SAGA-GIS Tool Library Documentation (v7.2.0)

Tool Minimum Redundancy Feature Selection

Identify the most relevant features for subsequent classification of tabular data.

The minimum Redundancy Maximum Relevance (mRMR) feature selection algorithm has been developed by Hanchuan Peng .

References:
Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. Hanchuan Peng, Fuhui Long, and Chris Ding, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 8, pp.1226-1238, 2005.

Minimum redundancy feature selection from microarray gene expression data,
Chris Ding, and Hanchuan Peng, Journal of Bioinformatics and Computational Biology, Vol. 3, No. 2, pp.185-205, 2005.

Hanchuan Peng's mRMR Homepage at http://penglab.janelia.org/proj/mRMR/

Parameters

 NameTypeIdentifierDescriptionConstraints
InputDataTable (input)DATA--
OutputFeature SelectionTable (output)SELECTION--
OptionsClass IdentifierTable fieldCLASS--
Verbose OutputBooleanVERBOSEoutput of intermediate results to execution message windowDefault: 1
Number of FeaturesIntegermRMR_NFEATURES-Minimum: 1
Default: 50
DiscretizationBooleanmRMR_DISCRETIZEuncheck this means no discretizaton (i.e. data is already integer)Default: 1
Discretization ThresholdFloating pointmRMR_THRESHOLDa double number of the discretization threshold; set to 0 to make binarizationMinimum: 0.000000
Default: 1.000000
Selection MethodChoicemRMR_METHOD-Available Choices:
[0] Mutual Information Difference (MID)
[1] Mutual Information Quotient (MIQ)
Default: 0

Command-line

Usage: saga_cmd table_calculus 12 [-DATA <str>] [-CLASS <str>] [-SELECTION <str>] [-VERBOSE <str>] [-mRMR_NFEATURES <num>] [-mRMR_DISCRETIZE <str>] [-mRMR_THRESHOLD <double>] [-mRMR_METHOD <str>]
  -DATA:<str>             	Data
	Table (input)
  -CLASS:<str>            	Class Identifier
	Table field
  -SELECTION:<str>        	Feature Selection
	Table (output)
  -VERBOSE:<str>          	Verbose Output
	Boolean
	Default: 1
  -mRMR_NFEATURES:<num>   	Number of Features
	Integer
	Minimum: 1
	Default: 50
  -mRMR_DISCRETIZE:<str>  	Discretization
	Boolean
	Default: 1
  -mRMR_THRESHOLD:<double>	Discretization Threshold
	Floating point
	Minimum: 0.000000
	Default: 1.000000
  -mRMR_METHOD:<str>      	Selection Method
	Choice
	Available Choices:
	[0] Mutual Information Difference (MID)
	[1] Mutual Information Quotient (MIQ)
	Default: 0