Correspondence Analysis with R

Correspondence analysis (CA) is a multivariate statistical technique that reveals the relative relationships between and within two groups of variables, based on data given in a contingency table.

This component apply the correspondence analysis to two string columns available in the dataset.

It automatically computes the contingency table. A third column to aggregate and an aggregation function must be specified in the configuration dialog in order to pivot the dataset.

A complete report with grapics is generated in the component dialog.

This component adopts "FactoMineR", "factoextra" and "ggplot2" R libraries.
You need R to be correctly configured to use this component.

Options

Row Dimension

Row dimension of the contingency table

Column dimension

Column dimension of the contingency table

Column to aggregate

Select the column to summarize (count, sum, unique count, mean)

Number of dimensions to keep

Eingevectors to extract

Aggregation function

Function used to aggregate the data

Nodes

• RowID7 ×
• Column Rename6 ×
• Image Output Widget6 ×
• R View (Workspace)6 ×
• R to Table6 ×
• Joiner4 ×
• Column Rename (Regex)3 ×
• Column Selection Configuration3 ×
• Column Filter2 ×
• Column Resorter2 ×
• Table View2 ×
• Component Input1 ×
• Component Output1 ×
• Integer Configuration1 ×
• Merge Variables1 ×
• Missing Value1 ×
• Pivoting1 ×
• Single Selection Configuration1 ×
• Table to R1 ×
• Text Output Widget1 ×

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Interactive R Statistics Integration
• FeatureKNIME Quick Forms
• FeatureKNIME Views

Links

• No links available