Often times users only want to quickly iterate the process of exploring data, building statistical models, and visualizing the model results, especially the models that focus on common tasks such as clustering and time series analysis. Some of these packages provide default visualizations for the data and models they generate. However, they look out-of-fashion and these components require additional transformation and clean-up before using them in ggplot2 and each of those transformation steps must be replicated by others when they wish to produce similar charts in their analyses. Creating a central repository for common/popular transformations and default plotting idioms would reduce the amount of effort needed by all to create compelling, consistent and informative charts.
The ggfortify package provides a unified interface with one single autoplot() function for plotting many statistics and machine learning packages and functions in order to help these users achieve reproducibility goals with minimal effort. ggfortify package has a very easy-to-use and uniform programming interface that enables users to use one line of code to visualize statistical results of many popular R packages using ggplot2 as building blocks. This helps statisticians, data scientists, and researchers avoid both repetitive work and the need to identify the correct ggplot2 syntax to achieve what they need. Users are able to generate beautiful visualizations of their statistical results produced by popular packages with minimal effort.
The autoplotly package is an extension built on top of ggplot2, plotly, and ggfortify to provide functionalities to automatically generate interactive visualizations for many popular statistical results supported by ggfortify package in plotly and ggplot2 styles. The generated visualizations can also be easily extended using ggplot2 and plotly syntax while staying interactive.
You can either try out the following examples in your RStudio or play around with the interactive visualizations embedded on the blogpost here. Note that it is recommended to use a desktop browser to play around with the embedded visualizations.
A couple hints for you to facilitate your exploration:
Install the latest stable release from CRAN:
install.packages('autoplotly')
The autoplotly() function works for the two essential classes of objects for principal component analysis (PCA) obtained from stats package: stats::prcomp and stats::princomp, for example:
p <- autoplotly(prcomp(iris[c(1, 2, 3, 4)]), data = iris,
colour = 'Species', frame = TRUE)
p
Visualization of the change points with optimal positioning for the AirPassengers data set
found in the changepoint package using the cpt.meanvar function:
library(changepoint)
autoplotly(cpt.meanvar(AirPassengers))
Visualization of the original and smoothed line from Kalman filter function in dlm package:
library(dlm)
form <- function(theta){
dlmModPoly(order = 1, dV = exp(theta[1]), dW = exp(theta[2]))
}
model <- form(dlmMLE(Nile, parm = c(1, 1), form)$par)
filtered <- dlmFilter(Nile, model)
autoplotly(filtered)
Visualization of optimal break points where possible structural changes happen in the
regression models built by strucchange::breakpoints:
library(strucchange)
autoplotly(breakpoints(Nile ~ 1), ts.colour = "blue", ts.linetype = "dashed",
cpt.colour = "dodgerblue3", cpt.linetype = "solid")
B-spline basis points visualization for natural cubic spline with boundary knots produced
from splines::ns:
library(splines)
autoplotly(ns(ggplot2::diamonds$price, df = 6))
You can find a complete list of supported objects by autoplotly here.
The plots generated using autoplotly() can be easily extended by applying additional
ggplot2 elements or components. For example, we can add title and axis labels to the
originally generated plot using ggplot2::ggtitle and ggplot2::labs:
autoplotly(
prcomp(iris[c(1, 2, 3, 4)]), data = iris, colour = 'Species', frame = TRUE) +
ggplot2::ggtitle("Principal Components Analysis") +
ggplot2::labs(y = "Second Principal Component", x = "First Principal Component")
Similarly, we can add additional interactive components using plotly. The following
example adds a custom plotly annotation element placed to the center of the plot with an arrow:
p <- autoplotly(prcomp(iris[c(1, 2, 3, 4)]), data = iris,
colour = 'Species', frame = TRUE)
p %>% plotly::layout(annotations = list(
text = "Example Text",
font = list(
family = "Courier New, monospace",
size = 18,
color = "black"),
x = 0,
y = 0,
showarrow = TRUE))
In addition, Tyler's excellent post PCA in a tidy(verse) framework
does a great job demonstrating the extensibility using the combination of broom, ggplot2, and ggfortify.
We can also stack multiple plots generated from autoplotly() together in a single view
using subplot(), two interactive splines visualizations with different degree of freedom
are stacked into one single view in the following example:
library(splines)
subplot(
autoplotly(ns(ggplot2::diamonds$price, df = 6)),
autoplotly(ns(ggplot2::diamonds$price, df = 3)), nrows = 2, margin = 0.03)
The snapshots of the interactive visualizations generated via autoplotly() can be exported using
a simple export() function, for example:
export(p, "/tmp/result.png")
It builds on top of RSelenium package for exporting WebGL plots and uses webshot package for non-WebGL formats such as JPEG, PNG, PDF, etc.
In addition, we can also write out the plot object to a JSON object:
plotly::plotly_json(p, jsonedit = FALSE)
and then use plotly's Javascript API plotly.js to extend further and embed in any website.
This package is still in an early development stage. Some details in the visualizations may not
look as perfect yet. I highly encourage you to use this package for exploratory analysis only.
If you ever decide to use the visualization in your publications, please consider changing
autoplotly() to ggfortify::autoplot() to get a better static plots or taking snapshots
of your autoplotly visualization.
We welcome suggestions and contributions from others. With this package, researchers will hopefully
spend less time focusing on learning ggplot2 syntax or interactive visualization packages like plotly.
Instead they can spend more time on their work and research. The source code of the package is located on
Github where users can test out development versions of
the package and provide feature requests, feedback and bug reports. We encourage you to submit your
issues and pull requests to help us make this package better for the R community.
In the future, we'll try to support a much wider range of objects through a larger coverage in ggfortify.
If you find any new use cases, please don't hesitate to submit an issue on Github and join us in the development!
Nothing could be done without all the efforts from developers of ggplot2, plotly, and ggfortify. I would like to thank
everyone for their time and efforts spent on visualizations in R and encourage others to join us to make our open-source
community even better!
broom, ggplot2, and ggfortify.