Untitled.Rmd

---
title: "Get AGES cases Altersgruppen"
author: "Erich Neuwirth"
date: "7/19/2021"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r}
suppressPackageStartupMessages({
  library(here)
  library(tidyverse)
  library(fs)
  library(purrr)
})
```


```{r ems03}
suppressMessages(
source(file.path(here(),"utils",
            "purl_and_source.R"))
)
```


```{r ems04}
suppressMessages(
purl_and_source(file.path(here(),"utils",
            "utils.Rmd"))
)
```

```{r}
coronaDAT_url <- "https://github.com/statistikat/coronaDAT"
```


```{r}
if (!dir_exists(file.path(here(),"data","downloaded",
                          "coronaDAT"))){
  setwd(file.path(here(),"data","downloaded"))
    system("git clone https://github.com/statistikat/coronaDAT")
  } else {
    setwd(file.path(here(),"data","downloaded","coronaDAT"))
    system("git pull")                        
  }
setwd(here())
```
```{r}
coronaDAT_dir <- file.path(here(),"data","downloaded",
                           "coronaDAT","archive")
  
```

```{r alter4}
dir_ls(coronaDAT_dir) ->
  alter_dirs
```


```{r alter6, warning=FALSE}
dates <- c()
suppressWarnings({
for (d in alter_dirs) {
  zip_file <-
   dir_ls(file.path(d,"data")) 
  

  if (str_detect(zip_file,"_orig_csv_ages.zip$")){
    str_split(zip_file,"/") |>  unlist() |> (\(x)x[10])() ->
      file_date
    dates <- c(dates,file_date)
  }
}
  dates |> keep(\(x)!str_detect(x,"[[:letter:]]")) |>
  keep(~as.numeric(.) > 20210500) ->
  date_strings_to_use
})
```


```{r alter7}
altersgruppen_since_may <- tibble()
for (dir_mid in date_strings_to_use) {
  d <- paste(coronaDAT_dir,dir_mid,"data",sep="/")
  file_to_unzip <- dir_ls(d)
  Datum <- paste(str_sub(dir_mid,1,4),
                 str_sub(dir_mid,5,6),
                 str_sub(dir_mid,7,8),
                 sep="-") |> as.Date()
  unzip(file_to_unzip,
        files="CovidFaelle_Altersgruppe.csv",
        exdir=file.path(here(),"unzipped"))

  one_day_df <-
suppressMessages(      

    read_csv2(file.path(
      file.path(here(),"unzipped",
               "CovidFaelle_Altersgruppe.csv")
      )
    )) |>
    mutate(Datum=Datum) |>
    select(Datum,everything())
  altersgruppen_since_may |>
    bind_rows(one_day_df) ->
    altersgruppen_since_may
}
altersgruppen_since_may |>
    mutate(Altersgruppe=case_when(
    Altersgruppe == "<5" ~ "0-4",
    Altersgruppe == ">84" ~ "85-",
    TRUE ~ Altersgruppe)
    ) ->
  altersgruppen_since_may
```