https://github.com/grantmcdermott/parttree

R package for plotting simple decision tree partitions
https://github.com/grantmcdermott/parttree

Last synced: 5 days ago
JSON representation

R package for plotting simple decision tree partitions

• Host: GitHub
• URL: https://github.com/grantmcdermott/parttree
• Owner: grantmcdermott
• License: other
• Created: 2020-03-25T05:52:20.000Z (almost 5 years ago)
• Default Branch: main
• Last Pushed: 2025-01-14T22:24:36.000Z (5 days ago)
• Last Synced: 2025-01-14T23:24:11.081Z (5 days ago)
• Language: R
• Homepage: http://grantmcdermott.com/parttree
• Size: 10.4 MB
• Stars: 95
• Watchers: 5
• Forks: 23
• Open Issues: 1
• Metadata Files:
  • Readme: README.Rmd
  • Changelog: NEWS.md
  • License: LICENSE

Awesome Lists containing this project

README

        
---

output: github_document

---

```{r, include = FALSE}

knitr::opts_chunk$set(

  collapse = TRUE,

  comment = "#>",

  fig.path = "man/figures/README-",

  out.width = "100%"

)

```

# parttree 

[![R-CMD-check](https://github.com/grantmcdermott/parttree/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/grantmcdermott/parttree/actions/workflows/R-CMD-check.yaml)

[![Docs](https://img.shields.io/badge/docs-homepage-blue.svg)](https://grantmcdermott.com/parttree/index.html)

Visualize simple 2-D decision tree partitions in R. The **parttree**

package provides visualization methods for both base R graphics (via 

[**tinyplot**](https://grantmcdermott.com/tinyplot/)) and

[**ggplot2**](https://ggplot2.tidyverse.org/).

## Installation

This package is not on CRAN yet, but can be installed from

[r-universe](https://grantmcdermott.r-universe.dev/parttree):

``` r

install.packages("parttree", repos = "https://grantmcdermott.r-universe.dev")

```

## Quickstart

The **parttree** [homepage](https://grantmcdermott.com/parttree/index.html)

includes an introductory vignette and detailed documentation. But here's a 

quickstart example using the

["kyphosis"](https://search.r-project.org/CRAN/refmans/rpart/html/kyphosis.html)

dataset that comes bundled with the **rpart** package. In this case, we are

interested in predicting kyphosis recovery after spinal surgery, as a function 

of 1) the number of topmost vertebra that were operated, and 2) patient age.

The key function is `parttree()`, which comes with its own plotting method.

```{r quickstart}

library(rpart)     # For the dataset and fitting decisions trees

library(parttree)  # This package

fit = rpart(Kyphosis ~ Start + Age, data = kyphosis)

# Grab the partitions and plot

fit_pt = parttree(fit)

plot(fit_pt)

```

Customize your plots by passing additional arguments:

```{r quickstart2}

plot(

  fit_pt,

  border  = NA, # no partition borders

  pch     = 19, # filled points

  alpha   = 0.6, # point transparency

  grid    = TRUE, # background grid

  palette = "classic", # new colour palette

  xlab    = "Topmost vertebra operated on", # custom x title

  ylab    = "Patient age (months)", # custom y title

  main    = "Tree predictions: Kyphosis recurrence" # custom title

)

```

### ggplot2

For **ggplot2** users, we offer an equivalent workflow via the `geom_partree()`

visualization layer.

```{r quickstart_gg}

library(ggplot2) ## Should be loaded separately

ggplot(kyphosis, aes(x = Start, y = Age)) +

  geom_parttree(data = fit, alpha = 0.1, aes(fill = Kyphosis)) + # <-- key layer

  geom_point(aes(col = Kyphosis)) +

  labs(

    x = "No. of topmost vertebra operated on", y = "Patient age (months)",

    caption = "Note: Points denote observations. Shading denotes model predictions."

    ) +

  theme_minimal()

```