Movatterモバイル変換

ggalluvial

This is aggplot2extension for alluvial plots.

Design

The alluvial plots implemented here can be used to visualizefrequency distributions over time or frequency tables involving severalcategorical variables. The design is inspired by thealluvialpackage, but theggplot2 framework induced severalconspicuous differences:

• alluvial understands a variety of inputs (vectors,lists, data frames), whereasggalluvial requires asingle data frame;
• alluvial uses each variable of these inputs as adimension of the data, whereasggalluvial requires theuser to specify the dimensions, either as separate aesthetics or askey-value pairs;
• alluvial produces both thealluvia, whichlink cohorts across multiple dimensions, and (what are here called) thestrata, which partition the data along each dimension, in asingle function; whereasggalluvial relies on separatelayers (stats and geoms) to produce strata, alluvia, and alluvialsegments calledlodes andflows.

Additionally,ggalluvial arranges these layersvertically without gaps, so that the secondary plotting axis indicatesthe cumulative values of the strata at each dimension.

Installation

The latest stable release can be installed from CRAN:

install.packages("ggalluvial")

Thecranbranch will contain the version most recently submitted toCRAN. It isduplicated in themaster branch, from which source thewebsite isbuilt.

The development version can be installed from the (default)main branch on GitHub:

remotes::install_github("corybrunson/ggalluvial@main",build_vignettes =TRUE)

Note that, in order to build the vignettes, the imported packagesalluvial,ggfittext, andggrepel must be installed. To skip this step, leavebuild_vignettes unspecified or set it toFALSE.

Theoptimizationbranch contains a development version with experimental functions toreduce the number or area of alluvial overlaps (see issue#6).Install it as follows:

remotes::install_github("corybrunson/ggalluvial",ref ="optimization")

Note, however, that this branch has not kept pace with themain branch or with recent upgrades on CRAN.

Usage

Example

Here is how to generate an alluvial plot representation of themulti-dimensional categorical dataset of passengers on the Titanic:

titanic_wide<-data.frame(Titanic)head(titanic_wide)#>   Class    Sex   Age Survived Freq#> 1   1st   Male Child       No    0#> 2   2nd   Male Child       No    0#> 3   3rd   Male Child       No   35#> 4  Crew   Male Child       No    0#> 5   1st Female Child       No    0#> 6   2nd Female Child       No    0ggplot(data = titanic_wide,aes(axis1 = Class,axis2 = Sex,axis3 = Age,y = Freq))+scale_x_discrete(limits =c("Class","Sex","Age"),expand =c(.2, .05))+xlab("Demographic")+geom_alluvium(aes(fill = Survived))+geom_stratum()+geom_text(stat ="stratum",aes(label =after_stat(stratum)))+theme_minimal()+ggtitle("passengers on the maiden voyage of the Titanic","stratified by demographics and survival")

The data is in “wide” format, butggalluvial alsorecognizes data in “long” format and can convert between the two:

titanic_long<-to_lodes_form(data.frame(Titanic),key ="Demographic",axes =1:3)head(titanic_long)#>   Survived Freq alluvium Demographic stratum#> 1       No    0        1       Class     1st#> 2       No    0        2       Class     2nd#> 3       No   35        3       Class     3rd#> 4       No    0        4       Class    Crew#> 5       No    0        5       Class     1st#> 6       No    0        6       Class     2ndggplot(data = titanic_long,aes(x = Demographic,stratum = stratum,alluvium = alluvium,y = Freq,label = stratum))+geom_alluvium(aes(fill = Survived))+geom_stratum()+geom_text(stat ="stratum")+theme_minimal()+ggtitle("passengers on the maiden voyage of the Titanic","stratified by demographics and survival")

Documentation

For detailed discussion of the data formats recognized byggalluvial and several examples that illustrate itsflexibility and limitations, read the technical vignette:

vignette(topic ="ggalluvial",package ="ggalluvial")

Several additional vignettes offer detailed solutions to specificneeds:

• “Labeling small strata” ("labels") for how to elegantlylabel strata of a wide range of heights in an alluvial plot;
• “The Order of the Rectangles” ("order-rectangles") forhow to control the positioning of strata and lodes in an alluvial plot;and
• “Tooltips for ggalluvial plots in Shiny apps” ("shiny")for how to incorporate alluvial plots into interactive apps.

The object documentation includes several more examples. Usehelp() to call forth more detail on

• any layer (stat_* orgeom_*),
• the conversion functions (to_*_form), and
• the data sets installed with the package (vaccinationsandmajors).

Short form

For some more digestible guidance on usingggalluvial, check out three cheat sheets and demos bystudents in Joyce Robbins’sExploratory DataAnalysis and Visualization Community Contribution Project:

• anintroductionby Meggie Wen (Chapter 33)
• acheatsheet by Qingyi Zhang (Chapter 14)
• ablogabout how this package implements alluvial plots by Arnav Saxena(Chapter 134)

Acknowledgments

Resources

Development of this package benefitted from the use of equipment andthe support of colleagues atUConnHealth and atUF Health.

Contribute

Contributions in any form are more than welcome! Pretty much everyfix and feature of this package derives from a problem or question posedby someone with datasets or design goals i hadn’t anticipated. See theCONTRIBUTINGfile for guidance, and please respect theCodeof Conduct.

Cite

If you useggalluvial-generated figures inpublication, i’d be grateful to hear about it! You can also cite thepackage according tocitation("ggalluvial").