Global GDP

1 input data

Code

library(tidyverse)
library(openxlsx)
library(readxl)
library(janitor)
library(plotly)

Code

library()

Code

#download.file('https://api.worldbank.org/v2/en/indicator/NY.GDP.MKTP.CD?downloadformat=excel','output.xls')

Code

data001=read_excel('output.xls')
head(data001)

# A tibble: 6 × 67
  `Data Source` World Development In…¹ ...3  ...4  ...5  ...6  ...7  ...8  ...9 
  <chr>         <chr>                  <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 Last Updated… 45132                  <NA>  <NA>  <NA>  <NA>  <NA>  <NA>  <NA> 
2 <NA>          <NA>                   <NA>  <NA>  <NA>  <NA>  <NA>  <NA>  <NA> 
3 Country Name  Country Code           Indi… Indi… 1960  1961  1962  1963  1964 
4 Taiwan        <NA>                   <NA>  <NA>  <NA>  <NA>  <NA>  <NA>  <NA> 
5 Aruba         ABW                    GDP … NY.G… <NA>  <NA>  <NA>  <NA>  <NA> 
6 Africa Easte… AFE                    GDP … NY.G… 2112… 2161… 2350… 2804… 2592…
# ℹ abbreviated name: ¹​`World Development Indicators`
# ℹ 58 more variables: ...10 <chr>, ...11 <chr>, ...12 <chr>, ...13 <chr>,
#   ...14 <chr>, ...15 <chr>, ...16 <chr>, ...17 <chr>, ...18 <chr>,
#   ...19 <chr>, ...20 <chr>, ...21 <chr>, ...22 <chr>, ...23 <chr>,
#   ...24 <chr>, ...25 <chr>, ...26 <chr>, ...27 <chr>, ...28 <chr>,
#   ...29 <chr>, ...30 <chr>, ...31 <chr>, ...32 <chr>, ...33 <chr>,
#   ...34 <chr>, ...35 <chr>, ...36 <chr>, ...37 <chr>, ...38 <chr>, …

read in excel and start from 3rd row and then clean up column names

Code

data001=read_excel('output.xls',skip = 2) %>% clean_names()
head(data001)

# A tibble: 6 × 67
  country_name      country_code indicator_name indicator_code    x1960    x1961
  <chr>             <chr>        <chr>          <chr>             <dbl>    <dbl>
1 Taiwan            <NA>         <NA>           <NA>           NA       NA      
2 Aruba             ABW          GDP (current … NY.GDP.MKTP.CD NA       NA      
3 Africa Eastern a… AFE          GDP (current … NY.GDP.MKTP.CD  2.11e10  2.16e10
4 Afghanistan       AFG          GDP (current … NY.GDP.MKTP.CD  5.38e 8  5.49e 8
5 Africa Western a… AFW          GDP (current … NY.GDP.MKTP.CD  1.04e10  1.12e10
6 Angola            AGO          GDP (current … NY.GDP.MKTP.CD NA       NA      
# ℹ 61 more variables: x1962 <dbl>, x1963 <dbl>, x1964 <dbl>, x1965 <dbl>,
#   x1966 <dbl>, x1967 <dbl>, x1968 <dbl>, x1969 <dbl>, x1970 <dbl>,
#   x1971 <dbl>, x1972 <dbl>, x1973 <dbl>, x1974 <dbl>, x1975 <dbl>,
#   x1976 <dbl>, x1977 <dbl>, x1978 <dbl>, x1979 <dbl>, x1980 <dbl>,
#   x1981 <dbl>, x1982 <dbl>, x1983 <dbl>, x1984 <dbl>, x1985 <dbl>,
#   x1986 <dbl>, x1987 <dbl>, x1988 <dbl>, x1989 <dbl>, x1990 <dbl>,
#   x1991 <dbl>, x1992 <dbl>, x1993 <dbl>, x1994 <dbl>, x1995 <dbl>, …

delete column

Code

data002=data001 %>% select(-country_code,-indicator_name,-indicator_code)

wide to long

Code

data003=data002 %>% pivot_longer(!country_name,names_to = "year", values_to = "GDP")

Code

glimpse(data003)

Rows: 16,821
Columns: 3
$ country_name <chr> "Taiwan", "Taiwan", "Taiwan", "Taiwan", "Taiwan", "Taiwan…
$ year         <chr> "x1960", "x1961", "x1962", "x1963", "x1964", "x1965", "x1…
$ GDP          <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…

Code

data003=data003 %>% mutate(year_num=as.numeric(str_replace(year,'x',''))) %>% select(-year)

Code

glimpse(data003)

Rows: 16,821
Columns: 3
$ country_name <chr> "Taiwan", "Taiwan", "Taiwan", "Taiwan", "Taiwan", "Taiwan…
$ GDP          <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ year_num     <dbl> 1960, 1961, 1962, 1963, 1964, 1965, 1966, 1967, 1968, 196…

2 China mainland and Hongkong

Code

data004=data003 %>%filter(country_name %in% c('China','Hong Kong SAR, China'))

Code

ggplot(data004, aes(year_num, GDP, colour = country_name)) + 
  geom_line()+ scale_y_continuous(labels = scales::label_number_si())

Code

data_cn_hk001=data002%>%filter(country_name %in% c('China','Hong Kong SAR, China'))

Code

data_cn_hk002=t(data_cn_hk001)%>% as.data.frame() 

Code

library(tibble)
data_cn_hk002=rownames_to_column(data_cn_hk002, "year")

Code

data_cn_hk003=data_cn_hk002[-1,] %>% mutate(year_num=as.numeric(str_replace(year,'x','')))

Code

glimpse(data_cn_hk003)

Rows: 63
Columns: 4
$ year     <chr> "x1960", "x1961", "x1962", "x1963", "x1964", "x1965", "x1966"…
$ V1       <chr> "59716251765", "50056688015", "47209188356", "50706616610", "…
$ V2       <chr> " 1320796652", " 1383681651", " 1612346412", " 1935298266", "…
$ year_num <dbl> 1960, 1961, 1962, 1963, 1964, 1965, 1966, 1967, 1968, 1969, 1…

Code

data_cn_hk003=data_cn_hk003 %>% mutate(V1=as.numeric(V1),V2=as.numeric(V2),total=V1+V2
                                       ,V1_share=V1/total,V12_share=V2/total,)

Code

ggplot(data_cn_hk003, aes(year_num, V12_share)) + 
  geom_line()+ scale_y_continuous(labels = scales::label_number_si())

Code

plot_ly(data = data_cn_hk003, x = ~year_num, y = ~V12_share,mode='lines')

3 Asia 4 drgan

Code

Asia_4_drgan001=data003 %>%filter(country_name %in% c('Taiwan','Korea, Rep.','Singapore','Hong Kong SAR, China'))

Code

glimpse(Asia_4_drgan001)

Rows: 252
Columns: 3
$ country_name <chr> "Taiwan", "Taiwan", "Taiwan", "Taiwan", "Taiwan", "Taiwan…
$ GDP          <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ year_num     <dbl> 1960, 1961, 1962, 1963, 1964, 1965, 1966, 1967, 1968, 196…

Code

ggplot(Asia_4_drgan001, aes(year_num, GDP, colour = country_name)) + 
  geom_line()+ scale_y_continuous(labels = scales::label_number_si())

4 GDP per capita

from imf

Code

#download.file('https://www.imf.org/external/datamapper//export/excel.php?indicator=NGDPDPC','output_gdp_per_capita.xls')

Code

data001=read_excel('output_gdp_per_capita.xls') %>% clean_names()
head(data001)

# A tibble: 6 × 50
  gdp_per_capita_current…¹ x1980 x1981 x1982 x1983 x1984 x1985 x1986 x1987 x1988
  <chr>                    <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 <NA>                     <NA>  <NA>  <NA>  <NA>  <NA>  <NA>  <NA>  <NA>  <NA> 
2 Afghanistan              no d… no d… no d… no d… no d… no d… no d… no d… no d…
3 Albania                  728.… 817.… 824.… 815.… 788.… 788.… 855.… 832.… 805.…
4 Algeria                  2268… 2305… 2254… 2316… 2432… 2753… 2698… 2705… 2143…
5 Andorra                  no d… no d… no d… no d… no d… no d… no d… no d… no d…
6 Angola                   802.… 731.… 712.… 723.… 747.… 817.… 743.… 828.… 875.…
# ℹ abbreviated name: ¹​gdp_per_capita_current_prices_u_s_dollars_per_capita
# ℹ 40 more variables: x1989 <chr>, x1990 <chr>, x1991 <chr>, x1992 <chr>,
#   x1993 <chr>, x1994 <chr>, x1995 <chr>, x1996 <chr>, x1997 <chr>,
#   x1998 <chr>, x1999 <chr>, x2000 <chr>, x2001 <chr>, x2002 <chr>,
#   x2003 <chr>, x2004 <chr>, x2005 <chr>, x2006 <chr>, x2007 <chr>,
#   x2008 <chr>, x2009 <chr>, x2010 <chr>, x2011 <chr>, x2012 <chr>,
#   x2013 <chr>, x2014 <chr>, x2015 <chr>, x2016 <chr>, x2017 <chr>, …

delete first empty row

Code

data002=data001[-c(1), ]

wide to long

Code

data003=data002 %>% pivot_longer(!gdp_per_capita_current_prices_u_s_dollars_per_capita,names_to = "year", values_to = "GDP") %>% rename(country_name=gdp_per_capita_current_prices_u_s_dollars_per_capita) %>% mutate(GDP=as.numeric(GDP))

Code

data003=data003 %>% mutate(year_num=as.numeric(str_replace(year,'x',''))) %>% select(-year)

5 Asia 4 drgan and more

Code

Asia_4_drgan001=data003 %>%filter(country_name %in% c('Taiwan Province of China','Korea, Republic of','Singapore','Hong Kong SAR',"China, People's Republic of",'Japan'))

Code

glimpse(Asia_4_drgan001)

Rows: 294
Columns: 3
$ country_name <chr> "China, People's Republic of", "China, People's Republic …
$ GDP          <dbl> 306.980, 288.491, 279.971, 296.509, 301.111, 292.990, 279…
$ year_num     <dbl> 1980, 1981, 1982, 1983, 1984, 1985, 1986, 1987, 1988, 198…

Code

ggplot(Asia_4_drgan001, aes(year_num, GDP, colour = country_name)) + 
  geom_line()+ scale_y_continuous(labels = scales::label_number_si())

6 Reference

https://data.worldbank.org/indicator/NY.GDP.MKTP.CD

https://zh.wikipedia.org/zh-cn/%E4%BA%9A%E6%B4%B2%E5%9B%9B%E5%B0%8F%E9%BE%99

https://www.imf.org/external/datamapper/PPPGDP@WEO/TWN?zoom=TWN&highlight=TWN