## library 

library(WDI)
library(readr)
library(tibble)
library(dplyr)
library(tidyr)
library(ggplot2)
library(knitr)

## pick indicators and years 

countries <- "all"

startyear <- 1990
endyear <- 2018

WDIsearch(string='inflation', field='name')
WDIsearch(string='FP.CPI.TOTL.ZG', field='indicator')
indic_inflation <- "FP.CPI.TOTL.ZG" # cpi 

WDIsearch(string='gdp per capita')
WDIsearch(string='gdp')
WDIsearch('gdp.*capita.*constant')
indic_gdp <-  "NY.GDP.MKTP.CD" # "GDP (current US$)"
indic_gdp_pcap <- "NY.GDP.PCAP.CD" # "GDP per capita (current US$)"

## import 

dfn <- WDI(countries, indic_inflation, startyear, endyear)
dfgdp <- WDI(countries, indic_gdp, startyear, endyear)
dfpcgdp <- WDI(countries, indic_gdp_pcap, startyear, endyear)

dfn <- as_tibble(dfn)
dfgdp <- as_tibble(dfgdp)
dfpcgdp <- as_tibble(dfpcgdp)

## see 

df %>%
  select(iso2c, country) %>%
  summarise(length(unique(iso2c)), 
            length(unique(country)))

## check 

# same nr of countries
stopifnot(length(unique(dfpcgdp$iso2c)) == length(unique(dfgdp$iso2c)))
stopifnot(length(unique(dfpcgdp$iso2c)) == length(unique(dfn$iso2c)))

## merge 

str(dfn)
str(dfgdp)
str(dfpcgdp)

df <- dfn %>%
  merge(dfgdp, on="iso2c") %>%
  merge(dfpcgdp, on="iso2c") %>%
  as_tibble() %>%
  rename(inflation = FP.CPI.TOTL.ZG,
         gdp = NY.GDP.MKTP.CD,
         pc_gdp = NY.GDP.PCAP.CD
         ) %>%
  mutate(pop = gdp / pc_gdp)


## remove non countries 

# all cuntry codes 
unique(dfpcgdp$iso2c)

# function 
iso_to_country <- function(isocode, data){
  data %>%
    filter(iso2c %in% isocode) %>%
    select(iso2c, country) %>%
    distinct()
}

# create list of iso & country pair
iso_to_country("AD", dfgdp)
all_iso <- unique(dfgdp$iso2c)
all_iso_cntr <- iso_to_country(all_iso, dfpcgdp)
all_iso_cntr <- as.data.frame(all_iso_cntr)

# select non countries 
all_iso_cntr
non_countries <- all_iso_cntr$iso2c[1:47] 

# remove non countries 
`%not in%` <- function (x, table) is.na(match(x, table, nomatch=NA_integer_))
df <- df %>%
  filter(iso2c %not in% non_countries) %>%
  arrange(iso2c)

df

saveRDS(df, file = "data/df.RDS")

## read from web or disk 
read_web <- FALSE
if(read_web){source("read.R")}
if(!read_web){
  df <- readRDS("data/df.RDS")
}

df

## plot 

# median inflation
median_infl_tot <- median(df$inflation, na.rm=TRUE)

# swe median 
df %>%
  filter(country == "Sweden") %>%
  filter(!is.na(inflation)) %>%
  summarise(median(inflation))

# swe plot 
df %>%
  filter(country == "Sweden") %>%
  ggplot(aes(year, inflation)) + 
  geom_smooth() + 
  ggtitle("Sweden")

plotinf <- function(cntry, data=df){
  data %>%
    filter(country == cntry) %>%
    ggplot(aes(year, inflation)) + 
    geom_smooth() + 
    ggtitle(cntry)
}

plotinfp <- function(cntry, data=df){
  data %>%
    filter(country == cntry) %>%
    ggplot(aes(year, inflation)) + 
    geom_point() +
    geom_smooth() + 
    ggtitle(cntry)
}


plotinf("United States")
plotinfp("Chile")

# us min max 
df %>%
  filter(country == "United States") %>%
  filter(!is.na(inflation)) %>%
  summarise(max(inflation), min(inflation))

# outlier inflaiton 
df %>% 
  filter(country == "Zimbabwe", year > 1999) %>%
  summarise(mean(inflation, na.rm=TRUE))

# plot countries with high inflation
df %>%
  filter(year > 1999) %>%
  filter(!is.na(inflation)) %>%
  group_by(country) %>%
  mutate(mean_infl = mean(inflation)) %>%
  filter(mean_infl > 15) %>%
  filter(mean_infl < 1000) %>%
  arrange(mean_infl) %>%
  ggplot(aes(mean_infl, country)) + 
  geom_point() +
  ggtitle("Inflation (%) since year 1999")

# mean inflation (and nr of datapoints) 
df %>%
  group_by(country) %>%
  filter(!is.na(inflation)) %>%
  filter(year > 1999) %>%
  summarise(mean_infl = mean(inflation)) %>%
  filter(mean_infl > 15) %>%
  mutate(n = length(country))

# countries with high inflation
df %>%
  filter(year > 1999) %>%
  filter(!is.na(inflation)) %>%
  group_by(country) %>%
  summarise(mean_infl = mean(inflation), 
            mean_gdp = mean(gdp),
            mean_pop = mean(pop)
  )

# gdp united states 
gdp_2017_us <- gdp_2017[gdp_2017$country == "United States", "gdp"]
gdp_2017_us <- as.numeric(gdp_2017_us)

# mean infl and gdp last 18y, for countries with high infl. 
tab_1 <- df %>%
  group_by(country) %>%
  filter(!is.na(inflation), !is.na(gdp)) %>% 
  filter(year > 1999) %>%
  mutate(n = length(year)) %>%
  summarise_all(mean, na.rm=TRUE) %>%
  select(country, inflation, n) %>%
  arrange(desc(inflation)) %>%
  filter(inflation > 8) %>%
  mutate(inflation = round(inflation, 1)) %>%
  rename(`Inflation (1999-2017 average)` = inflation)
tab_1
as.data.frame(tab_1)

# gdp per country 
tab_2 <- df %>%
  group_by(country) %>%
  fill(gdp) %>%
  filter(year == 2017) %>%
  select(country, gdp) %>%
  ungroup() %>%
  merge(tab_1, on="country") %>%
  arrange(desc(`Inflation (1999-2017 average)`)) %>%
  mutate(`GDP as % of US` = round(100* gdp / gdp_2017_us,1)) %>%
  mutate(`GDP mUSD in 2017` = round(gdp / 10^6, 0)) %>%
  select(-gdp)
names(tab_2)
tab_2 <- tab_2[, c(1,2,4,5,3)]
sum(tab_2$`GDP as % of US`)
sum(tab_2$`GDP mUSD in 2017`)

dim(tab_1)[1]
sum(tab_2$`GDP as % of US`)
conclusion_1 <- "42 countries have above 8 percent inflation (measured as CPI average 1999 to 2017)."
conclusion_2 <- "Their total gdp is 1/3 of the United States' GDP."

kable(tab_2)