Merge branch 'master' into pr/433

RichardMN · Feb 4, 2022 · b077c70 · b077c70
2 parents 3e2f873 + 097708f
commit b077c70
Show file tree

Hide file tree

Showing 41 changed files with 178 additions and 254 deletions.
diff --git a/.github/workflows/draft-pdf.yml b/.github/workflows/draft-pdf.yml
diff --git a/.github/workflows/pr-checklist.yaml b/.github/workflows/pr-checklist.yaml
@@ -14,4 +14,4 @@ jobs:
               issue_number: context.issue.number,
               owner: context.repo.owner,
               repo: context.repo.repo,
-              body: '👋 Thanks for opening this pull request! Can you please run through the following checklist before requesting review (ticking as complete or if not relevant). \n\n - [ ] Read our [contribution guidelines](https://github.com/epiforecasts/covidregionaldata/wiki/Contributing) if you have not already done so. \n- [ ] If you have altered an existing class please run the tests locally (using `devtools::load_all(); devtools::test()`) first setting `options(testDownload=TRUE, testSource=class-name)` and report your findings. \n- [ ] If you have added a new data class please run the tests locally for that class (using `devtools::load_all(); devtools::test()`). \n- [ ] Check your code passes our CI checks and review any style and code coverage warnings. \n- [ ] Comment with details if unable to get our CI checks to pass or unable to remove all warnings. \n\nThank you again for the contribution. If making large scale changes consider using our `pre-commit` hooks (see the [contributing guide](https://github.com/epiforecasts/covidregionaldata/wiki/Contributing)) to more easily comply with our guidelines.'})
+              body: '👋 Thanks for opening this pull request! Can you please run through the following checklist before requesting review (ticking as complete or if not relevant). \n\n - [ ] Read our [contribution guidelines](https://github.com/epiforecasts/covidregionaldata/wiki/Contributing) if you have not already done so. \n- [ ] If you have altered an existing class please run the tests locally (using `devtools::load_all(); devtools::test()`) first setting `options(testDownload=TRUE, testSource=class-name)` and report your findings. \n- [ ] If you have added a new data class please run the tests locally for that class (using `devtools::load_all(); devtools::test()`). \n- [ ] Check your code passes our CI checks and review any style and code coverage warnings. \n- [ ] Comment with details if unable to get our CI checks to pass or unable to remove all warnings. \n- [ ] Update the [news](https://github.com/epiforecasts/covidregionaldata/blob/master/NEWS.md) file with information on your changes (crediting yourself at the same time) \n\nThank you again for the contribution. If making large scale changes consider using our `pre-commit` hooks (see the [contributing guide](https://github.com/epiforecasts/covidregionaldata/wiki/Contributing)) to more easily comply with our guidelines.'})
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -93,19 +93,14 @@ Imports:
     jsonlite,
     lifecycle,
     lubridate,
-    magrittr,
     memoise,
     purrr,
     R6,
     readxl,
     rlang,
-    stringi,
     stringr,
-    tibble,
     tidyr (>= 1.0.0),
-    tidyselect,
     vroom,
-    withr,
     xml2
 Suggests:
     ggplot2,

diff --git a/NAMESPACE b/NAMESPACE
@@ -48,12 +48,14 @@ importFrom(countrycode,countrycode)
 importFrom(countrycode,countryname)
 importFrom(dplyr,"%>%")
 importFrom(dplyr,across)
+importFrom(dplyr,all_of)
 importFrom(dplyr,arrange)
 importFrom(dplyr,as_tibble)
 importFrom(dplyr,bind_rows)
 importFrom(dplyr,count)
 importFrom(dplyr,distinct)
 importFrom(dplyr,do)
+importFrom(dplyr,ends_with)
 importFrom(dplyr,everything)
 importFrom(dplyr,filter)
 importFrom(dplyr,full_join)
@@ -79,6 +81,7 @@ importFrom(dplyr,summarise)
 importFrom(dplyr,tally)
 importFrom(dplyr,tibble)
 importFrom(dplyr,transmute)
+importFrom(dplyr,tribble)
 importFrom(dplyr,ungroup)
 importFrom(dplyr,vars)
 importFrom(httr,GET)
@@ -97,10 +100,10 @@ importFrom(lubridate,month)
 importFrom(lubridate,year)
 importFrom(lubridate,ymd)
 importFrom(lubridate,ymd_hms)
-importFrom(magrittr,"%>%")
 importFrom(memoise,cache_filesystem)
 importFrom(memoise,memoise)
 importFrom(purrr,compact)
+importFrom(purrr,keep)
 importFrom(purrr,map)
 importFrom(purrr,map_chr)
 importFrom(purrr,map_lgl)
@@ -115,17 +118,12 @@ importFrom(rlang,"!!")
 importFrom(rlang,":=")
 importFrom(rlang,.data)
 importFrom(rlang,syms)
-importFrom(stringi,stri_replace_all)
-importFrom(stringi,stri_trans_general)
-importFrom(stringi,stri_trim_both)
+importFrom(stringr,str_conv)
 importFrom(stringr,str_detect)
 importFrom(stringr,str_replace_all)
 importFrom(stringr,str_to_sentence)
 importFrom(stringr,str_to_title)
-importFrom(tibble,add_column)
-importFrom(tibble,as_tibble)
-importFrom(tibble,tibble)
-importFrom(tibble,tribble)
+importFrom(stringr,str_trim)
 importFrom(tidyr,complete)
 importFrom(tidyr,drop_na)
 importFrom(tidyr,fill)
@@ -135,13 +133,8 @@ importFrom(tidyr,pivot_longer)
 importFrom(tidyr,pivot_wider)
 importFrom(tidyr,replace_na)
 importFrom(tidyr,separate)
-importFrom(tidyselect,all_of)
-importFrom(tidyselect,ends_with)
-importFrom(tidyselect,starts_with)
-importFrom(tidyselect,vars_select_helpers)
 importFrom(utils,download.file)
 importFrom(utils,untar)
 importFrom(vroom,vroom)
-importFrom(withr,with_envvar)
 importFrom(xml2,xml_find_first)
 importFrom(xml2,xml_text)
diff --git a/NEWS.md b/NEWS.md
@@ -6,11 +6,15 @@ This release is currently under development
 
 * Support for level 1 region data in Estonia (thanks to @RichardMN). See `?Estonia` for details.
 * Support for level 1 region data in Vietnam (thanks to @biocyberman). See `?Vietnam` for details.
-* Support for level 2 region data in Colombia has been added (thanks to @RichardMN). The package no longer relies on aggregation by another project but takes data direct from the Colombia open data API. This uses the `RSocrata` package, which is suggested but not required. Using the `RSocrata` package cuts download volume and time by a factor of about 8.
 
 ## Other changes
 
+* Change the data source for Switzerland to draw data from the Swiss Federal Office of Public Health (FOPH)
 * Updated the package logo to include the newly supported data sets.
+* Reduced the number of package dependencies (@bisaloo and @RichardMN)
+## Bug fixes
+
+- Fixed a bug in the data sourced from Germany so that instead of treating it as a line list of individuals it is treated as a relatively finely resolved count data which needs to be summed up (by @sbfnk).
 
 # covidregionaldata 0.9.2
 

diff --git a/R/Belgium.R b/R/Belgium.R
@@ -57,13 +57,13 @@ Belgium <- R6::R6Class("Belgium",
     source_url = "https://epistat.wiv-isp.be/covid/",
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble tribble
+    #' @importFrom dplyr tibble tribble
     set_region_codes = function() {
-      self$codes_lookup$`1` <- tibble::tibble(
+      self$codes_lookup$`1` <- tibble(
         level_1_region_code = c("BE-BRU", "BE-VLG", "BE-WAL"),
         level_1_region = c("Brussels", "Flanders", "Wallonia")
       )
-      self$codes_lookup$`2` <- tibble::tribble(
+      self$codes_lookup$`2` <- tribble(
         ~level_2_region_code, ~level_2_region, ~level_1_region_code,
         "BE-VAN", "Antwerpen", "BE-VLG",
         "BE-WBR", "BrabantWallon", "BE-WAL",
@@ -82,8 +82,7 @@ Belgium <- R6::R6Class("Belgium",
 
     #' @description Downloads data from source and (for Belgium)
     #' applies an initial data patch.
-    #' @importFrom dplyr select mutate filter bind_rows
-    #' @importFrom tibble tribble
+    #' @importFrom dplyr select mutate filter bind_rows tribble
     download = function() {
       # do the actual downloading using the parent download method
       super$download()
@@ -92,7 +91,7 @@ Belgium <- R6::R6Class("Belgium",
       # For now, we filter out the broken lines and replace them
       # with the following data shim
 
-      fixed_lines <- tibble::tribble(
+      fixed_lines <- tribble(
         ~DATE, ~PROVINCE, ~REGION, ~AGEGROUP, ~SEX, ~CASES,
         "2020-04-22", "Limburg", "Flanders", "50-59", "F", 10,
         "2021-02-17", "VlaamsBrabant", "Flanders", "10-19", "M", 12

diff --git a/R/Brazil.R b/R/Brazil.R
@@ -47,7 +47,7 @@ Brazil <- R6::R6Class("Brazil",
     source_url = "https://github.com/wcota/covid19br/blob/master/README.en.md",
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tribble
+    #' @importFrom dplyr tibble
     set_region_codes = function() {
       self$codes_lookup <- tibble(
         state_name = c(

diff --git a/R/Canada.R b/R/Canada.R
@@ -44,7 +44,7 @@ Canada <- R6::R6Class("Canada",
     source_url = "https://open.canada.ca/data/en/dataset/261c32ab-4cfd-4f81-9dea-7b64065690dc", # nolint
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
+    #' @importFrom dplyr tibble
     set_region_codes = function() {
       canada_codes <- tibble(
         code = c(

diff --git a/R/Colombia.R b/R/Colombia.R
@@ -47,7 +47,6 @@ Colombia <- R6::R6Class("Colombia",
     source_url = "https://www.datos.gov.co/Salud-y-Protecci-n-Social/Casos-positivos-de-COVID-19-en-Colombia/gt2j-8ykr", # nolint
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
     #' @importFrom dplyr mutate
     set_region_codes = function() {
       self$codes_lookup$`1` <- covidregionaldata::colombia_codes %>%

diff --git a/R/Cuba.R b/R/Cuba.R
@@ -42,7 +42,7 @@ Cuba <- R6::R6Class("Cuba",
 
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
+    #' @importFrom dplyr tibble
     set_region_codes = function() {
       self$codes_lookup$`1` <- tibble(
         code = c(

diff --git a/R/Estonia.R b/R/Estonia.R
@@ -43,7 +43,7 @@ Estonia <- R6::R6Class("Estonia",
 
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
+    #' @importFrom dplyr tibble
     set_region_codes = function() {
       self$codes_lookup$`1` <- tibble(
         code = c("EE-37",

diff --git a/R/France.R b/R/France.R
@@ -50,7 +50,6 @@ France <- R6::R6Class("France",
 
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
     #' @importFrom dplyr select
     set_region_codes = function() {
       self$codes_lookup$`1` <- france_codes %>%

diff --git a/R/Germany.R b/R/Germany.R
@@ -44,8 +44,7 @@ Germany <- R6::R6Class("Germany",
 
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
-    #' @importFrom dplyr mutate
+    #' @importFrom dplyr tibble
     set_region_codes = function() {
       self$codes_lookup$`1` <- tibble(
         code = c(
@@ -94,8 +93,8 @@ Germany <- R6::R6Class("Germany",
           .data$date
         ) %>%
         summarise(
-          cases_new = as.numeric(sum(.data$cases_new > 0)),
-          deaths_new = as.numeric(sum(.data$deaths_new > 0))
+          cases_new = as.numeric(sum(.data$cases_new)),
+          deaths_new = as.numeric(sum(.data$deaths_new))
         ) %>%
         ungroup()
     },
@@ -116,8 +115,8 @@ Germany <- R6::R6Class("Germany",
           .data$level_2_region, .data$date
         ) %>%
         summarise(
-          cases_new = as.numeric(sum(.data$cases_new > 0)),
-          deaths_new = as.numeric(sum(.data$deaths_new > 0))
+          cases_new = as.numeric(sum(.data$cases_new)),
+          deaths_new = as.numeric(sum(.data$deaths_new))
         ) %>%
         ungroup()
     }

diff --git a/R/India.R b/R/India.R
@@ -37,7 +37,7 @@ India <- R6::R6Class("India",
     source_url = "https://www.covid19india.org",
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
+    #' @importFrom dplyr tibble
     set_region_codes = function() {
       self$codes_lookup$`1` <- tibble(
         code = c(

diff --git a/R/Italy.R b/R/Italy.R
@@ -42,7 +42,7 @@ Italy <- R6::R6Class("Italy",
     source_url = "https://github.com/pcm-dpc/COVID-19/blob/master/README_EN.md",
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
+    #' @importFrom dplyr tibble
     set_region_codes = function() {
       self$codes_lookup$`1` <- tibble(
         code = c(

diff --git a/R/JHU.R b/R/JHU.R
@@ -84,7 +84,6 @@ JHU <- R6::R6Class("JHU", # rename to country name
     source_url = "https://github.com/CSSEGISandData/COVID-19/",
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
     set_region_codes = function() {
       self$codes_lookup$`1` <- JHU_codes
     },

diff --git a/R/Lithuania.R b/R/Lithuania.R
@@ -184,8 +184,7 @@ Lithuania <- R6::R6Class("Lithuania",
     #' @description Common data cleaning for both levels
     #'
     # nolint start
-    #' @importFrom dplyr mutate group_by summarise if_else filter select bind_rows rename left_join everything across lead
-    #' @importFrom tidyselect all_of
+    #' @importFrom dplyr mutate group_by summarise if_else filter select bind_rows rename left_join everything across lead all_of
     #' @importFrom lubridate as_date
     # nolint end
     clean_common = function() {
@@ -244,7 +243,7 @@ Lithuania <- R6::R6Class("Lithuania",
       # or qualitative)
       sum_cols <- names(select(
         self$data$raw$main,
-        "population":tidyselect::last_col()
+        "population":dplyr::last_col()
       ))
       sum_cols <- sum_cols[!grepl("prc|map_colors", sum_cols)]
 
@@ -345,7 +344,6 @@ Lithuania <- R6::R6Class("Lithuania",
     #' provided by the source at the level 2 (municipality) regional level.
     #'
     #' @importFrom dplyr group_by summarise ungroup full_join across if_else
-    #' @importFrom tidyselect vars_select_helpers
     clean_level_1 = function() {
       self$data$clean <- self$data$clean %>%
         group_by(
@@ -354,7 +352,7 @@ Lithuania <- R6::R6Class("Lithuania",
         ) %>%
         summarise(
           across(
-            tidyselect::vars_select_helpers$where(is.numeric),
+            where(is.numeric),
             sum
           )
         ) %>%

diff --git a/R/Mexico.R b/R/Mexico.R
@@ -54,7 +54,6 @@ Mexico <- R6::R6Class("Mexico",
     source_url = "https://datos.covid-19.conacyt.mx",
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
     #' @importFrom dplyr select
     set_region_codes = function() {
       self$codes_lookup$`1` <- covidregionaldata::mexico_codes %>%

diff --git a/R/Netherlands.R b/R/Netherlands.R
@@ -46,7 +46,6 @@ Netherlands <- R6::R6Class("Netherlands",
     source_url = "https://data.rivm.nl/covid-19/",
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
     set_region_codes = function() {
 
     },

diff --git a/R/SouthAfrica.R b/R/SouthAfrica.R
@@ -41,7 +41,7 @@ SouthAfrica <- R6::R6Class("SouthAfrica",
     source_url = "https://github.com/dsfsi/covid19za",
 
     #' @description Set up a table of region codes for clean data
-    #' @importFrom tibble tibble
+    #' @importFrom dplyr tibble
     set_region_codes = function() {
       self$codes_lookup$`1` <- tibble(
         code = c(