In talegari/ggisotonic: 'ggplot2' Friendly Isotonic or Monotonic Regression Curves

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)
library("ggisotonic")

ggisotonic

ggisotonic introduces a ggplot layer stat_isotonic to add isotonic or monotonic regression curves similar to ggplot2::geom_smooth.

Installation

install.packages("ggisotonic")
library("ggisotonic")

You can install the released version of ggisotonic from github with:

remotes::install_github("talegari/ggisotonic")

Example

library("ggplot2")
set.seed(100)
dataset = data.frame(x = sort(runif(1e2)),
                    y = c(rnorm(1e2/2), rnorm(1e2/2, mean = 4)),
                    w = sample(1:3, 1e2, replace = TRUE)
                    )
print(head(dataset))

# plot isotonic regression line
ggplot(dataset, aes(x = x, y = y)) +
   geom_point() +
   stat_isotonic()

# plot weighted isotonic regression line along with facets
ggplot(dataset, aes(x = x, y = y)) +
   geom_point() +
   stat_isotonic(aes(w = w), color = 'red', size = 1.5, show.legend = FALSE) +
   facet_wrap(w ~ .)