# `vip_spa_select` — VIP-seeded SPA
_Group_: **Variable selector** · _Registry tolerance_: `1e-06`
## Description
VIP_SPA — VIP-mask then SPA greedy (Phase 53)
From the `pls4all.sklearn.VIPSPASelector` docstring:
> VIP_SPA — VIP-mask + SPA greedy (Phase 53).
> **Registry note** — Python `auswahl.VIP_SPA` (LSX-UniWue) — VIP > 0.3 mask then greedy SPA pick. Default `_vip_spa_select_pls4all` path now invokes the same `auswahl.VIP_SPA` call, giving bit-exact mask parity. The C++ argmax-VIP SPA-start kernel is opt-in via `legacy=True`.
### Parameters
| Name | Type | Default | Notes |
|------|------|---------|-------|
| `top_k` | `int` | `None` | Number of features to retain. |
| `n_components` | `int` | `2` | Number of latent components extracted (k). |
| `vip_threshold` | `float` | `0.3` | Minimum VIP score required to enter the SPA candidate pool. |
| `seed` | `int` | `7` | registry benchmark cell value |
## Explanations
### Bibliographic source
Hybrid heuristic combining VIP ranking and the Successive Projections Algorithm. See registry notes; no single canonical paper.
### Mathematical principle
Use VIP scores to **seed** SPA's projection-orthogonal forward selection. SPA starts with the highest-VIP feature rather than the highest-coefficient one, then proceeds with the standard projection step. This biases SPA toward $y$-correlated seed features while preserving SPA's collinearity-minimising selection of subsequent features.
In practice this tends to outperform plain SPA on datasets where the first SPA seed is well-known to be noise-dominated (some real-world NIR datasets) but VIP correctly flags a different region as predictive.
### Implementation
`n4m_vip_spa_select`.
MATLAB header (`bindings/matlab/+pls4all/vip_spa_select.m`):
```text
pls4all.vip_spa_select VIP-then-SPA hybrid (Phase 53).
```
### Usage
Every pls4all binding tab dispatches into the same C kernel; the external libraries listed at the bottom of the page are the parity references registered in `benchmarks.parity_timing.registry`. Switch tabs to read the same fit in your language. The R package now ships drop-in-compatible facades for the CRAN `pls` package (`plsr`, `pcr`, `mvr`) and for the `mdatools::pls(x, y, ...)` matrix idiom — those tabs appear only on the methods that have a meaningful equivalence.
**pls4all bindings**
::::{tab-set}
:class: pls4all-bindings
:::{tab-item} C ABI · libn4m
:sync: c
:class-label: lang-c
```c
/* C ABI — libn4m */
n4m_context_t* ctx = n4m_context_create();
n4m_config_t* cfg = n4m_config_create();
n4m_method_result_t* res = NULL;
n4m_vip_spa_select_fit(ctx, cfg, &x_view, &y_view, /* hyperparams */, &res);
/* … read coefficients / mask / scores via */
/* n4m_method_result_get_double_matrix / vector / scalar … */
n4m_method_result_destroy(res);
n4m_config_destroy(cfg);
n4m_context_destroy(ctx);
```
:::
:::{tab-item} Python · pls4all (raw)
:sync: python-raw
:class-label: lang-python
```python
import pls4all
from pls4all._methods import vip_spa_select_fit
with pls4all.Context() as ctx, pls4all.Config() as cfg:
res = vip_spa_select_fit(ctx, cfg, X, y, n_components=4)
# then: res.matrix("predictions"), res.matrix("coefficients"),
# res.vector("mask"), res.scalar("intercept"), …
```
:::
:::{tab-item} Python · pls4all.sklearn
:sync: python-sklearn
:class-label: lang-python
```python
from pls4all.sklearn import VIPSPASelector
mdl = VIPSPASelector(top_k, n_components=2, vip_threshold=0.3)
mdl.fit(X, y)
y_hat = mdl.predict(X_test)
```
:::
:::{tab-item} R · pls4all_method()
:sync: r-dispatcher
:class-label: lang-r
```r
library(pls4all)
# Unified low-level dispatcher (May 2026 R cleanup):
res <- pls4all_method("vip_spa_select", X, y,
n_components = 4L, params = list(vip_threshold = 0.3, top_k = 6L, seed = 7L))
# res is a named list with MethodResult arrays/scalars.
# selected_indices / top_k_intervals are 1-based.
```
:::
:::{tab-item} MATLAB · pls4all (MEX)
:sync: matlab-mex
:class-label: lang-matlab
```matlab
res = pls4all.vip_spa_select(X, y, 4);
% see header of bindings/matlab/+pls4all/vip_spa_select.m for full
% parameter surface:
% res = vip_spa_select(X, Y, n_components, vip_threshold, top_k)
yhat = predict(res, Xtest);
```
:::
:::{tab-item} MATLAB · pls4all (classdef)
:sync: matlab-classdef
:class-label: lang-matlab
_No idiomatic classdef wrapper — invoke `pls4all.fit("vip_spa_select", X, y, …)` directly from the unified MEX factory._
:::
::::
**Registry parity references** 📐
:::{card}
:class-card: external-refs
- 📐 **`ref.python_auswahl`** (python · python) — `auswahl` 0.9.0 · strict (rmse_rel ≤ 1e-06) — Python `auswahl.VIP_SPA` from LSX-UniWue. Same VIP scoring and 0.3 threshold as pls4all; auswahl enumerates every candidate SPA start and picks the CV-best, pls4all takes argmax-VIP within the mask. Mask metric.
:::
### Benchmarks
Adaptive wall-clock per cell measured against [`full_matrix.csv`](../benchmarks/overview.md). 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 · ✗ divergent · ⚠ error · — not run. The fastest backend per column is marked 🏆.
**Reference gate**: strict — numeric equivalence (`rmse_rel_tol ≤ 1e-06`).
Rows tagged with **📐** are the canonical parity references for this method (declared in [`parity_timing.registry`](../benchmarks/methodology.md)). C++ and external rows show reference parity; pls4all language bindings show binding parity against the C++ backend. Hover the icon for role and tolerance band.
::::{tab-set}
:class: parity-tabs
:::{tab-item} 1 thread
:sync: threads-1
| Backend | Parity | 50×250 (ms) | 80×40 (ms) | 100×50 (ms) | 100×500 (ms) | 100×2500 (ms) | 250×50 (ms) | 500×50 (ms) | 500×500 (ms) | 500×2500 (ms) | 2500×50 (ms) | 2500×500 (ms) | 2500×2500 (ms) | 10000×50 (ms) | 10000×500 (ms) |
|---|
| C++ native · libn4m |
|---|
pls4all.cpp.blas | ⚠ | 909.9 ms | 136.2 ms | 2.7 s | 31.0 s🏆 | 371.6 s | 146.8 ms | 2.0 s | 86.8 s | — | — | 189.5 s | — | — | 182.9 s |
pls4all.cpp.blas+omp | ⚠ | 900.1 ms | 143.8 ms | 2.7 s | 31.6 s | 368.9 s | 135.1 ms | 1.9 s | 88.6 s | — | — | 189.1 s🏆 | — | — | 174.8 s |
pls4all.cpp.omp | ⚠ | 893.1 ms | 150.4 ms | 2.6 s | 34.4 s | 371.8 s | 145.5 ms | 2.0 s | 86.5 s | — | — | 189.9 s | — | — | 174.0 s🏆 |
pls4all.cpp.ref | ⚠ | 890.2 ms | 141.8 ms | 2.6 s🏆 | 33.6 s | 339.5 s🏆 | 139.2 ms | 1.9 s🏆 | 84.4 s🏆 | — | — | 190.4 s | — | — | 183.5 s |
| Python · pls4all |
|---|
pls4all.python | ✓ bind | 907.6 ms | 147.2 ms | — | — | — | 137.2 ms | — | — | — | — | — | — | — | — |
pls4all.sklearn | ✓ bind | 2.84 ms🏆 | 1.14 ms🏆 | — | — | — | 2.99 ms🏆 | — | — | — | — | — | — | — | — |
| R · pls4all |
|---|
pls4all.R | ✗ +1e+00 | 12.1 ms | 2.88 ms | — | — | — | 10.6 ms | — | — | — | — | — | — | — | — |
pls4all.R.formula | ✗ +1e+00 | 19.0 ms | 5.98 ms | — | — | — | 9.45 ms | — | — | — | — | — | — | — | — |
pls4all.R.mdatools | ✗ +1e+00 | 19.1 ms | 4.41 ms | — | — | — | 9.68 ms | — | — | — | — | — | — | — | — |
pls4all.R.pls | ✗ +1e+00 | 21.7 ms | 5.29 ms | — | — | — | 9.99 ms | — | — | — | — | — | — | — | — |
| MATLAB · pls4all |
|---|
pls4all.matlab | ✗ +1e+00 | 4.27 ms | 1.25 ms | — | — | — | 6.98 ms | — | — | — | — | — | — | — | — |
pls4all.matlab.classdef | ✗ +1e+00 | 5.19 ms | 1.53 ms | — | — | — | 7.24 ms | — | — | — | — | — | — | — | — |
| Python · external |
|---|
📐ref.python_auswahl | source | 826.1 ms | 131.0 ms | — | — | — | 134.1 ms | — | — | — | — | — | — | — | — |
:::
:::{tab-item} 3 threads
:sync: threads-3
| Backend | Parity | 50×250 (ms) | 80×40 (ms) | 100×50 (ms) | 100×500 (ms) | 100×2500 (ms) | 250×50 (ms) | 500×50 (ms) | 500×500 (ms) | 500×2500 (ms) | 2500×50 (ms) | 2500×500 (ms) | 2500×2500 (ms) | 10000×50 (ms) | 10000×500 (ms) |
|---|
| C++ native · libn4m |
|---|
pls4all.cpp.blas | ✓ ref | — | 93.9 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.cpp.blas+omp | ✓ ref | — | 85.2 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.cpp.omp | ✓ ref | — | 85.3 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.cpp.ref | ✓ ref | — | 88.5 ms | — | — | — | — | — | — | — | — | — | — | — | — |
| Python · pls4all |
|---|
pls4all.python | ✓ bind | — | 78.5 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.sklearn | ✓ bind | — | 1.08 ms🏆 | — | — | — | — | — | — | — | — | — | — | — | — |
| R · pls4all |
|---|
pls4all.R | ✗ +1e+00 | — | 4.27 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.R.formula | ✗ +1e+00 | — | 3.72 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.R.mdatools | ✗ +1e+00 | — | 6.08 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.R.pls | ✗ +1e+00 | — | 5.73 ms | — | — | — | — | — | — | — | — | — | — | — | — |
| MATLAB · pls4all |
|---|
pls4all.matlab | ✗ +1e+00 | — | 1.28 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.matlab.classdef | ✗ +1e+00 | — | 1.54 ms | — | — | — | — | — | — | — | — | — | — | — | — |
| Python · external |
|---|
📐ref.python_auswahl | source | — | 53.6 ms | — | — | — | — | — | — | — | — | — | — | — | — |
:::
:::{tab-item} 10 threads
:sync: threads-10
| Backend | Parity | 50×250 (ms) | 80×40 (ms) | 100×50 (ms) | 100×500 (ms) | 100×2500 (ms) | 250×50 (ms) | 500×50 (ms) | 500×500 (ms) | 500×2500 (ms) | 2500×50 (ms) | 2500×500 (ms) | 2500×2500 (ms) | 10000×50 (ms) | 10000×500 (ms) |
|---|
| C++ native · libn4m |
|---|
pls4all.cpp.blas | ✓ ref | — | 34.7 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.cpp.blas+omp | ✓ ref | — | 34.2 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.cpp.omp | ✓ ref | — | 34.2 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.cpp.ref | ✓ ref | — | 34.7 ms | — | — | — | — | — | — | — | — | — | — | — | — |
| Python · pls4all |
|---|
pls4all.python | ✓ bind | — | 34.3 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.sklearn | ✓ bind | — | 0.86 ms🏆 | — | — | — | — | — | — | — | — | — | — | — | — |
| R · pls4all |
|---|
pls4all.R | ✗ +1e+00 | — | 2.05 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.R.formula | ✗ +1e+00 | — | 2.97 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.R.mdatools | ✗ +1e+00 | — | 2.74 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.R.pls | ✗ +1e+00 | — | 2.84 ms | — | — | — | — | — | — | — | — | — | — | — | — |
| MATLAB · pls4all |
|---|
pls4all.matlab | ✗ +1e+00 | — | 1.20 ms | — | — | — | — | — | — | — | — | — | — | — | — |
pls4all.matlab.classdef | ✗ +1e+00 | — | 1.49 ms | — | — | — | — | — | — | — | — | — | — | — | — |
| Python · external |
|---|
📐ref.python_auswahl | source | — | 25.9 ms | — | — | — | — | — | — | — | — | — | — | — | — |
:::
::::
---
_See also_: [benchmark overview](../benchmarks/overview.md) · [methods index](index.md) · [interactive dashboard](../landing/dashboard.md)