prepare_PL_DATE.R

library(tidyverse)
library(aws.s3)

groupes <- c(
  "Ensemble du Québec",
  "01 Bas-Saint-Laurent",
  "02 Saguenay-Lac-Saint-Jean",
  "03 Capitale-Nationale",
  "04 Mauricie et Centre-du-Québec",
  "05 Estrie",
  "06 Montréal",
  "07 Outaouais",
  "08 Abitibi-Témiscamingue",
  "09 Côte-Nord",
  "10 Nord-du-Québec",
  "11 Gaspésie-Îles-de-la-Madeleine",
  "12 Chaudière-Appalaches",
  "13 Laval",
  "14 Lanaudière",
  "15 Laurentides",
  "16 Montérégie",
  "Inconnue",
  "Hors Québec",
  "Montréal et Laval",
  "Ceinture de Montréal",
  "Autres régions",
  "0 à 9 ans",
  "10 à 19 ans",
  "20 à 29 ans",
  "30 à 39 ans",
  "40 à 49 ans",
  "50 à 59 ans",
  "60 à 69 ans",
  "70 à 79 ans",
  "80 à 89 ans",
  "90 ans et +",
  "Âge inconnu",
  "Masculin",
  "Féminin",
  "Sexe inconnu"
)  

types <- c(
  "total",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region",
  "region_montreal",
  "region_montreal",
  "region_montreal",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "groupe_age",
  "sexe",
  "sexe",
  "sexe"
)  




pouet <- list.files(
  path = "~/cronjob/inspq-PL_DATE/",
  pattern = ".csv$", 
  full.names = TRUE)

datetimes <- lubridate::ymd_hms(
  paste0(
    pouet %>% str_sub(
      start=-19, end = -12),pouet %>% 
      str_sub(start=-10, end = -5) ))




latest_pl_date <- pouet[which.max(datetimes)]


my_colnames <- read_csv(latest_pl_date, skip =2)[,c(1,2:39)] %>%
  janitor::clean_names() %>%
  colnames


z <- map(seq(1:length(groupes)),~ {
  temp <- read_csv(latest_pl_date, 
                   skip =2, 
                   col_types= cols(Mesure = col_character(),.default = col_double()))[,c(1,(38*(.x-1)+2):(38*.x+1))] %>%
    janitor::clean_names() 
  
  colnames(temp) <- my_colnames
  
  temp %>%
    rename(date = mesure) %>%
    mutate(groupe = groupes[.x], 
           type = types[.x],
           date = lubridate::ymd(date)
    ) %>%
    select(date, groupe, type, everything())
  
  
} 
)

prepared_PL_DATE <- bind_rows(z)

write_csv(prepared_PL_DATE, "~/git/adhoc_prive/covid19_PNG/prepared_PL_DATE.csv")

put_object(file = "~/git/adhoc_prive/covid19_PNG/prepared_PL_DATE.csv", 
           object = paste0("covid19/", "prepared_PL_DATE.csv"), 
           bucket = "blogsimoncoulombe")