Linear Discriminant Analysis

This node performs Linear Discriminant Analysis (LDA) which is a dimensionality reduction technique. It takes class information into account in order to project the data into a space in which classes are well separated. The results are similar to Principle Component Analysis (PCA) and may be used in subsequent classification.

This node is equivalent to using a Linear Discriminant Ananlysis Compute node in combination with a Linear Discriminant Analysis Apply node. This pattern may be useful when applying a transformation to multiple datasets.


Target dimensions
Number of dimensions to reduce the input data to. This cannot exceed the number of classes minus one or the number of selected columns, depending on which one is smaller.
Class column
Column containing class information.
Column selection
Columns containing the input data.
Remove original data columns
If checked, the columns containing the input data are removed.
Fail if missing values are encountered
If checked, execution fails when the selected columns contain missing values. Otherwise, rows containing missing values are ignored during computation.

Input Ports

Input table containing numeric columns and one column with class information.

Output Ports

The original data (if not excluded) plus columns for the projected dimensions.


This node has no views


  • No workflows found



You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.