Squashed commit of the following:

commit 950e625 Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Fri Dec 3 16:37:48 2021 +0000 Update NEWS.md commit b93e19d Merge: f6c9759 007b535 Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Fri Dec 3 16:36:05 2021 +0000 Merge pull request epiforecasts#437 from epiforecasts/fewer-deps Reduce the number of `Imports` commit f6c9759 Merge: 4509d81 ac3e63e Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Fri Dec 3 16:33:49 2021 +0000 Merge pull request epiforecasts#439 from epiforecasts/pr-checklist-news Update pr-checklist.yaml to include news nudge commit 4509d81 Merge: 04009e7 b24f2b6 Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Fri Dec 3 16:33:08 2021 +0000 Merge pull request epiforecasts#429 from epiforecasts/alternate-switzerland New data source for Switzerland - fix for epiforecasts#412 commit b24f2b6 Author: Richard Martin-Nielsen <richard.martin@alumni.utoronto.ca> Date: Wed Dec 1 19:50:08 2021 +0200 Update all_country_data.rda commit ed0f6c0 Author: Richard Martin-Nielsen <richard.martin@alumni.utoronto.ca> Date: Wed Dec 1 19:36:35 2021 +0200 Fixed documentation links to FOPH as source of Switzerland data, updated News commit 2a7f105 Merge: aea9b96 04009e7 Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Wed Dec 1 15:23:21 2021 +0000 Merge branch 'master' into alternate-switzerland commit 04009e7 Merge: d1630f5 68200f9 Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Wed Dec 1 14:27:05 2021 +0000 Merge pull request epiforecasts#443 from epiforecasts/feature-boostrap-5-in-docs Switch to bootstrap 5 for pkgdown commit 68200f9 Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Wed Dec 1 13:52:07 2021 +0000 switch to bootstrap 5 for pkgdown commit d1630f5 Merge: 71d7b1f ddbdb8e Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Wed Dec 1 13:48:12 2021 +0000 Merge pull request epiforecasts#442 from epiforecasts/fix-logo Fix giant logo by specifying width instead of height commit ddbdb8e Merge: a19643f 71d7b1f Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Wed Dec 1 13:47:52 2021 +0000 Merge branch 'master' into fix-logo commit a19643f Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Wed Dec 1 14:30:11 2021 +0100 Fix giant logo by specifying width instead of height fix epiforecasts#440 commit aea9b96 Merge: 0d8a6e5 71d7b1f Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Wed Dec 1 10:52:16 2021 +0000 Merge branch 'master' into alternate-switzerland commit ac3e63e Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Wed Dec 1 10:42:33 2021 +0000 Update pr-checklist.yaml commit 71d7b1f Merge: 2e5cabc fb10488 Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Wed Dec 1 10:21:14 2021 +0000 Merge pull request epiforecasts#438 from epiforecasts/rm-joss-action Remove action re-building JOSS paper commit 007b535 Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Wed Dec 1 10:43:26 2021 +0100 Run devtools::document() commit fe79373 Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Wed Dec 1 10:43:16 2021 +0100 Get rid of tidyselect commit 3f5c115 Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Wed Dec 1 10:27:44 2021 +0100 Remove withr dependency as well commit fb10488 Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Tue Nov 30 19:09:00 2021 +0100 Remove action re-building JOSS paper commit 79857e9 Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Tue Nov 30 19:03:17 2021 +0100 Use dplyr::tibble in tests as well commit d3c150b Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Tue Nov 30 18:59:59 2021 +0100 Remove broken rlang::.data import to prevent it from being understood as a re-export commit e711456 Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Tue Nov 30 12:53:15 2021 +0100 Run devtools::document() commit 4032abd Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Tue Nov 30 12:43:43 2021 +0100 Use stringr everywhere instead of stringi commit 1c4ede0 Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Tue Nov 30 12:34:20 2021 +0100 Get tibble functions from dplyr commit a499cc0 Author: Hugo Gruson <hugo.gruson@protonmail.com> Date: Tue Nov 30 12:10:05 2021 +0100 Re-export pipe from dplyr commit 2e5cabc Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Mon Nov 29 13:43:29 2021 +0000 Update NEWS.md commit d1350d9 Merge: 8c77b82 782256c Author: Sam Abbott <s.e.abbott12@gmail.com> Date: Mon Nov 29 13:41:00 2021 +0000 Merge pull request epiforecasts#436 from epiforecasts/fix-germany fix Germany case/death data commit 782256c Author: Sebastian Funk <sebastian.funk@lshtm.ac.uk> Date: Mon Nov 29 07:40:01 2021 +0000 add missing sum commit 4c7cb8c Author: Sebastian Funk <sebastian.funk@lshtm.ac.uk> Date: Mon Nov 29 07:19:09 2021 +0000 fix Germany case/death data commit 0d8a6e5 Author: Richard Martin-Nielsen <richard.martin@alumni.utoronto.ca> Date: Mon Oct 11 22:19:24 2021 +0300 Fixes to keep lintr happier commit 4eb12da Author: Richard Martin-Nielsen <richard.martin@alumni.utoronto.ca> Date: Mon Oct 11 22:05:46 2021 +0300 Cleaning code added and running. Passes tests. Removed AltSwitzerland code, generated data file of sample data and list of data sets. commit 76e4c44 Author: Richard Martin-Nielsen <richard.martin@alumni.utoronto.ca> Date: Mon Oct 4 22:16:44 2021 +0300 Moved old Switzerland code to SwitzerlandAlt, written functional 2-stage download method
RichardMN · Dec 3, 2021 · 9195c3e · 9195c3e
1 parent 00e02e1
commit 9195c3e
Show file tree

Hide file tree

Showing 40 changed files with 177 additions and 252 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)
@@ -78,6 +80,7 @@ importFrom(dplyr,summarise)
 importFrom(dplyr,tally)
 importFrom(dplyr,tibble)
 importFrom(dplyr,transmute)
+importFrom(dplyr,tribble)
 importFrom(dplyr,ungroup)
 importFrom(dplyr,vars)
 importFrom(httr,GET)
@@ -96,10 +99,10 @@ importFrom(lubridate,now)
 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
@@ -9,8 +9,13 @@ This release is currently under development
 
 ## Other changes
 
+* Change the data source for Switzerland to draw data from the Swiss Federal Office of Public Health (FOPH)
 * Updated code for accessing U.S. data as provided by @nytimes
 * 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
@@ -41,7 +41,6 @@ Colombia <- R6::R6Class("Colombia",
     source_url = "https://github.com/danielcs88/colombia_covid-19/",
 
     #' @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(