plot.gg_minimal_depth: Plot a 'gg_minimal_depth' object for random forest variable...

View source: R/plot.gg_minimal_depth.R

plot.gg_minimal_depthR Documentation

Plot a gg_minimal_depth object for random forest variable ranking.

Description

Plot a gg_minimal_depth object for random forest variable ranking.

Usage

## S3 method for class 'gg_minimal_depth'
plot(x, selection = FALSE, type = c("named", "rank"), lbls, ...)

Arguments

x

gg_minimal_depth object created from a rfsrc object

selection

should we restrict the plot to only include variables selected by the minimal depth criteria (boolean).

type

select type of y axis labels c("named","rank")

lbls

a vector of alternative variable names.

...

optional arguments passed to gg_minimal_depth

Value

ggplot object

References

Breiman L. (2001). Random forests, Machine Learning, 45:5-32.

Ishwaran H. and Kogalur U.B. (2007). Random survival forests for R, Rnews, 7(2):25-31.

Ishwaran H. and Kogalur U.B. (2014). Random Forests for Survival, Regression and Classification (RF-SRC), R package version 1.5.

See Also

var.select gg_minimal_depth

Examples

## Not run: 
## Examples from RFSRC package...
## ------------------------------------------------------------
## classification example
## ------------------------------------------------------------
## -------- iris data
## You can build a randomForest
rfsrc_iris <- rfsrc(Species ~ ., data = iris)
varsel_iris <- var.select(rfsrc_iris)

# Get a data.frame containing minimaldepth measures
gg_dta<- gg_minimal_depth(varsel_iris)

# Plot the gg_minimal_depth object
plot(gg_dta)

## ------------------------------------------------------------
## Regression example
## ------------------------------------------------------------
## -------- air quality data
rfsrc_airq <- rfsrc(Ozone ~ ., data = airquality, na.action = "na.impute")
varsel_airq <- var.select(rfsrc_airq)

# Get a data.frame containing error rates
gg_dta<- gg_minimal_depth(varsel_airq)

# Plot the gg_minimal_depth object
plot(gg_dta)

## -------- Boston data
data(Boston, package="MASS")
rfsrc_boston <- randomForestSRC::rfsrc(medv~., Boston)
# Get a data.frame containing error rates
plot(gg_minimal_depth(varsel_boston))

## -------- mtcars data
rfsrc_mtcars <- rfsrc(mpg ~ ., data = mtcars)
varsel_mtcars <- var.select(rfsrc_mtcars)


# Get a data.frame containing error rates
plot.gg_minimal_depth(varsel_mtcars)

## ------------------------------------------------------------
## Survival example
## ------------------------------------------------------------
## -------- veteran data
## randomized trial of two treatment regimens for lung cancer
data(veteran, package = "randomForestSRC")
rfsrc_veteran <- rfsrc(Surv(time, status) ~ ., data = veteran, ntree = 100)
varsel_veteran <- var.select(rfsrc_veteran)

gg_dta <- gg_minimal_depth(varsel_veteran)
plot(gg_dta)

## -------- pbc data
#' # We need to create this dataset
data(pbc, package = "randomForestSRC",) 
# For whatever reason, the age variable is in days... makes no sense to me
for (ind in seq_len(dim(pbc)[2])) {
 if (!is.factor(pbc[, ind])) {
   if (length(unique(pbc[which(!is.na(pbc[, ind])), ind])) <= 2) {
     if (sum(range(pbc[, ind], na.rm = TRUE) == c(0, 1)) == 2) {
       pbc[, ind] <- as.logical(pbc[, ind])
     }
   }
 } else {
   if (length(unique(pbc[which(!is.na(pbc[, ind])), ind])) <= 2) {
     if (sum(sort(unique(pbc[, ind])) == c(0, 1)) == 2) {
       pbc[, ind] <- as.logical(pbc[, ind])
     }
     if (sum(sort(unique(pbc[, ind])) == c(FALSE, TRUE)) == 2) {
       pbc[, ind] <- as.logical(pbc[, ind])
     }
   }
 }
 if (!is.logical(pbc[, ind]) &
     length(unique(pbc[which(!is.na(pbc[, ind])), ind])) <= 5) {
   pbc[, ind] <- factor(pbc[, ind])
 }
}
#Convert age to years
pbc$age <- pbc$age / 364.24

pbc$years <- pbc$days / 364.24
pbc <- pbc[, -which(colnames(pbc) == "days")]
pbc$treatment <- as.numeric(pbc$treatment)
pbc$treatment[which(pbc$treatment == 1)] <- "DPCA"
pbc$treatment[which(pbc$treatment == 2)] <- "placebo"
pbc$treatment <- factor(pbc$treatment)
dta_train <- pbc[-which(is.na(pbc$treatment)), ]
# Create a test set from the remaining patients
pbc_test <- pbc[which(is.na(pbc$treatment)), ]

#========
# build the forest:
rfsrc_pbc <- randomForestSRC::rfsrc(
  Surv(years, status) ~ .,
 dta_train,
 nsplit = 10,
 na.action = "na.impute",
 forest = TRUE,
 importance = TRUE,
 save.memory = TRUE
)

varsel_pbc <- var.select(rfsrc_pbc)

gg_dta <- gg_minimal_depth(varsel_pbc)
plot(gg_dta)


## End(Not run)


ggRandomForests documentation built on Sept. 1, 2022, 5:07 p.m.