Merge pull request #520 from cmu-delphi/ndefries/epidatasets-migration

Import datasets and documentation from epidatasets

Author: brookslogan

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: epiprocess
 Title: Tools for basic signal processing in epidemiology
-Version: 0.9.4
+Version: 0.9.5
 Authors@R: c(
     person("Jacob", "Bien", role = "ctb"),
     person("Logan", "Brooks", , "[email protected]", role = c("aut", "cre")),
@@ -20,7 +20,13 @@ Authors@R: c(
     person("Hadley", "Wickham", role = "ctb",
            comment = "Author of included rlang fragments"),
     person("Posit", role = "cph",
-           comment = "Copyright holder of included rlang fragments")
+           comment = "Copyright holder of included rlang fragments"),
+    person("Johns Hopkins University Center for Systems Science and Engineering", role = "dtc",
+            comment = "Owner of COVID-19 cases and deaths data from the COVID-19 Data Repository"),
+    person("Johns Hopkins University", role = "cph",
+            comment = "Copyright holder of COVID-19 cases and deaths data from the COVID-19 Data Repository"),
+    person("Carnegie Mellon University Delphi Group", role = "dtc",
+            comment = "Owner of claims-based CLI data from the Delphi Epidata API")
   )
 Description: This package introduces a common data structure for
     epidemiological data reported by location and time, provides another
@@ -36,6 +42,7 @@ Imports:
     cli,
     data.table,
     dplyr (>= 1.1.0),
+    epidatasets,
     genlasso,
     ggplot2,
     glue,
@@ -64,6 +71,7 @@ Suggests:
 VignetteBuilder:
     knitr
 Remotes:
+    cmu-delphi/epidatasets,
     cmu-delphi/epidatr,
     glmgen/genlasso,
     reconverse/outbreaks
@@ -78,7 +86,6 @@ Collate:
     'archive.R'
     'autoplot.R'
     'correlation.R'
-    'data.R'
     'epi_df.R'
     'epi_df_forbidden_methods.R'
     'epiprocess.R'

NAMESPACE

@@ -59,8 +59,12 @@ export(as_epi_archive)
 export(as_epi_df)
 export(as_tsibble)
 export(autoplot)
+export(cases_deaths_subset)
 export(clone)
 export(complete)
+export(covid_case_death_rates_extended)
+export(covid_incidence_county_subset)
+export(covid_incidence_outliers)
 export(detect_outlr)
 export(detect_outlr_rm)
 export(detect_outlr_stl)
@@ -100,6 +104,7 @@ export(ungroup)
 export(unnest)
 export(validate_epi_archive)
 export(version_column_names)
+import(epidatasets)
 importFrom(checkmate,anyInfinite)
 importFrom(checkmate,anyMissing)
 importFrom(checkmate,assert)

NEWS.md

@@ -6,6 +6,17 @@ Pre-1.0.0 numbering scheme: 0.x will indicate releases, while 0.x.y will indicat
 
 ## Breaking changes
 
+- Moved example datasets from being hosted in the package to being reexported
+  from the `epidatasets` package. The datasets can no longer be loaded with
+  `data()` but can be accessed with `epiprocess::` or, after loading the
+  package, just the name of the dataset (#520). Those with names starting with
+  `jhu` have been renamed to a more uniform scheme and now have names starting
+  with `covid`. The data set previously named `jhu_confirmed_cumulative_num` has
+  been removed from the package, but a renamed version is has been removed from
+  the package, but a renamed version is still available in `epidatasets`.
+
+## Bug fixes
+
 - Removed `.window_size = 1` default from `epi_slide_{mean,sum,opt}`; this
   argument is now mandatory, and should nearly always be greater than 1 except
   for testing purposes.

R/autoplot.R

@@ -26,19 +26,19 @@
 #' @export
 #'
 #' @examples
-#' autoplot(jhu_csse_daily_subset, cases, death_rate_7d_av)
-#' autoplot(jhu_csse_daily_subset, case_rate_7d_av, .facet_by = "geo_value")
-#' autoplot(jhu_csse_daily_subset, case_rate_7d_av,
+#' autoplot(cases_deaths_subset, cases, death_rate_7d_av)
+#' autoplot(cases_deaths_subset, case_rate_7d_av, .facet_by = "geo_value")
+#' autoplot(cases_deaths_subset, case_rate_7d_av,
 #'   .color_by = "none",
 #'   .facet_by = "geo_value"
 #' )
-#' autoplot(jhu_csse_daily_subset, case_rate_7d_av,
+#' autoplot(cases_deaths_subset, case_rate_7d_av,
 #'   .color_by = "none",
 #'   .base_color = "red", .facet_by = "geo_value"
 #' )
 #'
 #' # .base_color specification won't have any effect due .color_by default
-#' autoplot(jhu_csse_daily_subset, case_rate_7d_av,
+#' autoplot(cases_deaths_subset, case_rate_7d_av,
 #'   .base_color = "red", .facet_by = "geo_value"
 #' )
 autoplot.epi_df <- function(

R/correlation.R

@@ -44,15 +44,15 @@
 #'
 #' # linear association of case and death rates on any given day
 #' epi_cor(
-#'   x = jhu_csse_daily_subset,
+#'   x = cases_deaths_subset,
 #'   var1 = case_rate_7d_av,
 #'   var2 = death_rate_7d_av,
 #'   cor_by = "time_value"
 #' )
 #'
 #' # correlation of death rates and lagged case rates
 #' epi_cor(
-#'   x = jhu_csse_daily_subset,
+#'   x = cases_deaths_subset,
 #'   var1 = case_rate_7d_av,
 #'   var2 = death_rate_7d_av,
 #'   cor_by = time_value,
@@ -61,15 +61,15 @@
 #'
 #' # correlation grouped by location
 #' epi_cor(
-#'   x = jhu_csse_daily_subset,
+#'   x = cases_deaths_subset,
 #'   var1 = case_rate_7d_av,
 #'   var2 = death_rate_7d_av,
 #'   cor_by = geo_value
 #' )
 #'
 #' # correlation grouped by location and incorporates lagged cases rates
 #' epi_cor(
-#'   x = jhu_csse_daily_subset,
+#'   x = cases_deaths_subset,
 #'   var1 = case_rate_7d_av,
 #'   var2 = death_rate_7d_av,
 #'   cor_by = geo_value,