Merge pull request epiforecasts#388 from RichardMN:source-fields

Add source text and url fields to classes

R/Belgium.R

@@ -50,6 +50,11 @@ Belgium <- R6::R6Class("Belgium",
     ),
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new", "deaths_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Sciensano (Belgian institute of health)",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://epistat.wiv-isp.be/covid/",
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble tribble

R/Brazil.R

@@ -40,6 +40,11 @@ Brazil <- R6::R6Class("Brazil",
     ),
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_total", "deaths_total"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Wesley Cota",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    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

R/Canada.R

@@ -37,7 +37,12 @@ Canada <- R6::R6Class("Canada",
       "cases_new", "cases_total", "deaths_new",
       "recovered_total", "tested_new"
     ),
-
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Public Health Infobase, Public Health Agency of Canada",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    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
     set_region_codes = function() {

R/Colombia.R

@@ -34,6 +34,11 @@ Colombia <- R6::R6Class("Colombia",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_total"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Daniel C\u00e1rdenas",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://github.com/danielcs88/colombia_covid-19/",
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/Covid19DataHub.R

@@ -93,6 +93,11 @@ Covid19DataHub <- R6::R6Class("Covid19DataHub",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("confirmed", "deaths", "recovered", "tested", "hosp"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "COVID-19 Data Hub",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://covid19datahub.io",
 
     #' @description Covid19 Data Hub specific data cleaning.
     #' This takes all the raw data, renames some columns and checks types.

R/Cuba.R

@@ -34,6 +34,12 @@ Cuba <- R6::R6Class("Cuba",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "COVID19 Cuba Data team",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://covid19cubadata.github.io/#cuba",
+
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/ECDC.R

@@ -36,6 +36,11 @@ ECDC <- R6::R6Class("ECDC",
     ),
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new", "deaths_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "European Centre for Disease Prevention and Control (ECDC)",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://www.ecdc.europa.eu/en/publications-data/download-todays-data-geographic-distribution-covid-19-cases-worldwide", # nolint
 
     #' @description ECDC specific state level data cleaning
     #' @importFrom dplyr mutate rename select arrange filter

R/France.R

@@ -42,6 +42,12 @@ France <- R6::R6Class("France",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new", "tested_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "French Public Open Data Platform",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://www.data.gouv.fr/fr/pages/donnees-coronavirus",
+
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/Germany.R

@@ -36,6 +36,12 @@ Germany <- R6::R6Class("Germany",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new", "deaths_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Robert Koch-Institut (RKI)",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://hub.arcgis.com/datasets/dd4580c810204019a7b8eb3e0b329dd6_0/explore", # nolint
+
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/Google.R

@@ -84,6 +84,12 @@ Google <- R6::R6Class("Google",
       "total_recovered",
       "total_tested"
     ),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "O. Wahltinez et al.",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://github.com/GoogleCloudPlatform/covid-19-open-data",
+
     #' @description GoogleData specific subregion2 level data cleaning. This
     #' takes all the raw data, puts into a single data frame, renames some
     #' columns and checks types.

R/India.R

@@ -30,6 +30,11 @@ India <- R6::R6Class("India",
     ),
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new", "deaths_new", "recovered_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "COVID19India",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://www.covid19india.org",
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/Italy.R

@@ -35,6 +35,11 @@ Italy <- R6::R6Class("Italy",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_total", "deaths_total", "tested_total"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Department of Civil Protection, Italy",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    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

R/JHU.R

@@ -77,6 +77,11 @@ JHU <- R6::R6Class("JHU", # rename to country name
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("confirmed", "deaths", "recovered"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Center for Systems Science and Engineering (CSSE) at Johns Hopkins University (JHU)", # nolint
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://github.com/CSSEGISandData/COVID-19/",
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/JRC.R

@@ -61,6 +61,12 @@ JRC <- R6::R6Class("JRC",
       "Hospitalized",
       "IntensiveCare"
     ),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "European Commission Joint Research Centre (JRC)",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://github.com/ec-jrc/COVID-19",
+
 
     #' @description JRC specific data cleaning. The raw source data columns are
     #' converted to the correct type and renamed appropriately to match the

R/Lithuania.R

@@ -154,6 +154,12 @@ Lithuania <- R6::R6Class("Lithuania",
     source_data_cols = c(
       "cases_new", "tested_new", "recovered_total", "deaths_new"
     ),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Lithuanian Statistics Department",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://hub.arcgis.com/datasets/d49a63c934be4f65a93b6273785a8449_0/about", # nolint
+
     # Additional attributes specific to the Lithuania functionality
     #' @field death_definition which criteria of deaths attributed to
     #' COVID to use

R/Mexico.R

@@ -47,6 +47,11 @@ Mexico <- R6::R6Class("Mexico",
     ),
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new", "deaths_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Government of Mexico",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://datos.covid-19.conacyt.mx",
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/Netherlands.R

@@ -39,6 +39,11 @@ Netherlands <- R6::R6Class("Netherlands",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new", "deaths_new", "hosp_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "National Institute for Public Health and the Environment (RIVM), Netherlands", # nolint
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://data.rivm.nl/covid-19/",
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/SouthAfrica.R

@@ -34,10 +34,14 @@ SouthAfrica <- R6::R6Class("SouthAfrica",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_new", "deaths_new", "recovered_new"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Data Science for Social Impact research group, University of Pretoria", # nolint
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://github.com/dsfsi/covid19za",
 
     #' @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` <- tibble(
         code = c(

R/Switzerland.R

@@ -62,6 +62,11 @@ Switzerland <- R6::R6Class("Switzerland",
       "cases_total",
       "tested_total"
     ),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Open Data, Canton of Zurich",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://github.com/openZH/covid_19/",
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tibble

R/UK.R

@@ -101,6 +101,11 @@ UK <- R6::R6Class("UK",
       "newPillarOneTestsByPublishDate", "newPillarTwoTestsByPublishDate",
       "newPillarThreeTestsByPublishDate", "newPillarFourTestsByPublishDate"
     ),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "Public Health England",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://coronavirus.data.gov.uk/",
 
     #' @description Specific function for getting region codes for UK .
     set_region_codes = function() {

R/USA.R

@@ -42,6 +42,11 @@ USA <- R6::R6Class("USA",
     # nolint end
     #' @field source_data_cols existing columns within the raw data
     source_data_cols = c("cases_total", "deaths_total"),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "New York Times",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://github.com/nytimes/covid-19-data",
 
     #' @description Set up a table of region codes for clean data
     #' @importFrom tibble tribble

R/WHO.R

@@ -38,6 +38,12 @@ WHO <- R6::R6Class("WHO",
       "deaths_new",
       "deaths_total"
     ),
+    #' @field source_text Plain text description of the source of the data
+    source_text = "World Health Organisation",
+    #' @field source_url Website address for explanation/introduction of the
+    #' data
+    source_url = "https://covid19.who.int",
+
 
     #' @description WHO specific data cleaning
     #' @importFrom dplyr mutate rename

R/shared-methods.R

@@ -510,7 +510,9 @@ DataClass <- R6::R6Class(
           "national", "regional"
         ),
         data_urls = paste(unlist(self$data_urls), collapse = ", "),
-        source_data_cols = paste(unlist(self$source_data_cols), collapse = ", ")
+        source_data_cols = paste(unlist(self$source_data_cols), collapse = ", "),
+        source_text = ifelse(is.null(self$source_text), NA, self$source_text),
+        source_url = ifelse(is.null(self$source_url), NA, self$source_url)
       )
       return(sum_df)
     },