k-fold cross validation stratified on y, a splitFunction in the sense of vtreat::buildEvalSets

kWayStratifiedY(nRows, nSplits, dframe, y)

Arguments

nRows	number of rows to split (>1)
nSplits	number of groups to split into (<nRows,>1).
dframe	original data frame (ignored).
y	numeric outcome variable try to have equidistributed in each split.

Value

split plan

Examples


set.seed(23255)
d <- data.frame(y=sin(1:100))
pStrat <- kWayStratifiedY(nrow(d),5,d,d$y)
problemAppPlan(nrow(d),5,pStrat,TRUE)
#> NULL
d$stratGroup <- vtreat::getSplitPlanAppLabels(nrow(d),pStrat)
pSimple <- kWayCrossValidation(nrow(d),5,d,d$y)
problemAppPlan(nrow(d),5,pSimple,TRUE)
#> NULL
d$simpleGroup <- vtreat::getSplitPlanAppLabels(nrow(d),pSimple)
summary(tapply(d$y,d$simpleGroup,mean))
#>      Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
#> -0.106875 -0.059623 -0.007774 -0.001272  0.068139  0.099774 
summary(tapply(d$y,d$stratGroup,mean))
#>      Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
#> -0.011531 -0.010448 -0.002826 -0.001272  0.008797  0.009649