Create extended covid rates data (#8)

* add extended version of covid_case_death_rates

* use syntax for new version of epiprocess

Author: nmdefries

R/epipredict-data.R

@@ -3,7 +3,7 @@
 #' This data source of confirmed COVID-19 cases and deaths is based on reports
 #' made available by the Center for Systems Science and Engineering at Johns
 #' Hopkins University, as downloaded from the CMU Delphi COVIDcast Epidata
-#' API. This example data is a snapshot as of March 20, 2024, and
+#' API. This example data is a snapshot as of May 31, 2022, and
 #' ranges from December 31, 2020 to December 31, 2021. It
 #' includes all states.
 #'

R/epiprocess-data.R

@@ -208,3 +208,42 @@
 #' * Furthermore, the data has been limited to a very small number of rows,
 #'   formatted into an `epi_df`, and the signal names slightly altered.
 "jhu_confirmed_cumulative_num"
+
+#' JHU daily COVID-19 cases and deaths rates from all states
+#'
+#' This data source of confirmed COVID-19 cases and deaths is based on reports
+#' made available by the Center for Systems Science and Engineering at Johns
+#' Hopkins University, as downloaded from the CMU Delphi COVIDcast Epidata
+#' API. This example data is a snapshot as of May 31, 2022, and
+#' ranges from March 1, 2020 to December 31, 2021. It
+#' includes all states.
+#'
+#' @format An [`epiprocess::epi_df`] (object of class `c("epi_df", "tbl_df", "tbl", "data.frame")`) with 37576 rows and 4 columns.
+#' @section Data dictionary:
+#' The data has columns:
+#' \describe{
+#'   \item{geo_value}{the geographic value associated with each row
+#'       of measurements.}
+#'   \item{time_value}{the time value associated with each row of measurements.}
+#'   \item{case_rate}{7-day average signal of number of new
+#'       confirmed COVID-19 cases per 100,000 population, daily}
+#'   \item{death_rate}{7-day average signal of number of new confirmed
+#'       deaths due to COVID-19 per 100,000 population, daily}
+#' }
+#' @source This object contains a modified part of the
+#'   \href{https://github.com/CSSEGISandData/COVID-19}{COVID-19 Data Repository by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University}
+#'   as \href{https://cmu-delphi.github.io/delphi-epidata/api/covidcast-signals/jhu-csse.html}{republished in the COVIDcast Epidata API}.
+#'   This data set is licensed under the terms of the
+#'   \href{https://creativecommons.org/licenses/by/4.0/}{Creative Commons Attribution 4.0 International license}
+#'   by the Johns Hopkins University on behalf of its Center for Systems Science
+#'   in Engineering. Copyright Johns Hopkins University 2020.
+#'
+#' Modifications:
+#' * \href{https://cmu-delphi.github.io/delphi-epidata/api/covidcast-signals/jhu-csse.html}{From the COVIDcast Epidata API}:
+#'   These signals are taken directly from the JHU CSSE
+#'   \href{https://github.com/CSSEGISandData/COVID-19}{COVID-19 GitHub repository}
+#'   without changes. The 7-day average signals are computed by Delphi by
+#'   calculating moving averages of the preceding 7 days, so the signal for
+#'   June 7 is the average of the underlying data for June 1 through 7,
+#'   inclusive.
+"covid_case_death_rates_extended"

R/sysdata.rda

@@ -47,26 +47,17 @@ case_death_rate_archive_tbl <- epix_merge(
 # Calculate 7-day averages for case and death rates.
 case_death_rate_archive_tbl <- case_death_rate_archive_tbl %>%
   epix_slide(
-    before = 365000L, ref_time_values = fc_time_values,
+    .before = 365000L, .versions = fc_time_values,
     function(x, gk, rtv) {
       x %>%
         group_by(geo_value) %>%
-        epi_slide_mean(case_rate, before = 6L) %>%
+        epi_slide_mean(case_rate, .align = "right", .window_size = 7L) %>%
         rename(case_rate_7d_av = slide_value_case_rate) %>%
-        epi_slide_mean(death_rate, before = 6L) %>%
+        epi_slide_mean(death_rate, .align = "right", .window_size = 7L) %>%
         ungroup() %>%
         rename(death_rate_7d_av = slide_value_death_rate)
     }
   ) %>%
-  rename(
-    version = time_value,
-    time_value = slide_value_time_value,
-    geo_value = slide_value_geo_value,
-    case_rate = slide_value_case_rate,
-    death_rate = slide_value_death_rate,
-    case_rate_7d_av = slide_value_case_rate_7d_av,
-    death_rate_7d_av = slide_value_death_rate_7d_av
-  ) %>%
   as_epi_archive(compactify = TRUE)
 # Convert DT component back to tibble.
 case_death_rate_archive_tbl <- case_death_rate_archive_tbl$DT %>%

data-raw/case_death_rate_archive_tbl.R

@@ -0,0 +1,39 @@
+library(dplyr)
+library(epidatr)
+
+source(here::here("data-raw/_helper.R"))
+
+d <- as.Date("2022-05-31")
+
+x <- pub_covidcast(
+  source = "jhu-csse",
+  signals = "confirmed_7dav_incidence_prop",
+  time_type = "day",
+  geo_type = "state",
+  time_values = epirange(20200301, 20201231 - 1),
+  geo_values = "*",
+  as_of = d
+) %>%
+  select(geo_value, time_value, case_rate = value)
+
+y <- pub_covidcast(
+  source = "jhu-csse",
+  signals = "deaths_7dav_incidence_prop",
+  time_type = "day",
+  geo_type = "state",
+  time_values = epirange(20200301, 20201231 - 1),
+  geo_values = "*",
+  as_of = d
+) %>%
+  select(geo_value, time_value, death_rate = value)
+
+covid_case_death_rates_extension_tbl <- x %>%
+  full_join(y, by = c("geo_value", "time_value")) %>%
+  as_tibble()
+
+# We're trying to do:
+#   usethis::use_data(covid_case_death_rates_extension_tbl, internal = TRUE, overwrite = TRUE, compress = "xz")
+# but `usethis::use_data` can only store multiple objects if they're added in
+# the same call. This workaround is from
+# https://github.com/r-lib/usethis/issues/1512
+save_to_sysdata(covid_case_death_rates_extension_tbl, "covid_case_death_rates_extension_tbl")

data-raw/covid_case_death_rates_extension_tbl.R

@@ -0,0 +1,17 @@
+delayedAssign("covid_case_death_rates_extended", local({
+  if (requireNamespace("epiprocess", quietly = TRUE)) {
+    d <- as.Date("2022-05-31")
+    epiprocess::as_epi_df(
+      dplyr::bind_rows(
+        epidatasets:::covid_case_death_rates_extension_tbl,
+        epidatasets:::covid_case_death_rates_tbl
+      )
+      , as_of = d)
+  } else {
+    warning("Since the package `epiprocess` is not installed, this object will be loaded as a tibble (class `tbl_df`)")
+    dplyr::bind_rows(
+      epidatasets:::covid_case_death_rates_extension_tbl,
+      epidatasets:::covid_case_death_rates_tbl
+    )
+  }
+}))