This is development documentation. Some features are not available in the stable release. View stable documentation.

Tensor plugin

Introduction

The spectrochempy-tensor plugin provides tensor decomposition classes backed by TensorLy. Keeping these algorithms in a plugin lets the core package remain independent from tensor-specific dependencies while preserving integrated access when the plugin is installed.

Installation

python -m pip install "spectrochempy[tensor]"

or directly:

pip install spectrochempy-tensor

Recommended API

import spectrochempy as scp

model = scp.tensor.CP(n_components=2)
model.fit(dataset)
factors = model.result.factors
weights = model.result.weights

Compatibility aliases

The historical scp.CP alias is kept as a deprecated compatibility path, but new documentation and examples should use scp.tensor.CP.

Direct accessors such as model.A, model.B, model.C, and model.weights remain available.

API Reference

The generated public API page for the Tensor plugin is listed in Plugin public API reference. See spectrochempy.tensor.CP.

Examples

Use the package-level scp.tensor.CP(...) estimator shown above for TensorLy-backed CP/PARAFAC workflows on existing datasets.

Limitations

Tensor decomposition implementations live under spectrochempy_tensor.decompositions. This page currently focuses on the main CP/PARAFAC workflow exposed through scp.tensor.CP(...).