R/odata.R

In orf: Ordered Random Forests

#' Simulated Example Dataset
#'
#' A simulated example dataset with ordered categorical outcome variable
#' containing different types of covariates for illustration purposes.
#'
#' @format A data frame with 1000 rows and 5 variables
#'
#' @return
#'   \item{Y}{ordered outcome, classes 1, 2, and 3}
#'   \item{X1}{continuous covariate, N(0,1)}
#'   \item{X2}{categorical covariate, values 1, 2, and 3}
#'   \item{X3}{binary covariate, values 0 and 1}
#'   \item{X4}{continuous covariate, N(0,10)}
#'
#' @details
#' For the exact data generating process, see the example below.
#'
#' @examples
#' # generate example data
#'
#' # set seed for replicability
#' set.seed(123)
#'
#' # number of observations
#' n  <- 1000
#'
#' # various covariates
#' X1 <- rnorm(n, 0, 1)    # continuous
#' X2 <- rbinom(n, 2, 0.5) # categorical
#' X3 <- rbinom(n, 1, 0.5) # dummy
#' X4 <- rnorm(n, 0, 10)   # noise
#'
#' # bind into matrix
#' X <- as.matrix(cbind(X1, X2, X3, X4))
#'
#' # deterministic component
#' deterministic <- X1 + X2 + X3
#' # generate continuous outcome with logistic error
#' Y <- deterministic + rlogis(n, 0, 1)
#' # thresholds for continuous outcome
#' cuts <- quantile(Y, c(0, 1/3, 2/3, 1))
#' # discretize outcome into ordered classes 1, 2, 3
#' Y <- as.numeric(cut(Y, breaks = cuts, include.lowest = TRUE))
#'
#' # save data as a dataframe
#' odata <- as.data.frame(cbind(Y, X))
#'
#' # end of data generating
#'
"odata"