Merge pull request epiforecasts#383 from epiforecasts/hexisticker

made draft hexsticker

.pre-commit-config.yaml

@@ -43,7 +43,7 @@ repos:
     rev: v3.4.0
     hooks: 
     -   id: check-added-large-files
-        args: ['--maxkb=200']
+        args: ['--maxkb=800']
     -   id: end-of-file-fixer
         exclude: '\.Rd'
 -   repo: local

DESCRIPTION

@@ -68,8 +68,8 @@ Description: An interface to subnational and national level COVID-19 data
     the UK, and from other Covid-19 data collections, including the World
     Health Organisation (WHO), European Centre for Disease Prevention and
     Control (ECDC), John Hopkins University (JHU), Google Open Data and
-    others. Designed to streamline Covid-19 data extraction, cleaning,
-    and processing from a range of data sources in an open and transparent
+    others. Designed to streamline Covid-19 data extraction, cleaning, and
+    processing from a range of data sources in an open and transparent
     way. This allows users to inspect and scrutinise the data, and tools
     used to process it, at every step. For all countries supported, data
     includes a daily time-series of cases. Wherever available data is also
@@ -103,6 +103,7 @@ Imports:
     xml2
 Suggests:
     ggplot2,
+    ggspatial,
     knitr,
     mockery,
     pkgdown,

README.Rmd

@@ -11,7 +11,7 @@ knitr::opts_chunk$set(
 )
 ```
 
-# Subnational data for the COVID-19 outbreak
+# Subnational data for the COVID-19 outbreak <img src="man/figures/logo.png" align="right" alt="" height="150" />
 
 [![Lifecycle: maturing](https://img.shields.io/badge/lifecycle-maturing-blue.svg)](https://lifecycle.r-lib.org/articles/stages.html) [![R-CMD-check](https://github.com/epiforecasts/covidregionaldata/workflows/R-CMD-check/badge.svg)](https://github.com/epiforecasts/covidregionaldata/actions) [![Codecov test coverage](https://codecov.io/gh/epiforecasts/covidregionaldata/branch/master/graph/badge.svg)](https://codecov.io/gh/epiforecasts/covidregionaldata?branch=master) [![Data status](https://img.shields.io/badge/Data-status-lightblue.svg?style=flat)](https://epiforecasts.io/covidregionaldata/articles/supported-countries.html) [![metacran downloads](http://cranlogs.r-pkg.org/badges/grand-total/covidregionaldata?color=ff69b4)](https://cran.r-project.org/package=covidregionaldata)
 

README.md

@@ -1,5 +1,5 @@
 
-# Subnational data for the COVID-19 outbreak
+# Subnational data for the COVID-19 outbreak <img src="man/figures/logo.png" align="right" alt="" height="150" />
 
 [![Lifecycle:
 maturing](https://img.shields.io/badge/lifecycle-maturing-blue.svg)](https://lifecycle.r-lib.org/articles/stages.html)
@@ -27,11 +27,11 @@ both official sources, such as Public Health England in the UK, and from
 other Covid-19 data collections, including the World Health Organisation
 (WHO), European Centre for Disease Prevention and Control (ECDC), John
 Hopkins University (JHU), Google Open Data and others. This package is
-designed to streamline Covid-19 data extraction, cleaning, and processing
-from a range of data sources in an open and transparent way. This allows
-users to inspect and scrutinise the data, and tools used to process it,
-at every step. For all countries supported, data includes a daily
-time-series of cases and, wherever available, data on deaths,
+designed to streamline Covid-19 data extraction, cleaning, and
+processing from a range of data sources in an open and transparent way.
+This allows users to inspect and scrutinise the data, and tools used to
+process it, at every step. For all countries supported, data includes a
+daily time-series of cases and, wherever available, data on deaths,
 hospitalisations, and tests. National level data is also supported using
 a range of data sources as well as line list data and links to
 intervention data sets.
@@ -78,7 +78,7 @@ the temporary directory by default),
 
 ``` r
 start_using_memoise()
-#> Using a cache at: /tmp/RtmpJAeC7J
+#> Using a cache at: /tmp/RtmpXdh1Cd
 ```
 
 To stop using `memoise` use,
@@ -103,7 +103,7 @@ the Google COVID-19 open data project), use:
 ``` r
 nots <- get_national_data()
 #> Downloading data from https://covid19.who.int/WHO-COVID-19-global-data.csv
-#> Rows: 124,425
+#> Rows: 128,546
 #> Columns: 8
 #> Delimiter: ","
 #> chr  [3]: Country_code, Country, WHO_region
@@ -115,7 +115,7 @@ nots <- get_national_data()
 #> Cleaning data
 #> Processing data
 nots
-#> # A tibble: 124,425 x 15
+#> # A tibble: 128,690 x 15
 #>    date       un_region who_region country        iso_code cases_new cases_total
 #>    <date>     <chr>     <chr>      <chr>          <chr>        <dbl>       <dbl>
 #>  1 2020-01-03 Asia      EMRO       Afghanistan    AF               0           0
@@ -128,7 +128,7 @@ nots
 #>  8 2020-01-03 Americas  AMRO       Antigua & Bar… AG               0           0
 #>  9 2020-01-03 Americas  AMRO       Argentina      AR               0           0
 #> 10 2020-01-03 Asia      EURO       Armenia        AM               0           0
-#> # … with 124,415 more rows, and 8 more variables: deaths_new <dbl>,
+#> # … with 128,680 more rows, and 8 more variables: deaths_new <dbl>,
 #> #   deaths_total <dbl>, recovered_new <dbl>, recovered_total <dbl>,
 #> #   hosp_new <dbl>, hosp_total <dbl>, tested_new <dbl>, tested_total <dbl>
 ```
@@ -169,7 +169,7 @@ for example by level 1 region in the UK, use:
 ``` r
 uk_nots <- get_regional_data(country = "UK", verbose = FALSE)
 uk_nots
-#> # A tibble: 6,474 x 26
+#> # A tibble: 6,695 x 26
 #>    date       region   region_code cases_new cases_total deaths_new deaths_total
 #>    <date>     <chr>    <chr>           <dbl>       <dbl>      <dbl>        <dbl>
 #>  1 2020-01-30 East Mi… E12000004          NA          NA         NA           NA
@@ -182,7 +182,7 @@ uk_nots
 #>  8 2020-01-30 Scotland S92000003          NA          NA         NA           NA
 #>  9 2020-01-30 South E… E12000008          NA          NA         NA           NA
 #> 10 2020-01-30 South W… E12000009          NA          NA         NA           NA
-#> # … with 6,464 more rows, and 19 more variables: recovered_new <dbl>,
+#> # … with 6,685 more rows, and 19 more variables: recovered_new <dbl>,
 #> #   recovered_total <dbl>, hosp_new <dbl>, hosp_total <dbl>, tested_new <dbl>,
 #> #   tested_total <dbl>, areaType <chr>, cumCasesByPublishDate <dbl>,
 #> #   cumCasesBySpecimenDate <dbl>, newCasesByPublishDate <dbl>,
@@ -256,10 +256,10 @@ using the following,
 
 [![Development](https://img.shields.io/badge/Wiki-lightblue.svg?style=flat)](https://github.com/epiforecasts/covidregionaldata/wiki/)
 
-This package is the result of work from a number of contributors
-(see contributors list in the
-[here](https://epiforecasts.io/covidregionaldata/authors.html)).
-We would like to thank the [CMMID COVID-19 working
+This package is the result of work from a number of contributors (see
+contributors list
+[here](https://epiforecasts.io/covidregionaldata/authors.html)). We
+would like to thank the [CMMID COVID-19 working
 group](https://cmmid.github.io/groups/ncov-group.html) for inciteful
 comments and feedback.
 

inst/WORDLIST

@@ -166,6 +166,7 @@ geocoding
 getRversion
 GFM
 ggplot
+ggspatial
 Gimma
 github
 Github
@@ -190,6 +191,7 @@ HDTRA
 Healy
 hellewell
 Hellewell
+Hexsticker
 Hiroaki
 hl
 Hongru

inst/make_hexsticker.R

@@ -0,0 +1,102 @@
+library(covidregionaldata)
+library(hexSticker)
+library(showtext)
+library(ggplot2)
+library(dplyr)
+library(maps)
+library(countrycode)
+library(sf)
+library(rnaturalearth)
+library(rmapshaper)
+
+# font setup
+font_add_google("Zilla Slab Highlight", "useme")
+
+# get countries we have data for
+regional_countries <- get_available_datasets() %>%
+  filter(.data$type == "regional")
+
+regional_countries_l2 <- regional_countries %>%
+  filter(!(is.na(.data$level_2_region)))
+
+regional_countries_l1 <- regional_countries %>%
+  filter(is.na(.data$level_2_region))
+
+# Approach using Natural Earth data
+
+world_without_regions <- ne_countries(returnclass = "sf") %>%
+  filter(sovereignt != "Antarctica")
+
+# numberOfLevels should be less than half the number of colours in the
+# divergent palette used (usually 7)
+numberOfLevels <- 3
+
+regional_maps_l1 <- ms_simplify(
+  ne_states(gsub(" \\(.*\\)", "",
+    regional_countries_l1$origin,
+    perl = TRUE
+  ), returnclass = "sf") %>%
+    mutate(region_code = woe_id %% numberOfLevels),
+  keep = 0.04
+)
+
+regional_maps_l2 <- ms_simplify(
+  ne_states(gsub(" \\(.*\\)", "",
+    regional_countries_l2$origin,
+    perl = TRUE
+  ), returnclass = "sf") %>%
+    mutate(region_code = woe_id %% numberOfLevels + numberOfLevels + 1),
+  keep = 0.04
+)
+
+regional_maps <- bind_rows(regional_maps_l1, regional_maps_l2)
+
+# We keep 50% of the points of the country outlines because it's a
+# finer scale map
+# We add the US and the UK to the list because otherwise we don't
+# successfully include them.
+regional_outlines <- ms_lines(
+  ms_simplify(
+    ne_countries(
+      country = c(
+        gsub(" \\(.*\\)", "", regional_countries$origin, perl = TRUE),
+        "United States", "United Kingdom"
+      ),
+      returnclass = "sf"
+    ),
+    keep = 0.1,
+    scale = 50
+  )
+)
+
+covid_map <- ggplot() +
+  ggspatial::layer_spatial(data = world_without_regions, size = 0.01) +
+  ggspatial::layer_spatial(
+    data = regional_maps,
+    aes(fill = region_code), size = 0.02
+  ) +
+  ggspatial::layer_spatial(
+    data = regional_outlines,
+    aes(colour = factor(RANK)), size = 0.1
+  ) +
+  coord_sf(crs = "ESRI:54016") +
+  scale_fill_fermenter(palette = "RdBu") +
+  theme_void() +
+  scale_colour_manual(name = "", values = c("black", "black", "black")) +
+  theme(legend.position = "none", axis.text.x = element_blank())
+
+print(covid_map)
+
+logo <- sticker(
+  covid_map,
+  package = "covidregionaldata",
+  p_size = 48, s_x = 1, s_y = 0.8, s_width = 1.7, s_height = 1.7,
+  p_y = 1.45,
+  p_color = "white",
+  p_family = "useme",
+  h_color = "#646770",
+  h_fill = "#24A7DF",
+  filename = "man/figures/logo.png",
+  u_size = 3.5,
+  dpi = 1000
+)