create_tasks: Create tasks
In NaiaraLopezRojo/globalIRmap: What the Package Does (One Line, Title Case)

Description Usage Arguments Details Value

Create machine learning Task list for random forest models.

create_tasks(
  in_gaugestats,
  in_predvars,
  id_suffix = NULL,
  include_discharge = TRUE
)

`in_gaugestats`	data.table of formatted gauging station summary statistics and hydro-environmental attributes. Output from format_gaugestats.
`in_predvars`	data.table of candidate predictor variable codes and names. Output from selectformat_predvars.
`id_suffix`	(character) suffix to add after task names
`include_discharge`	(logical) whether to include predictor variables of long-term discharge modeled from WaterGAP v2.2.

Tasks are objects that contain the (usually tabular) data and additional meta-data to define a machine learning problem. The meta-data is, for example, the name of the target variable for supervised machine learning problems, or the type of the dataset (e.g. a spatial or survival). This information is used for specific operations that can be performed on a task. For more info on tasks, see https://mlr3book.mlr-org.com/tasks.html.

list of three Task:

(a spatiotemporal classification task) |link[mlr3spatiotempcv]TaskClassifST; for classification random forest with spatiotemporal CV (standard probability and probability CIF)
(a standard regression tasks) |link[mlr3]TaskRegr; for regression random forest (MAXSTAT)
(a regression task where the minority class has already been oversampled) |link[mlr3]TaskRegr; for regression random forest (MAXSTAT). Implemented because class oversampling pipelines are not available for regression tasks.

NaiaraLopezRojo/globalIRmap documentation built on Dec. 17, 2021, 5:19 a.m.