get_data.R

library(here)
library(tidyverse)
library(lubridate)
library(tsibble)

url <- "https://opendata.digilugu.ee/opendata_covid19_test_results.csv"
if (!file.exists(here("data", basename(url)))) {
  download.file(url, destfile = here("data", basename(url)))
}

tests <- read_csv(here("data", basename(url)))
tests <- tests %>% 
  distinct()
tests_sample <- tests %>% 
  sample_frac(0.05)

tests_sample %>%
  mutate(yw = format(StatisticsDate, "%Y-%U"),
         yw2 = yearweek(StatisticsDate)) %>% 
  group_by(yw2) %>% 
  count(ResultValue) %>% 
  ggplot() +
  geom_line(aes(yw2, n, color = ResultValue))

tests_sample %>% 
  select(Gender, AgeGroup, Country,  County, ResultValue, StatisticsDate) %>% 
  write_csv(here("data", "covid_tests.csv"))

n_distinct(tests$id)

tests %>% 
  add_count(id) %>% 
  filter(n > 1)