gg_variable.ggRandomForests: Marginal variable depedance data object.

Description

randomForestSRC::plot.variable generates a data.frame containing the marginal variable dependance 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.

Usage

gg_variable.ggRandomForests(object, time, time.labels, oob = TRUE, ...)

Arguments

object

a randomForestSRC::rfsrc object

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.

...

extra arguments

Value

gg_variable object

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 randomForestSRC::rfsrc object, or the output from the randomForestSRC::plot.variable function.

Examples

Run this code

## ------------------------------------------------------------
## classification
## ------------------------------------------------------------

## 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")

## ------------------------------------------------------------
## regression
## ------------------------------------------------------------

## airquality
#rfsrc_airq <- rfsrc(Ozone ~ ., data = airquality)
data(rfsrc_airq, package="ggRandomForests")
gg_dta <- gg_variable(rfsrc_airq)
plot(gg_dta, xvar="Wind")
plot(gg_dta, xvar="Temp")
plot(gg_dta, xvar="Solar.R")

## motor trend cars
#rfsrc_mtcars <- rfsrc(mpg ~ ., data = mtcars)
data(rfsrc_mtcars, package="ggRandomForests")
gg_dta <- gg_variable(rfsrc_mtcars)

# mtcars$cyl is an ordinal variable
gg_dta$cyl <- factor(gg_dta$cyl)
plot(gg_dta, xvar="cyl")

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

# panel
plot(gg_dta, xvar=c("disp","hp"), panel=TRUE)

## ------------------------------------------------------------
## survival examples
## ------------------------------------------------------------

## 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 dependance 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)

# 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 dependance 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)

Run the code above in your browser using DataLab

Data Engineering and BI courses are free this week!