Norway Adult Deaths & Population, 2021-2023

population_norway.r

library(readr)
library(tidyr)
library(readxl)
library(tidyverse)


### Deaths

# https://ec.europa.eu/eurostat/databrowser/product/view/demo_magec
df <- read_tsv("/Users/Ben/Downloads/estat_demo_magec.tsv")

cleaned_data <- df |>
  separate(
    col = 1, # First column of the dataset
    into = c("freq", "unit", "sex", "age", "geo"),
    sep = ",", # Assuming values are separated by commas
    remove = TRUE
  )

# Filtering and selecting columns as needed
filtered_data <- cleaned_data |>
  filter(geo == "NO", sex == "T") |>
  select(freq, unit, sex, age, geo, `2021`, `2022`) |>
  mutate(
    # Extract numeric age or handle special cases
    age_numeric = case_when(
      age == "TOTAL" ~ NA_real_, # Set TOTAL to NA
      age == "UNK" ~ NA_real_, # Set UNK to NA
      age == "Y_LT1" ~ 0, # Less than 1 year old mapped to 0
      age == "Y_OPEN" ~ 100, # 100+ mapped to 100
      TRUE ~ as.numeric(str_remove(age, "^Y")) # Remove "Y" and convert to num
    )
  ) |>
  filter(
    age_numeric >= 18 # Select ages 18+ or rows with NA (e.g., TOTAL)
  ) |>
  select(-age_numeric)

# 2023 not avail; thus double '22
sum(as.integer(filtered_data$`2021`)) + 2 * sum(as.integer(filtered_data$`2022`))



### Population

# https://www.ssb.no/en/statbank/table/07459/tableViewLayout1/
# Ages 0-105+
pop <- read_xlsx("/Users/ben/Downloads/population.xlsx", skip = 3) |>
  filter(!is.na(`2021`)) |>
  setNames(c("age", "2021", "2022", "2023")) |>
  mutate(
    age = str_replace_all(str_replace_all(age, " years", ""), " year", ""),
    age = case_when(
      age == "105 or older" ~ "105+",
      TRUE ~ age
    )
  )

a <- pop |> filter(!age %in% as.character(0:17))

(sum(a$`2021`) + sum(a$`2022`) + sum(a$`2023`)) / 3