pp_beads — B E A D S

Group: Baseline correction · Binding: n4m.sklearn.BEADS · C ABI: n4m_pp_beads_*

Description

Baseline estimation and denoising with sparsity.

Parameters

Name	Type	Default
lam_0	float	100.0
lam_1	float	0.5
lam_2	float	0.5
max_iter	int	50
tol	float	0.001

Explanations

Bibliographic source

Standard spectroscopic operator — see the nirs4all preprocessing / augmentation handbook and the cited literature within the binding docstring.

Mathematical principle

Baseline estimation and denoising with sparsity.

Implementation

C ABI n4m_pp_beads_* in libn4m (create / apply / destroy lifecycle), wrapped by n4m.sklearn.BEADS. The same numerical kernel backs every language binding.

Usage

from n4m.sklearn import BEADS
op = BEADS()
X_transformed = op.fit_transform(X)

Benchmarks

Adaptive wall-clock per cell measured against full_matrix.csv. Only backends that implement this method are listed; libraries without the method are omitted.

Verdict  ·  ✓ ref / ≈ ref / ~ shape mark a reference-gate pass at strict / relaxed / qualitative tolerance  ·  ✓ bind = pls4all binding agrees with the C++ baseline  ·  ⇄ cross-check = documented by-design selector/RNG/model, noncanonical API/facade convention, or secondary oracle  ·  ✗ divergent  ·  ⚠ error  ·  — not run. The fastest backend per column is marked 🏆.

Reference gate: strict — numeric equivalence (rmse_rel_tol ≤ 1e-12).

1 thread

Backend	Parity	50×250 (ms)	250×50 (ms)
C++ native · libn4m
pls4all.cpp.blas	✓ ref	—	—
pls4all.cpp.blas+omp	✓ ref	24.5 ms	20.3 ms
pls4all.cpp.omp	✓ ref	—	—
pls4all.cpp.ref	✓ ref	23.3 ms	19.5 ms
Python · pls4all
pls4all.python	✓ bind	13.6 ms🏆	10.9 ms🏆
pls4all.sklearn	✓ bind	13.7 ms	10.9 ms
Python · external
nirs4all	source	94.4 ms	301.7 ms
ref.python_numpy	source	—	—

---

See also: methods index · interactive dashboard