aug_spline_x_simplify — Spline X Simplification Augmenter

Group: Augmentation · Binding: n4m.sklearn.SplineXSimplificationAugmenter · C ABI: n4m_aug_spline_x_simplify_*

Description

Simplify each spectrum by refitting a cubic interpolating B-spline through a random control subset on the x-axis (numpy.choice(replace=False), bit-for-bit). spline_points <= 0 uses the reference default of n_features // 4.

Parameters

Name

Type

Default

spline_points

int

-1

uniform

bool

False

rng

Optional[PCG64]

None

seed

int

0

Explanations

Bibliographic source

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

Mathematical principle

Simplify each spectrum by refitting a cubic interpolating B-spline through a random control subset on the x-axis (numpy.choice(replace=False), bit-for-bit). spline_points <= 0 uses the reference default of n_features // 4.

Implementation

C ABI n4m_aug_spline_x_simplify_* in libn4m (create / apply / destroy lifecycle), wrapped by n4m.sklearn.SplineXSimplificationAugmenter. The same numerical kernel backs every language binding.

Usage

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

See also: methods index · interactive dashboard