Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.clickml.app/llms.txt

Use this file to discover all available pages before exploring further.

The Feature Extraction component applies dimensionality reduction algorithms to transform a set of input features into a smaller number of extracted components. This is useful for reducing noise, speeding up training, and visualizing high-dimensional data.

Configuration

OptionDescriptionDefault
MethodReduction algorithm to use (see table below)
ColumnsNumerical columns to reduce. Supports All Numerical Features.All numerical
N ComponentsNumber of output components to produce2
Random StateSeed for reproducibility42
Kernel (Kernel PCA only)Kernel type: rbf, poly, sigmoid, cosinerbf

Methods

MethodDescription
PCAPrincipal Component Analysis — finds the directions of maximum variance. The most common choice.
Kernel PCANon-linear version of PCA using a kernel function.
Truncated SVDSVD-based reduction that works on sparse matrices.
ICAIndependent Component Analysis — separates statistically independent signals.
NMFNon-Negative Matrix Factorization — requires all values to be non-negative.

Input / Output

Type
InputDataFrame
OutputDataFrame (original non-feature columns + new component columns)
The output columns are named pca_1, pca_2, ica_1, etc. depending on the method chosen. Non-selected columns are preserved.