The Delphi Epidata API provides real-time access to epidemiological surveillance data for influenza, COVID-19, and other diseases from both official government sources such as the Centers for Disease Control and Prevention (CDC), private partners such as Facebook (now Meta) and Change Healthcare, and other public datasets like Google Trends. It is built and maintained by the Carnegie Mellon University Delphi Research Group.
Today we introduce the R package epidatr
, available on
CRAN, with the
source and development on github.
This package is designed to streamline the downloading and usage of data from the Delphi Epidata API. It provides a simple R interface to the API, including functions for downloading data, parsing the results, and converting the data into a tidy format. The API stores a historical record of all data, including corrections and updates, which is particularly useful for accurately backtesting forecasting models. We also provide packages for downstream data processing (epiprocess) and modeling (epipredict).
library(epidatr)
# Obtain the smoothed covid-like illness (CLI) signal from Delphi's US COVID-19
# Trends and Impact Survey (CTIS), in partnership with Facebook, as it was on
# April 10, 2021 for the US at the national level
epidata <- pub_covidcast(
source = "fb-survey",
signals = "smoothed_cli",
geo_type = "nation",
time_type = "day",
geo_values = "us",
time_values = epirange(20210101, 20210601),
as_of = 20210601
)
epidata
# A tibble: 151 × 15
geo_value signal source geo_type time_type time_value
<chr> <chr> <chr> <fct> <fct> <date>
1 us smoothed_cli fb-su… nation day 2021-01-01
2 us smoothed_cli fb-su… nation day 2021-01-02
3 us smoothed_cli fb-su… nation day 2021-01-03
4 us smoothed_cli fb-su… nation day 2021-01-04
5 us smoothed_cli fb-su… nation day 2021-01-05
6 us smoothed_cli fb-su… nation day 2021-01-06
7 us smoothed_cli fb-su… nation day 2021-01-07
8 us smoothed_cli fb-su… nation day 2021-01-08
9 us smoothed_cli fb-su… nation day 2021-01-09
10 us smoothed_cli fb-su… nation day 2021-01-10
# ℹ 141 more rows
# ℹ 9 more variables: direction <dbl>, issue <date>,
# lag <dbl>, missing_value <dbl>, missing_stderr <dbl>,
# missing_sample_size <dbl>, value <dbl>, stderr <dbl>,
# sample_size <dbl>
# ℹ Use `print(n = ...)` to see more rows
Installing the package is straightforward.
# Install the CRAN version
pak::pkg_install("epidatr")
# Install the development version from the GitHub dev branch
pak::pkg_install("cmu-delphi/epidatr@dev")
The Delphi API requires a (free) API key for full functionality. To generate
your key, register for a pseudo-anonymous account
here and see more
discussion on the general API
website. The
epidatr
client will automatically look for this key in the environment
variable DELPHI_EPIDATA_KEY
. We recommend storing your key in your .Renviron
file, which R will read by default.
Note that for the time being, the private endpoints (i.e. those prefixed with
pvt
) will require a separate key that needs to be passed as an argument.
The covidcast
package is deprecated and will no longer be updated. The
epidatr
package is a complete rewrite of the covidcast
package, with a focus on
speed, reliability, and ease of use. It also supports more endpoints and data
sources than covidcast
. When migrating from that package, you will need to use
the
pub_covidcast
function in epidatr
.