29529704838
94%

Ran 16 Jul 2026 07:52PM UTC

Jobs 20

Files 13

Run time 1min

Badge

Embed ▾

Committed 16 Jul 2026 07:52PM UTC coverage: 94.449%. Remained the same

Build # 29529704838

Build Type

push

github

Committed by

web-flow

Commit Message

Optimize Q loading for the 2<=M<K branch (6.1.2) (#51)

## Summary

Micro-optimizes the improved Y-loadings `Q` update in the `2 <= M < K` branch of the
shared Improved Kernel PLS inner loop (`ikpls._impl.pls_steps`, used by
`ikpls.numpy.PLS` and `ikpls.fast_cross_validation.numpy.PLS`). Performance-only up to
a ~1-ULP floating-point reassociation; NumPy backend only.

```diff
- q = q * np.sqrt(eig_vals[-1]) / tTt
+ q = q * (np.sqrt(eig_vals[-1]) / tTt_val)

Folding the two scalar factors before the single array multiply — reusing the Python
float tTt_val (already materialized for the score-norm stability guard) and
precomputing sqrt(eig_vals[-1]) / tTt_val — turns two array ufuncs (a multiply and
a divide by the (1, 1) array tTt) into one array multiply, and drops the
(1, 1)-array broadcast.

Motivation

For small M this update is dominated by per-call NumPy dispatch, not arithmetic. Under
the previous form the improved element-wise Q was measurably slower in-fit than the
original matmul (rᵀ XᵀY)ᵀ / tTt at small M — the original's BLAS matmul stays
cache/branch-warm alongside the surrounding fit while the element-wise dispatch does not.
The reassociation roughly halves the dispatch and removes that regression.

Coverage Stats

1242 of 1315 relevant lines covered (94.45%)

11.86 hits per line

Jobs

ID	Job ID	Ran	Files	Coverage
1	windows-latest-python-3.13-numpy-only - 29529704838.1	16 Jul 2026 07:53PM UTC	13	25.17	GitHub Action Run
2	windows-latest-python-3.10-numpy-only - 29529704838.2	16 Jul 2026 07:53PM UTC	13	24.94	GitHub Action Run
3	ubuntu-latest-python-3.13-numpy-only - 29529704838.3	16 Jul 2026 07:52PM UTC	13	25.17	GitHub Action Run
4	windows-latest-python-3.13-jax - 29529704838.4	16 Jul 2026 08:34PM UTC	13	93.54	GitHub Action Run
5	windows-latest-python-3.14-numpy-only - 29529704838.5	16 Jul 2026 07:53PM UTC	13	25.17	GitHub Action Run
6	ubuntu-latest-python-3.11-numpy-only - 29529704838.6	16 Jul 2026 07:52PM UTC	13	24.94	GitHub Action Run
7	ubuntu-latest-python-3.12-jax - 29529704838.7	16 Jul 2026 08:25PM UTC	13	93.54	GitHub Action Run
8	ubuntu-latest-python-3.11-jax - 29529704838.8	16 Jul 2026 08:22PM UTC	13	93.54	GitHub Action Run
9	ubuntu-latest-python-3.10-jax - 29529704838.9	16 Jul 2026 09:13PM UTC	13	93.54	GitHub Action Run
10	ubuntu-latest-python-3.13-jax - 29529704838.10	16 Jul 2026 08:27PM UTC	13	93.54	GitHub Action Run
11	windows-latest-python-3.11-jax - 29529704838.11	16 Jul 2026 08:38PM UTC	13	93.54	GitHub Action Run
12	windows-latest-python-3.11-numpy-only - 29529704838.12	16 Jul 2026 07:53PM UTC	13	24.94	GitHub Action Run
13	windows-latest-python-3.12-numpy-only - 29529704838.13	16 Jul 2026 07:53PM UTC	13	24.94	GitHub Action Run
14	ubuntu-latest-python-3.14-jax - 29529704838.14	16 Jul 2026 08:21PM UTC	13	93.54	GitHub Action Run
15	windows-latest-python-3.12-jax - 29529704838.15	16 Jul 2026 08:40PM UTC	13	93.54	GitHub Action Run
16	windows-latest-python-3.14-jax - 29529704838.16	16 Jul 2026 08:27PM UTC	13	93.54	GitHub Action Run
17	ubuntu-latest-python-3.14-numpy-only - 29529704838.17	16 Jul 2026 07:52PM UTC	13	25.17	GitHub Action Run
18	ubuntu-latest-python-3.12-numpy-only - 29529704838.18	16 Jul 2026 07:52PM UTC	13	24.94	GitHub Action Run
19	windows-latest-python-3.10-jax - 29529704838.19	16 Jul 2026 09:03PM UTC	13	93.54	GitHub Action Run
20	ubuntu-latest-python-3.10-numpy-only - 29529704838.20	16 Jul 2026 07:52PM UTC	13	24.94	GitHub Action Run

sm00thix / ikpls / 29529704838
94%

README BADGES
x

Markdown

Textile

RDoc

HTML

Rst

Jobs

Source Files on build 29529704838

sm00thix / ikpls / 29529704838 94%

README BADGES x

Markdown

Textile

RDoc

HTML

Rst

Jobs

Source Files on build 29529704838

sm00thix / ikpls / 29529704838
94%

README BADGES
x