gg_variable: Marginal variable dependence data object.

Description

plot.variable generates a data.frame containing the marginal variable dependence or the partial variable dependence. The gg_variable function creates a data.frame of containing the full set of covariate data (predictor variables) and the predicted response for each observation. Marginal dependence figures are created using the plot.gg_variable function.

Optional arguments time point (or vector of points) of interest (for survival forests only) time_labels If more than one time is specified, a vector of time labels for differentiating the time points (for survival forests only) oob indicate if predicted results should include oob or full data set.

Usage

gg_variable(object, ...)

Value

gg_variable object

Arguments

object: a rfsrc object
...: optional arguments

Details

The marginal variable dependence is determined by comparing relation between the predicted response from the randomForest and a covariate of interest.

The gg_variable function operates on a rfsrc object, or the output from the plot.variable function.

Examples

Run this code

## ------------------------------------------------------------
## classification
## ------------------------------------------------------------
## -------- iris data
## iris
#rfsrc_iris <- rfsrc(Species ~., data = iris)
data(rfsrc_iris, package="ggRandomForests")

gg_dta <- gg_variable(rfsrc_iris)
plot(gg_dta, xvar="Sepal.Width")
plot(gg_dta, xvar="Sepal.Length")

plot(gg_dta, xvar=rfsrc_iris$xvar.names,
     panel=TRUE) # , se=FALSE)

## ------------------------------------------------------------
## regression
## ------------------------------------------------------------
if (FALSE) {
## -------- air quality data
rfsrc_airq <- rfsrc(Ozone ~ ., data = airquality)
gg_dta <- gg_variable(rfsrc_airq)

# an ordinal variable
gg_dta[,"Month"] <- factor(gg_dta[,"Month"])

plot(gg_dta, xvar="Wind")
plot(gg_dta, xvar="Temp")
plot(gg_dta, xvar="Solar.R")


plot(gg_dta, xvar=c("Solar.R", "Wind", "Temp", "Day"), panel=TRUE)

plot(gg_dta, xvar="Month", notch=TRUE)
}
if (FALSE) {
## -------- motor trend cars data
rfsrc_mtcars <- rfsrc(mpg ~ ., data = mtcars)

gg_dta <- gg_variable(rfsrc_mtcars)

# mtcars$cyl is an ordinal variable
gg_dta$cyl <- factor(gg_dta$cyl)
gg_dta$am <- factor(gg_dta$am)
gg_dta$vs <- factor(gg_dta$vs)
gg_dta$gear <- factor(gg_dta$gear)
gg_dta$carb <- factor(gg_dta$carb)

plot(gg_dta, xvar="cyl")

# Others are continuous
plot(gg_dta, xvar="disp")
plot(gg_dta, xvar="hp")
plot(gg_dta, xvar="wt")

# panels
plot(gg_dta,xvar=c("disp","hp", "drat", "wt", "qsec"),  panel=TRUE)
plot(gg_dta, xvar=c("cyl", "vs", "am", "gear", "carb"), panel=TRUE,
     notch=TRUE)
}
## -------- Boston data
data(Boston, package="MASS")

rf_boston <- randomForest::randomForest(medv~., data=Boston)
gg_dta <- gg_variable(rf_boston)
plot(gg_dta)

## ------------------------------------------------------------
## survival examples
## ------------------------------------------------------------
if (FALSE) {
## -------- veteran data
## survival
# data(veteran, package = "randomForestSRC")
# rfsrc_veteran <- rfsrc(Surv(time,status)~., veteran, nsplit = 10,
#                        ntree = 100)
data(rfsrc_veteran, package="ggRandomForests")

# get the 1 year survival time.
gg_dta <- gg_variable(rfsrc_veteran, time=90)

# Generate variable dependence plots for age and diagtime
plot(gg_dta, xvar = "age")
plot(gg_dta, xvar = "diagtime", )

# Generate coplots
plot(gg_dta, xvar = c("age", "diagtime"), panel=TRUE, se=FALSE)

# If we want to compare survival at different time points, say 30, 90 day
# and 1 year
gg_dta <- gg_variable(rfsrc_veteran, time=c(30, 90, 365))

# Generate variable dependence plots for age and diagtime
plot(gg_dta, xvar = "age")
}
## -------- pbc data