timeSplitter: Split test/train data by time and then partitions training...

Description Usage Arguments Details Value

View source: R/DataSplitting.R

Description

Split test/train data by time and then partitions training set into random folds stratified by class

Usage

1
timeSplitter(population, test = 0.3, train = NULL, nfold = 3, seed = NULL)

Arguments

population

An object created using createStudyPopulation().

test

A real number between 0 and 1 indicating the test set fraction of the data

train

A real number between 0 and 1 indicating the training set fraction of the data

nfold

An integer >= 1 specifying the number of folds used in cross validation

seed

If set a fixed seed is used, otherwise a random split is performed

Details

Returns a dataframe of rowIds and indexes with a -1 index indicating the rowId belongs to the test set and a positive integer index value indicating the rowId's cross valiation fold within the train set.

Value

A dataframe containing the columns: rowId and index


hxia/plp-git-demo documentation built on March 19, 2021, 1:54 a.m.