# NOT RUN {
# load data
data(airquality)
# remove observations with missing predictor variable values
airquality <- airquality[complete.cases(airquality), ]
# get number of observations and the response column index
n <- nrow(airquality)
response.col <- 1
# split data into training and test sets
train.ind <- sample(1:n, n * 0.9, replace = FALSE)
Xtrain <- airquality[train.ind, -response.col]
Ytrain <- airquality[train.ind, response.col]
Xtest <- airquality[-train.ind, -response.col]
Ytest <- airquality[-train.ind, response.col]
# fit random forest to the training data
rf <- randomForest::randomForest(Xtrain, Ytrain, nodesize = 5,
ntree = 500,
keep.inbag = TRUE)
# estimate conditional error distribution functions
output <- quantForestError(rf, Xtrain, Xtest,
what = c("p.error", "q.error"))
# get the probability that the error associated with each test
# prediction is less than -4 and the probability that the error
# associated with each test prediction is less than 7
output$perror(c(-4, 7))
# same as above but only for the first three test observations
output$perror(c(-4, 7), 1:3)
# }
Run the code above in your browser using DataCamp Workspace