Package
weka.attributeSelection
Synopsis
Performs latent semantic analysis and transformation of the data. Use in conjunction with a Ranker search. A low-rank approximation of the full data is found by either specifying the number of singular values to use or specifying a proportion of the singular values to cover.
Available in Weka 3.6.x - 3.7.1. Available via the package management system for Weka >= 3.7.2 (latentSemanticAnalysis).
Options
The table below describes the options available for LatentSemanticAnalysis.
Option | Description |
---|---|
maximumAttributeNames | The maximum number of attributes to include in transformed attribute names. |
normalize | Normalize input data. |
rank | Matrix rank to use for data reduction. Can be a proportion to indicate desired coverage |
Capabilities
The table below describes the capabilites of LatentSemanticAnalysis.
Capability | Supported |
---|---|
Class | Date class, Numeric class, Binary class, Nominal class, Missing class values, No class |
Attributes | Numeric attributes, Nominal attributes, Binary attributes, Missing values, Date attributes, Empty nominal attributes, Unary attributes |
Min # of instances | 1 |