fix: manually do smoothing in jhu_csse_daily_subset, regenerate

NEWS.md

@@ -12,18 +12,13 @@ Pre-1.0.0 numbering scheme: 0.x will indicate releases, while 0.x.y will indicat
 * regenerated the `jhu_csse_daily_subset` dataset with the latest versions of
   the data from the API
 * changed approach to versioning, see DEVELOPMENT.md for details
-
-# epiprocess 0.7.1.9999
+* `select` on grouped `epi_df`s now only drops `epi_df`ness if it makes sense; PR #390
+* Minor documentation updates; PR #393
 
 ## Breaking changes
 
 * Switched `epi_df`'s `other_keys` default from `NULL` to `character(0)`; PR #390
 
-## Improvements
-
-* `select` on grouped `epi_df`s now only drops `epi_df`ness if it makes sense; PR #390
-* Minor documentation updates; PR #393
-
 # epiprocess 0.7.0
 
 ## Improvements

R/data.R

@@ -28,15 +28,15 @@
 #'   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.
-#' * Furthermore, the data has been limited to a very small number of rows,
-#'   the signal names slightly altered, and formatted into a tibble.
+#' * \href{https://cmu-delphi.github.io/delphi-epidata/api/covidcast-signals/jhu-csse.html}{From
+#'   the COVIDcast Epidata API}: The case signal is taken directly from the JHU
+#'   CSSE \href{https://github.com/CSSEGISandData/COVID-19}{COVID-19 GitHub
+#'   repository}. The rate signals were computed by Delphi using Census
+#'   population data. The 7-day average signals were 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.
+#' * Furthermore, the data has been limited to a very small number of rows, the
+#'   signal names slightly altered, and formatted into a tibble.
 "jhu_csse_daily_subset"
 
 

data-raw/jhu_csse_daily_subset.R

@@ -2,58 +2,58 @@ library(epidatr)
 library(epiprocess)
 library(dplyr)
 
-confirmed_7dav_incidence_prop <- pub_covidcast(
+confirmed_incidence_num <- pub_covidcast(
   source = "jhu-csse",
-  signals = "confirmed_7dav_incidence_prop",
+  signals = "confirmed_incidence_num",
   geo_type = "state",
   time_type = "day",
   geo_values = "ca,fl,ny,tx,ga,pa",
   time_values = epirange(20200301, 20211231),
 ) %>%
-  select(geo_value, time_value, case_rate_7d_av = value) %>%
+  select(geo_value, time_value, cases = value) %>%
   arrange(geo_value, time_value)
 
-deaths_7dav_incidence_prop <- pub_covidcast(
+confirmed_7dav_incidence_num <- pub_covidcast(
   source = "jhu-csse",
-  signals = "deaths_7dav_incidence_prop",
+  signals = "confirmed_7dav_incidence_num",
   geo_type = "state",
   time_type = "day",
   geo_values = "ca,fl,ny,tx,ga,pa",
   time_values = epirange(20200301, 20211231),
 ) %>%
-  select(geo_value, time_value, death_rate_7d_av = value) %>%
+  select(geo_value, time_value, cases_7d_av = value) %>%
   arrange(geo_value, time_value)
 
-confirmed_incidence_num <- pub_covidcast(
+confirmed_7dav_incidence_prop <- pub_covidcast(
   source = "jhu-csse",
-  signals = "confirmed_incidence_num",
+  signals = "confirmed_7dav_incidence_prop",
   geo_type = "state",
   time_type = "day",
   geo_values = "ca,fl,ny,tx,ga,pa",
   time_values = epirange(20200301, 20211231),
 ) %>%
-  select(geo_value, time_value, cases = value) %>%
+  select(geo_value, time_value, case_rate_7d_av = value) %>%
   arrange(geo_value, time_value)
 
-confirmed_7dav_incidence_num <- pub_covidcast(
+deaths_7dav_incidence_prop <- pub_covidcast(
   source = "jhu-csse",
-  signals = "confirmed_7dav_incidence_num",
+  signals = "deaths_7dav_incidence_prop",
   geo_type = "state",
   time_type = "day",
   geo_values = "ca,fl,ny,tx,ga,pa",
   time_values = epirange(20200301, 20211231),
 ) %>%
-  select(geo_value, time_value, cases_7d_av = value) %>%
+  select(geo_value, time_value, death_rate_7d_av = value) %>%
   arrange(geo_value, time_value)
 
-jhu_csse_daily_subset <- confirmed_7dav_incidence_prop %>%
-  full_join(deaths_7dav_incidence_prop,
+jhu_csse_daily_subset <- confirmed_incidence_num %>%
+  full_join(confirmed_7dav_incidence_num,
     by = c("geo_value", "time_value")
   ) %>%
-  full_join(confirmed_incidence_num,
+  full_join(confirmed_7dav_incidence_prop,
     by = c("geo_value", "time_value")
   ) %>%
-  full_join(confirmed_7dav_incidence_num,
+  full_join(deaths_7dav_incidence_prop,
     by = c("geo_value", "time_value")
   ) %>%
   as_epi_df()