An R package that provides access to the code and data sets published by FiveThirtyEight Note that while we received guidance from editors at 538, this package is not officially published by 538.


Get the released version from CRAN:


Or the development version from GitHub:

# If you haven't installed devtools yet, do so:
# install.packages("devtools")


Example Usage


# Bechdel data set (note that data is lazy loaded so one can also just access `bechdel` without running `data(bechdel)`):
# If using RStudio:

# To see a list of all data sets:
data(package = "fivethirtyeight")

# To see a more detailed list of all data sets, see the package vignette:
vignette("fivethirtyeight", package = "fivethirtyeight")

Data Analysis Examples in Vignettes

For some data sets, there is an example analysis in a package vignette. For example, we did this using the R code for the article The Dollar-And-Cents Case Against Hollywood’s Exclusion of Women here:

vignette("bechdel", package = "fivethirtyeight")

For a complete list of vignettes run:

browseVignettes(package = "fivethirtyeight")

More Information

  • Andrew Flowers gave a great demonstration of the package and the bechdel vignette during his rstudio::conf talk in Orlando, Florida in January. The video of his talk is available here.
  • We’re now featured on Kaggle!
  • Click this Google Sheet for a master spreadsheet connecting
    1. the original 538 data on GitHub with
    2. the data frames in the package with
    3. information on the corresponding article
  • See the package vignette for:
    1. Our motivation for creating this package.
    2. Guidelines we followed preparing the data sets and links to the code.
    3. A more detailed list of all data sets.
vignette("fivethirtyeight", package = "fivethirtyeight")


Data Analysis Examples in Vignettes

In many instances, the data sets on the original 538 GitHub repository had the R code used in the analysis. We would love to have these, or any other interesting analyses, in the form of package vignettes. We ask you follow these guidelines as much as possible:

  1. Use tidyverse packages: ggplot2, dplyr, tidyr, modelr, etc.
  2. Use R Markdown:
    • In particular the Package Vignette (HTML) template option when creating an R Markdown document.
    • Have the name of the R Markdown file match the name of the data set. Ex: vignettes/bechdel.Rmd
  3. Follow the GitHub fork/pull request model. Otherwise, contact us directly.

Contributing to the Package

If you want to contribute to the package:

  • We followed the principles in Hadley Wickham’s R packages book
  • Preliminary instructions for automating R package documentation and collecting data about the data sets is available here.