Skip to content

MAINT Remove -Wcpp warnings when compiling sklearn.decomposition._online_lda_fast #25020

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 8 commits into from
Jan 26, 2023
Merged

MAINT Remove -Wcpp warnings when compiling sklearn.decomposition._online_lda_fast #25020

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8c654ed
MAINT Remove -Wcpp warnings when compiling sklearn.decomposition._onl…
OmarManzoor Nov 24, 2022
e1703a3
Merge remote-tracking branch 'upstream/main' into cython_online_lda_fast
OmarManzoor Nov 24, 2022
e18a8dc
Merge remote-tracking branch 'upstream/main' into cython_online_lda_fast
OmarManzoor Nov 24, 2022
268d614
Merge branch 'main' into cython_online_lda_fast
OmarManzoor Jan 19, 2023
7d57fe0
Use const with floating memory type
OmarManzoor Jan 19, 2023
20f4d90
Remove TODO
OmarManzoor Jan 19, 2023
089764c
Merge branch 'main' into cython_online_lda_fast
jjerphan Jan 19, 2023
949d3f4
Trigger CI
OmarManzoor Jan 20, 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
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 @@ -78,6 +78,7 @@
"sklearn.cluster._k_means_minibatch",
"sklearn.datasets._svmlight_format_fast",
"sklearn.decomposition._cdnmf_fast",
"sklearn.decomposition._online_lda_fast",
"sklearn.ensemble._gradient_boosting",
"sklearn.ensemble._hist_gradient_boosting._gradient_boosting",
"sklearn.ensemble._hist_gradient_boosting.histogram",
Expand Down
19 changes: 10 additions & 9 deletions sklearn/decomposition/_online_lda_fast.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,7 @@ from libc.math cimport exp, fabs, log
from numpy.math cimport EULER


def mean_change(cnp.ndarray[ndim=1, dtype=floating] arr_1,
cnp.ndarray[ndim=1, dtype=floating] arr_2):
def mean_change(const floating[:] arr_1, const floating[:] arr_2):
"""Calculate the mean difference between two arrays.

Equivalent to np.abs(arr_1 - arr2).mean().
Expand All @@ -28,9 +27,11 @@ def mean_change(cnp.ndarray[ndim=1, dtype=floating] arr_1,
return total / size


def _dirichlet_expectation_1d(cnp.ndarray[ndim=1, dtype=floating] doc_topic,
floating doc_topic_prior,
cnp.ndarray[ndim=1, dtype=floating] out):
def _dirichlet_expectation_1d(
floating[:] doc_topic,
floating doc_topic_prior,
floating[:] out
):
"""Dirichlet expectation for a single sample:
exp(E[log(theta)]) for theta ~ Dir(doc_topic)
after adding doc_topic_prior to doc_topic, in-place.
Expand All @@ -56,7 +57,7 @@ def _dirichlet_expectation_1d(cnp.ndarray[ndim=1, dtype=floating] doc_topic,
out[i] = exp(psi(doc_topic[i]) - psi_total)


def _dirichlet_expectation_2d(cnp.ndarray[ndim=2, dtype=floating] arr):
def _dirichlet_expectation_2d(const floating[:, :] arr):
"""Dirichlet expectation for multiple samples:
E[log(theta)] for theta ~ Dir(arr).

Expand All @@ -66,7 +67,7 @@ def _dirichlet_expectation_2d(cnp.ndarray[ndim=2, dtype=floating] arr):
the exp and doesn't add in the prior.
"""
cdef floating row_total, psi_row_total
cdef cnp.ndarray[ndim=2, dtype=floating] d_exp
cdef floating[:, :] d_exp
cdef cnp.npy_intp i, j, n_rows, n_cols

n_rows = arr.shape[0]
Expand All @@ -82,7 +83,7 @@ def _dirichlet_expectation_2d(cnp.ndarray[ndim=2, dtype=floating] arr):
for j in range(n_cols):
d_exp[i, j] = psi(arr[i, j]) - psi_row_total

return d_exp
return d_exp.base


# Psi function for positive arguments. Optimized for speed, not accuracy.
Expand All @@ -107,4 +108,4 @@ cdef floating psi(floating x) nogil:
result += log(x) - .5 * r
r = r * r
result -= r * ((1./12.) - r * ((1./120.) - r * (1./252.)))
return result;
return result