PredTask-class: Class "PredTask"

In performanceEstimation: An Infra-Structure for Performance Estimation of Predictive Models

Description

This is the class of objects that represent a predictive task

Objects from the Class

Objects can be created by calls to the constructor PredTask(...). The constructor requires a formula and a data frame on the first two arguments. You may also a name for the task through the parameter taskName of the constructor. Optional parameter type allows you to indicate the type of task (either "regr", "class" or "ts", for regression, classification and time series tasks, respectively). If not provided this will be inferred from constructor. Setting the optional parameter copy to TRUE (defaults to FALSE) will force the constructor to make a copy of the given data frame and store it in the dataSource slot of the PredTask object.

Slots

formula:

Object of class formula containing the formula representing the predictive task.

dataSource:

Object of class data.frame, call or name. This will be used to fecth the task data when necessary. The first of these options will only be used if the user calls the constructor with copy=TRUE and will result in the source data being copied into the PredTask object.

taskName:

Optional object of class character containing the ID of the predictive task

type:

Optional object of class character containing the type of the predictive task (it can be "regr", "class" or "ts").

target:

Optional object of class character containing the name of the target variable.

Methods

show

signature(object = "PredTask"): method used to show the contents of a PredTask object.

Author(s)

Luis Torgo [e-mail]

References

Torgo, L. (2014) An Infra-Structure for Performance Estimation and Experimental Comparison of Predictive Models in R. arXiv:1412.0436 [cs.MS] http://arxiv.org/abs/1412.0436

See Also

Workflow, EstimationTask, performanceEstimation

Examples

showClass("PredTask")
data(iris)
PredTask(Species  ~ .,iris)
PredTask(Species  ~ .,iris[1:20,],"irisSubset")
## after the next example you can safely remove the iris data frame from
## your environment because the data was stored inside the "t" object.
t <- PredTask(Species ~ ., iris,copy=TRUE) 

performanceEstimation documentation built on May 2, 2019, 6:01 a.m.