The script used during session 10.

#S10 - Script

The script using during session 10. For more precise solutions see:
https://gist.github.com/graebnerc/5d5ec7591a45d6cbad3a58ddf06fff6b

data_analysis_script.R

# This is the script used during the lecture. For a more comprehensive solution
#  to the exercises see the solutions here:
#  https://gist.github.com/graebnerc/5d5ec7591a45d6cbad3a58ddf06fff6b
here::i_am("R/data_analysis_script.R")
library(data.table)
library(here)
library(dplyr)
library(tidyr)
library(countrycode)

# 1. Import data-------------

gdp_file <- here("data/raw/API_NY.GDP.PCAP.PP.KD_DS2_en_csv_v2_5359165.csv")

gpd_data_raw <- fread(
  file = gdp_file, 
  header = TRUE) %>% 
  as_tibble(.)
# Usind the WDI package:
# wdi_style <- WDI::WDI(indicator = "SH.DYN.MORT")

mortality_data_raw <- fread(
  file = here("data/raw/API_SH.DYN.MORT_DS2_en_csv_v2_5358988.csv"), 
  header = TRUE) %>% 
  as_tibble(.)

gini_data_raw <- fread(file = here("data/raw/swiid9_4_summary.csv")) %>% 
  as_tibble(.)

# Transform the data---------
gpd_data <- gpd_data_raw %>% 
  dplyr::select(
    -c("Indicator Name", "Indicator Code", "Country Name", "V67")
    ) %>% 
  tidyr::pivot_longer(
    cols = -"Country Code", 
    names_to = "year", 
    values_to = "GDP"
    ) %>% 
  dplyr::mutate(
    year = as.double(year)) %>% 
  dplyr::rename(
    country = `Country Code`)

mortality_data <- mortality_data_raw %>% 
  dplyr::select(
    -c("Indicator Name", "Indicator Code", "Country Name", "V67")
  ) %>% 
  tidyr::pivot_longer(
    cols = -"Country Code", 
    names_to = "year", 
    values_to = "Mortality"
  ) %>% 
  dplyr::mutate(
    year = as.double(year)) %>% 
  dplyr::rename(
    country = `Country Code`)

gini_data <- gini_data_raw %>% 
  select(c("country", "year", "gini_disp")) %>% 
  dplyr::filter(country!="Soviet Union") %>% 
  dplyr::mutate(
    country = countrycode(
      country, origin = "country.name", destination = "iso3c"))

# Merge World Bank Data------
world_data <- dplyr::inner_join(
  x = gpd_data, y = mortality_data, by = c("country", "year")
  )
complete_data <- dplyr::inner_join(
  x = world_data, y = gini_data, by=c("country", "year")
  )
fwrite(
  x = complete_data, 
  file = here("data/tidy/full_data.csv")
  )