aug_batch_effect — Offset, slope, and gain batch effects¶
Group: Augmentation · C ABI: n4m_augmentation_batch_effect_*
Description¶
Random offset, slope and gain batch effects.
Parameters¶
Name |
Type |
Default |
|---|---|---|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
API and bindings¶
C ABI (ABI 2): n4m_augmentation_batch_effect_apply · n4m_augmentation_batch_effect_create · n4m_augmentation_batch_effect_destroy. Use the linked public header for the exact signature, configuration, and result handles.
Python (verified public re-export):
from n4m.augmentation.scattering import BatchEffectAugmenter
R: no current source-verified entry point was found for this catalog method.
MATLAB / Octave: no current source-verified entry point was found for this catalog method.
Explanations¶
Bibliographic source¶
No canonical publication defines this three-component simulator. It is an internal instrument/session perturbation model related to affine spectral augmentation.
Mathematical principle¶
On centered normalized wavelength \(t_j\), draw \(a\sim N(0,\sigma_a^2)\), \(b\sim N(0,\sigma_b^2)\) and \(g\sim N(1,\sigma_g^2)\), then \(X'_{ij}=gX_{ij}+a+bt_j\). variation_scope=0 draws a tuple per row; scope 1 shares one tuple across the batch.
Appropriate uses¶
Simulating acquisition-session or instrument-to-instrument affine shifts.
Limits and validation¶
Zero defaults make this a no-op until standard deviations are set. A shared batch draw models one batch only and does not attach batch labels.
Implementation¶
Python role API n4m.augmentation.scattering.BatchEffectAugmenter; ABI 2 family n4m_augmentation_batch_effect_{create,apply,destroy}.
The ABI-2 implementation is the n4m_augmentation_batch_effect_* lifecycle in libn4m.
Sources and provenance¶
See also: methods index · interactive dashboard