plot.rfpredinterval: Plot constructed prediction intervals for '('rfpredinterval',...

In RFpredInterval: Prediction Intervals with Random Forests and Boosted Forests

Plot constructed prediction intervals for ('rfpredinterval', 'piall') objects

Description

Plots the 16 constructed PIs obtained with piall() for a test observation. For each method, the red point presents the point prediction and blue line shows the constructed prediction interval for the test observation. If the true response of the test observation is known, it is demonstrated with a dashed vertical line. Note that we may have multiple prediction intervals with the HDR PI method.

Usage

## S3 method for class 'rfpredinterval'
plot(x, test_id = 1, sort = TRUE, show_response = TRUE, ...)

Arguments

x	An object of class ('rfpredinterval', 'piall').
test_id	Integer value specifying the test observation to be plotted. The default is 1.
sort	Should the prediction intervals be sorted according to their lengths in the plot? The default is TRUE.
show_response	Should the true response value of the test observation (if available) be displayed in the plot?
...	Optional arguments to be passed to other methods.

Value

Invisibly, the prediction intervals and point predictions that were plotted for the test observation.

See Also

piall

Examples

## load example data
data(BostonHousing, package = "RFpredInterval")
set.seed(2345)

## define train/test split
testindex <- 1
trainindex <- sample(2:nrow(BostonHousing), size = 50, replace = FALSE)
traindata <- BostonHousing[trainindex, ]
testdata <- BostonHousing[testindex, ]

## build 95% PIs with all 16 methods for the first observation in testdata
out <- piall(formula = medv ~ ., traindata = traindata,
             testdata = testdata, num.trees = 50)

## plot the constructed PIs for test_id = 1 with all methods
plot(out, test_id = 1)

RFpredInterval documentation built on March 7, 2023, 7:17 p.m.