makeDEWSList: Construct a DEWSlist from a model matrix

In jknowles/ModelEWS: Wisconsin Dropout Early Warning System

Description

Construct a DEWSlist from a model matrix

Usage

makeDEWSList(matrix, DV = NULL, preProcess = TRUE, MODE = "PROD",
  PRELIM = FALSE, P, PVALID)

Arguments

matrix	a matrix produced by gatherData
DV	a character representing the column name associated with the dependent variable
preProcess	logical, should a preProcess routine be applied to the data
P	numeric, 0 to 1, proportion of data to be used for training
PVALID,	0 to 1, proportion of the data to be used for the validation data
mode	character, is this running in production or development mode, see details
prelim	logical, is this the preliminary or final model, see details

Details

This function makes the data suitable for use in EWStools functions for testing and selecting models.

Value

a list of lists, the lists are named "traindata", "testdata" and "validdata", and each list has two elements, a predictor matrix called "preds" and an outcome vector called "class". A fourth element called "scale" is included if preProcess = TRUE which contains the preProcess object used

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