtype)
cdef floating[::1] norms_view = norms
dtype = np.float32 if floating is float else np.float64

for i in range(n_samples):
sum_ = 0.0
for j in range(X_indptr[i], X_indptr[i + 1]):
sum_ += X_data[j] * X_data[j]
norms_view[i] = sum_
cdef floating[::1] 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]

return norms
return np.asarray(norms)


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