replaceDefaultClassificationParams: Replace classification parameters

In joaofgoncalves/SegOptim: Optimization of Image Segmentation Parameters for Object-Based Image Analysis (OBIA)

Replace classification parameters

Description

An auxiliary function to replace default parameters of classification algorithms.

Usage

replaceDefaultClassificationParams(oldParamSet, newParamSet)

Arguments

oldParamSet	A parameter list object of class classificationParamList.
newParamSet	A nested list with names equal to the parameters defined in generateDefaultClassifierParams.

Value

A nested list object of class classificationParamList with parameters for the available algorithms.

See Also

generateDefaultClassifierParams to get the list of parameters that can be changed for each classification algorithm.

Examples

# x is the classification dataset with one column with the segment ID, 
# other for train/test data inputs, and the remaining columns with classification features

x<-data.frame(SID=1:10, train=sample(c(0,1),10, replace=TRUE), feature1=rnorm(10), 
feature2=rnorm(10,5,2), feature3=rnorm(10,12,3))

oldParams<-generateDefaultClassifierParams(x)

newParams<-list(RF=list(mtry=3),
               GBM=list(n.trees=3000))

replaceDefaultClassificationParams(oldParams, newParams)

joaofgoncalves/SegOptim documentation built on Feb. 5, 2024, 11:10 p.m.