change_oversamp: Change oversampling ratio

In messamat/globalIRmap: What the Package Does (One Line, Title Case)

Description

Change the class oversampling ratio of an existing random forest \mlr3[mlr3]Learner object.

Usage

change_oversamp(in_oversamprf, in_task)

Arguments

in_oversamprf	Learner whose oversample.ratio parameter to update.
in_task	Task based on which to determine minority class oversampling ratio.

Details

In this study, this function was created to adjust the oversampling ratio after updating the criterion for classifying rivers and streams as non-perennial (see change_taskbackend). The ratio of perennial to non-perennial gauges increases a lot when only considering watercourses that cease to flow at least 30 days per year as non-perennial. This function enables one to keep all settings and hyperparameters intact for a given Learner while updating that ratio.

Value

input Learner (in_oversamprf) with updated oversampling ratio.

messamat/globalIRmap documentation built on July 4, 2021, 10:48 a.m.