The Economistがビックマック指数を公開している件について

英国のThe Economistがビックマック指数をオープンデータ化しています．データ分析を練習していると，データが無性に欲しくなる時がありますが，こう言うオープンデータの流れが広まると僕らのデータリテラシーが高まりますね．

記事の中でも，今後公開できるものについてはどんどん公開していく予定であると述べています．

We plan to publish more of our data on GitHub in the coming months—and, where it’s appropriate, the analysis and code behind them as well. We look forward to seeing how our readers use and build upon the data reporting we do. If you have thoughts on the way we’ve released these data, or how we should go about releasing more in the future, please let us know.

データ分析に興味がある人ととして非常にありがたいのが，GitHubではThe Economistがコードを公開しています（当たり前っちゃ当たり前だけど）．

例えばこんな感じ：

library('tidyverse')
library('data.table')

big_mac_countries = c('ARG', 'AUS', 'BRA', 'GBR', 'CAN', 'CHL', 'CHN', 'CZE', 'DNK',
                      'EGY', 'HKG', 'HUN', 'IDN', 'ISR', 'JPN', 'MYS', 'MEX', 'NZL',
                      'NOR', 'PER', 'PHL', 'POL', 'RUS', 'SAU', 'SGP', 'ZAF', 'KOR',
                      'SWE', 'CHE', 'TWN', 'THA', 'TUR', 'ARE', 'USA', 'COL', 'CRI',
                      'PAK', 'LKA', 'UKR', 'URY', 'IND', 'VNM', 'GTM', 'HND', # Venezuela removed
                      'NIC', 'AZE', 'BHR', 'HRV', 'JOR', 'KWT', 'LBN', 'MDA', 'OMN',
                      'QAT', 'ROU', 'EUZ')
base_currencies = c('USD', 'EUR', 'GBP', 'JPY', 'CNY')

big_mac_data = fread('./source-data/big-mac-source-data.csv', na.strings = '#N/A',
                     # sort by date and then by country name, for easy reading;
                     # index on currency_code for faster joining
                     key = 'date,name', index = 'currency_code') %>%
  # remove lines where the local price is missing
  .[!is.na(local_price)]

big_mac_data[, dollar_price := local_price / dollar_ex]

big_mac_index = big_mac_data[
    !is.na(dollar_price) & iso_a3 %in% big_mac_countries
    ,.(date, iso_a3, currency_code, name, local_price, dollar_ex, dollar_price)]

for(currency in base_currencies) {
  big_mac_index[
    ,
    (currency) := dollar_price / .SD[currency_code == currency]$dollar_price - 1,
    by=date
  ]
}
big_mac_index[, (base_currencies) := lapply(.SD, round, 3L), .SDcols=base_currencies]

fwrite(big_mac_index, './output-data/big-mac-raw-index.csv')

big_mac_gdp_data = big_mac_data[GDP_dollar > 0]

regression_countries = c('ARG', 'AUS', 'BRA', 'GBR', 'CAN', 'CHL', 'CHN', 'CZE', 'DNK',
                         'EGY', 'EUZ', 'HKG', 'HUN', 'IDN', 'ISR', 'JPN', 'MYS', 'MEX',
                         'NZL', 'NOR', 'PER', 'PHL', 'POL', 'RUS', 'SAU', 'SGP', 'ZAF',
                         'KOR', 'SWE', 'CHE', 'TWN', 'THA', 'TUR', 'USA', 'COL', 'PAK',
                         'IND', 'AUT', 'BEL', 'NLD', 'FIN', 'FRA', 'DEU', 'IRL', 'ITA',
                         'PRT', 'ESP', 'GRC', 'EST')
big_mac_gdp_data = big_mac_gdp_data[iso_a3 %in% regression_countries]

big_mac_gdp_data[,adj_price := lm(dollar_price ~ GDP_dollar)$fitted.values, by=date]

big_mac_adj_index = big_mac_gdp_data[
  !is.na(dollar_price) & iso_a3 %in% big_mac_countries
  ,.(date, iso_a3, currency_code, name, local_price, dollar_ex, dollar_price, GDP_dollar, adj_price)]

for(currency in base_currencies) {
  big_mac_adj_index[
    ,
    (currency) := (dollar_price / adj_price) /
      .SD[currency_code == currency, dollar_price / adj_price] - 1,
    by=date
  ]
}
big_mac_adj_index[, (base_currencies) := lapply(.SD, round, 3L), .SDcols=base_currencies]

fwrite(big_mac_adj_index, './output-data/big-mac-adjusted-index.csv')

big_mac_full_index = merge(big_mac_index, big_mac_adj_index,
  by=c('date', 'iso_a3', 'currency_code', 'name', 'local_price', 'dollar_ex', 'dollar_price'),
  suffixes=c('_raw', '_adjusted'),
  all.x=TRUE
  )

fwrite(big_mac_full_index, './output-data/big-mac-full-index.csv')