Merge pull request #382 from cmu-delphi/ndefries/epidatasets-migration

Ndefries/epidatasets migration

Author: nmdefries

DESCRIPTION

@@ -25,6 +25,7 @@ URL: https://github.com/cmu-delphi/epipredict/,
 BugReports: https://github.com/cmu-delphi/epipredict/issues/
 Depends:
     epiprocess (>= 0.9.0),
+    epidatasets,
     parsnip (>= 1.0.0),
     R (>= 3.5.0)
 Imports:
@@ -49,7 +50,6 @@ Imports:
     workflows (>= 1.0.0)
 Suggests:
     data.table,
-    epidatasets,
     epidatr (>= 1.0.0),
     fs,
     grf,
@@ -69,6 +69,7 @@ Suggests:
 VignetteBuilder:
     knitr
 Remotes:
+    cmu-delphi/epidatasets,
     cmu-delphi/epidatr,
     cmu-delphi/epiprocess,
     dajmcdon/smoothqr

NAMESPACE

@@ -215,6 +215,7 @@ export(update_model)
 export(validate_layer)
 export(weighted_interval_score)
 import(distributional)
+import(epidatasets)
 import(epiprocess)
 import(parsnip)
 import(recipes)

NEWS.md

@@ -4,12 +4,21 @@ Pre-1.0.0 numbering scheme: 0.x will indicate releases, while 0.0.x will indicat
 
 # epipredict 0.2
 
-## features
+## Breaking changes
+
+- Moved example datasets from being hosted in the package to being loaded
+  from the `epidatasets` package. The datasets can no longer be loaded with
+  `data(<dataset name>)`, but can be accessed with 
+  `data(<dataset name>, package = "epidatasets")`, `epidatasets::<dataset name>` 
+  or, after loading the package, the name of the dataset alone (#382).
+
+## Improvements
+
 - Add `step_adjust_latency`, which give several methods to adjust the forecast if the `forecast_date` is after the last day of data.
 - (temporary) ahead negative is allowed for `step_epi_ahead` until we have `step_epi_shift`
 
-## bugfixes
-- shifting no columns results in no error for either `step_epi_ahead` and `step_epi_lag`
+## Bug fixes
+- Shifting no columns results in no error for either `step_epi_ahead` and `step_epi_lag`
 - Quantiles produced by `grf` were sometimes out of order.
 
 # epipredict 0.1

R/arx_classifier.R

@@ -27,7 +27,7 @@
 #'
 #' @examples
 #' library(dplyr)
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value >= as.Date("2021-11-01"))
 #'
 #' out <- arx_classifier(jhu, "death_rate", c("case_rate", "death_rate"))
@@ -104,7 +104,7 @@ arx_classifier <- function(
 #' @seealso [arx_classifier()]
 #' @examples
 #' library(dplyr)
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value >= as.Date("2021-11-01"))
 #'
 #' arx_class_epi_workflow(jhu, "death_rate", c("case_rate", "death_rate"))

R/arx_forecaster.R

@@ -25,7 +25,7 @@
 #' @seealso [arx_fcast_epi_workflow()], [arx_args_list()]
 #'
 #' @examples
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   dplyr::filter(time_value >= as.Date("2021-12-01"))
 #'
 #' out <- arx_forecaster(
@@ -96,7 +96,7 @@ arx_forecaster <- function(
 #'
 #' @examples
 #' library(dplyr)
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value >= as.Date("2021-12-01"))
 #'
 #' arx_fcast_epi_workflow(

R/autoplot.R

@@ -29,7 +29,7 @@ ggplot2::autoplot
 #' @name autoplot-epipred
 #' @examples
 #' library(dplyr)
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value >= as.Date("2021-11-01"))
 #'
 #' r <- epi_recipe(jhu) %>%
@@ -70,7 +70,7 @@ ggplot2::autoplot
 #'
 #' # ------- Plotting canned forecaster output
 #'
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value >= as.Date("2021-11-01"))
 #' flat <- flatline_forecaster(jhu, "death_rate")
 #' autoplot(flat, .max_facets = 4)

R/cdc_baseline_forecaster.R

@@ -23,7 +23,7 @@
 #'
 #' @examples
 #' library(dplyr)
-#' weekly_deaths <- case_death_rate_subset %>%
+#' weekly_deaths <- covid_case_death_rates %>%
 #'   select(geo_value, time_value, death_rate) %>%
 #'   left_join(state_census %>% select(pop, abbr), by = c("geo_value" = "abbr")) %>%
 #'   mutate(deaths = pmax(death_rate / 1e5 * pop * 7, 0)) %>%

R/data.R

@@ -43,7 +43,7 @@ epi_recipe.default <- function(x, ...) {
 #' @examples
 #' library(dplyr)
 #' library(recipes)
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value > "2021-08-01") %>%
 #'   arrange(geo_value, time_value)
 #'
@@ -263,7 +263,7 @@ is_epi_recipe <- function(x) {
 #' library(dplyr)
 #' library(recipes)
 #'
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value > "2021-08-01") %>%
 #'   arrange(geo_value, time_value)
 #'
@@ -347,7 +347,7 @@ update_epi_recipe <- function(x, recipe, ..., blueprint = default_epi_recipe_blu
 #' library(dplyr)
 #' library(workflows)
 #'
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value > "2021-11-01", geo_value %in% c("ak", "ca", "ny"))
 #' r <- epi_recipe(jhu) %>%
 #'   step_epi_lag(death_rate, lag = c(0, 7, 14)) %>%

R/epi_recipe.R

@@ -20,7 +20,7 @@
 #' @importFrom generics augment
 #' @export
 #' @examples
-#' jhu <- case_death_rate_subset
+#' jhu <- covid_case_death_rates
 #'
 #' r <- epi_recipe(jhu) %>%
 #'   step_epi_lag(death_rate, lag = c(0, 7, 14)) %>%
@@ -84,7 +84,7 @@ is_epi_workflow <- function(x) {
 #' @name fit-epi_workflow
 #' @export
 #' @examples
-#' jhu <- case_death_rate_subset %>%
+#' jhu <- covid_case_death_rates %>%
 #'   filter(time_value > "2021-11-01", geo_value %in% c("ak", "ca", "ny"))
 #'
 #' r <- epi_recipe(jhu) %>%
@@ -142,7 +142,7 @@ fit.epi_workflow <- function(object, data, ..., control = workflows::control_wor
 #' @name predict-epi_workflow
 #' @export
 #' @examples
-#' jhu <- case_death_rate_subset
+#' jhu <- covid_case_death_rates
 #'
 #' r <- epi_recipe(jhu) %>%
 #'   step_epi_lag(death_rate, lag = c(0, 7, 14)) %>%