SAGA-GIS Tool Library Documentation (v7.7.0)

Tool Random Forest Classification (ViGrA)

Random Forest Classification.


References


Parameters

 NameTypeIdentifierDescriptionConstraints
InputFeaturesGrid list, inputFEATURES--
Training AreasShapes, inputTRAINING--
OutputRandom Forest ClassificationGrid, outputCLASSES--
Prediction Probability (*)Grid, output, optionalPROBABILITY--
Feature ProbabilitiesGrid list, outputPROBABILITIES--
Feature ImportancesTable, outputIMPORTANCES--
OptionsGrid SystemGrid systemPARAMETERS_GRID_SYSTEM--
Feature ProbabilitiesBooleanBPROBABILITIES-Default: 0
Label FieldTable fieldFIELD--
Use Label as IdentifierBooleanLABEL_AS_IDUse training area labels as identifier in classification result, assumes all label values are integer numbers!Default: 0
Minimum Redundancy Feature SelectionBooleanDO_MRMRUse only features selected by the minimum Redundancy Maximum Relevance (mRMR) algorithmDefault: 0
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
Load ModelFile pathRF_IMPORT--
Save ModelFile pathRF_EXPORT--
Tree CountIntegerRF_TREE_COUNTHow many trees to create?Minimum: 1
Default: 32
Samples per TreeFloating pointRF_TREE_SAMPLESSpecifies the fraction of the total number of samples used per tree for learning.Minimum: 0.000000
Maximum: 1.000000
Default: 1.000000
Sample with ReplacementBooleanRF_REPLACESample from training population with or without replacement?Default: 1
Minimum Node Split SizeIntegerRF_SPLIT_MIN_SIZENumber of examples required for a node to be split. Choose 1 for complete growing.Minimum: 1
Default: 1
Features per NodeChoiceRF_NODE_FEATURES-Available Choices:
[0] logarithmic
[1] square root
[2] all
Default: 1
StratificationChoiceRF_STRATIFICATIONSpecifies stratification strategy. Either none, equal amount of class samples, or proportional to fraction of class samples.Available Choices:
[0] none
[1] equal
[2] proportional
Default: 0
(*) optional

Command-line

Usage: saga_cmd imagery_vigra 9 [-FEATURES <str>] [-CLASSES <str>] [-PROBABILITY <str>] [-BPROBABILITIES <str>] [-PROBABILITIES <str>] [-IMPORTANCES <str>] [-TRAINING <str>] [-FIELD <str>] [-LABEL_AS_ID <str>] [-DO_MRMR <str>] [-mRMR_NFEATURES <num>] [-mRMR_DISCRETIZE <str>] [-mRMR_THRESHOLD <double>] [-mRMR_METHOD <str>] [-RF_IMPORT <str>] [-RF_EXPORT <str>] [-RF_TREE_COUNT <num>] [-RF_TREE_SAMPLES <double>] [-RF_REPLACE <str>] [-RF_SPLIT_MIN_SIZE <num>] [-RF_NODE_FEATURES <str>] [-RF_STRATIFICATION <str>]
  -FEATURES:<str>          	Features
	Grid list, input
  -CLASSES:<str>           	Random Forest Classification
	Grid, output
  -PROBABILITY:<str>       	Prediction Probability
	Grid, output, optional
  -BPROBABILITIES:<str>    	Feature Probabilities
	Boolean
	Default: 0
  -PROBABILITIES:<str>     	Feature Probabilities
	Grid list, output
  -IMPORTANCES:<str>       	Feature Importances
	Table, output
  -TRAINING:<str>          	Training Areas
	Shapes, input
  -FIELD:<str>             	Label Field
	Table field
  -LABEL_AS_ID:<str>       	Use Label as Identifier
	Boolean
	Default: 0
  -DO_MRMR:<str>           	Minimum Redundancy Feature Selection
	Boolean
	Default: 0
  -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
  -RF_IMPORT:<str>         	Load Model
	File path
  -RF_EXPORT:<str>         	Save Model
	File path
  -RF_TREE_COUNT:<num>     	Tree Count
	Integer
	Minimum: 1
	Default: 32
  -RF_TREE_SAMPLES:<double>	Samples per Tree
	Floating point
	Minimum: 0.000000
	Maximum: 1.000000
	Default: 1.000000
  -RF_REPLACE:<str>        	Sample with Replacement
	Boolean
	Default: 1
  -RF_SPLIT_MIN_SIZE:<num> 	Minimum Node Split Size
	Integer
	Minimum: 1
	Default: 1
  -RF_NODE_FEATURES:<str>  	Features per Node
	Choice
	Available Choices:
	[0] logarithmic
	[1] square root
	[2] all
	Default: 1
  -RF_STRATIFICATION:<str> 	Stratification
	Choice
	Available Choices:
	[0] none
	[1] equal
	[2] proportional
	Default: 0