The following node is available in the Open Source KNIME predictive analytics and data mining platform version 2.7.1. Discover over 1000 other nodes, as well as enterprise functionality at http://knime.com.

PCA Inversion

This node inverts the transformation applied by the PCA Apply node. Given data in the space resulting from the PCA reduction is transformed back to its original space. Information that was lost in the PCA reduction can of course not be recovered.

Dialog Options

Fail if missing values are encountered
If checked, execution fails, when the selected columns contain missing values. By default, rows containing missing values are ignored and not considered in the computation of the principal components.
Replace PCA columns
If checked, the PCA columns are removed in the output table.
Columns
Select all columns containing the principal components of the original data. Usually the default selection should capture all of these.

Ports

Input Ports
0 Output data of the PCA
1 Input data for the PCA
Output Ports
0 Model with projection to principal components
This node is contained in KNIME Base Nodes provided by KNIME GmbH, Konstanz, Germany.