buildROCcurveFrame: Generate an empty dataframe to match 'modAcc' lists

In jknowles/EWStools: Tools for automating the testing and evaluation of education early warning system models

Description

Used for generating the data to make good looking ROC curves of training and test data.

Usage

buildROCcurveFrame(methods)

Arguments

methods

a list of train method names to generate the dataframe for

Value

a data.frame with the following columns:

• sens - the sensitivities of the model at various thresholds

• spec - the specificities of the model at various thresholds

• auc - the area under the curve

• auc - the standard deviation of the AUC for the best method reported by train

• method - the model method

• grp - whether the model is using training or test data

• elapsedTime - the time reported for the model to run

Note

The sensitivities and specificities come from the roc object stored in the ROCit object

jknowles/EWStools documentation built on May 19, 2019, 11:42 a.m.