Feature implementation sst

[inarteroger]

Why is this change needed?

Adds the Spectral Space Transform (SST) transformer to the chemotools.adaptation
module. SST is a linear domain adaptation method that aligns target spectral data
to a source (reference) domain via SVD of the concatenated source-target matrix.
This extends the adaptation module alongside the existing DS and PDS transformers.

Type of change

• New feature

Description

Implementation of SpectralSpaceTransform following the method described in:

Du et al. (2011). Maintaining the predictive abilities of multivariate calibration models by spectral space transformation.
Analytica Chimica Acta, 690(1), 64–70.
https://doi.org/10.1016/j.aca.2011.02.014

What was added

• SpectralSpaceTransform transformer in chemotools/adaptation/_spectral_space_transform.py
• Full sklearn API compliance (fit, transform, fit_transform)
• Identity fallback when X_source=None

Tests added

• sklearn estimator compliance
• fit attributes and shape checks
• boundary and edge case validation for n_components
• Pipeline + GridSearchCV + metadata routing integration

[Copilot]

Pull request overview

Adds a new domain-adaptation transformer, Spectral Space Transform (SST), to align target spectra to a source/reference domain using an SVD-based shared latent space approach, plus a comprehensive test suite to validate sklearn compatibility and expected behavior.

Changes:

• Implement SpectralSpaceTransform (fit/transform) with optional identity behavior when X_source=None.
• Add extensive tests covering sklearn compliance, correctness snapshots, edge cases for n_components, and Pipeline/GridSearchCV metadata routing.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 6 comments.

File	Description
chemotools/adaptation/_spectral_space_transform.py	Introduces the SST transformer implementation, including parameter constraints, fitting logic, and the transformation formula.
tests/adaptation/test_spectral_space_transform.py	Adds sklearn compliance checks, numerical regression tests, edge-case validation, and metadata-routing integration tests for SST.

Comments suppressed due to low confidence (1)

tests/adaptation/test_spectral_space_transform.py:258

• Typo in docstring: "rises ValueError" should be "raises ValueError".

        """Verifies n_components > 2*n_features rises ValueError."""

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 13 out of 13 changed files in this pull request and generated 3 comments.