R Markdown

library(readxl)
penn <- read_excel("C:/Users/ranja/Downloads/pwt100 (1).xlsx", 
    sheet = "Data")
penn
## # A tibble: 12,810 × 52
##    countrycode country currency_unit   year rgdpe rgdpo   pop   emp   avh    hc
##    <chr>       <chr>   <chr>          <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
##  1 ABW         Aruba   Aruban Guilder  1950    NA    NA    NA    NA    NA    NA
##  2 ABW         Aruba   Aruban Guilder  1951    NA    NA    NA    NA    NA    NA
##  3 ABW         Aruba   Aruban Guilder  1952    NA    NA    NA    NA    NA    NA
##  4 ABW         Aruba   Aruban Guilder  1953    NA    NA    NA    NA    NA    NA
##  5 ABW         Aruba   Aruban Guilder  1954    NA    NA    NA    NA    NA    NA
##  6 ABW         Aruba   Aruban Guilder  1955    NA    NA    NA    NA    NA    NA
##  7 ABW         Aruba   Aruban Guilder  1956    NA    NA    NA    NA    NA    NA
##  8 ABW         Aruba   Aruban Guilder  1957    NA    NA    NA    NA    NA    NA
##  9 ABW         Aruba   Aruban Guilder  1958    NA    NA    NA    NA    NA    NA
## 10 ABW         Aruba   Aruban Guilder  1959    NA    NA    NA    NA    NA    NA
## # ℹ 12,800 more rows
## # ℹ 42 more variables: ccon <dbl>, cda <dbl>, cgdpe <dbl>, cgdpo <dbl>,
## #   cn <dbl>, ck <dbl>, ctfp <dbl>, cwtfp <dbl>, rgdpna <dbl>, rconna <dbl>,
## #   rdana <dbl>, rnna <dbl>, rkna <dbl>, rtfpna <dbl>, rwtfpna <dbl>,
## #   labsh <dbl>, irr <dbl>, delta <dbl>, xr <dbl>, pl_con <dbl>, pl_da <dbl>,
## #   pl_gdpo <dbl>, i_cig <chr>, i_xm <chr>, i_xr <chr>, i_outlier <chr>,
## #   i_irr <chr>, cor_exp <dbl>, statcap <dbl>, csh_c <dbl>, csh_i <dbl>, …

This is PENN WORLD DATA.

penn
## # A tibble: 12,810 × 52
##    countrycode country currency_unit   year rgdpe rgdpo   pop   emp   avh    hc
##    <chr>       <chr>   <chr>          <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
##  1 ABW         Aruba   Aruban Guilder  1950    NA    NA    NA    NA    NA    NA
##  2 ABW         Aruba   Aruban Guilder  1951    NA    NA    NA    NA    NA    NA
##  3 ABW         Aruba   Aruban Guilder  1952    NA    NA    NA    NA    NA    NA
##  4 ABW         Aruba   Aruban Guilder  1953    NA    NA    NA    NA    NA    NA
##  5 ABW         Aruba   Aruban Guilder  1954    NA    NA    NA    NA    NA    NA
##  6 ABW         Aruba   Aruban Guilder  1955    NA    NA    NA    NA    NA    NA
##  7 ABW         Aruba   Aruban Guilder  1956    NA    NA    NA    NA    NA    NA
##  8 ABW         Aruba   Aruban Guilder  1957    NA    NA    NA    NA    NA    NA
##  9 ABW         Aruba   Aruban Guilder  1958    NA    NA    NA    NA    NA    NA
## 10 ABW         Aruba   Aruban Guilder  1959    NA    NA    NA    NA    NA    NA
## # ℹ 12,800 more rows
## # ℹ 42 more variables: ccon <dbl>, cda <dbl>, cgdpe <dbl>, cgdpo <dbl>,
## #   cn <dbl>, ck <dbl>, ctfp <dbl>, cwtfp <dbl>, rgdpna <dbl>, rconna <dbl>,
## #   rdana <dbl>, rnna <dbl>, rkna <dbl>, rtfpna <dbl>, rwtfpna <dbl>,
## #   labsh <dbl>, irr <dbl>, delta <dbl>, xr <dbl>, pl_con <dbl>, pl_da <dbl>,
## #   pl_gdpo <dbl>, i_cig <chr>, i_xm <chr>, i_xr <chr>, i_outlier <chr>,
## #   i_irr <chr>, cor_exp <dbl>, statcap <dbl>, csh_c <dbl>, csh_i <dbl>, …
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.4.2
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
penn%>%
  group_by(country)%>%
  select(country,avh)%>%
  filter(!is.na(avh))%>%
  summarize(average_avh=mean(avh))%>%
  mutate(wwk=average_avh/52)
## # A tibble: 69 × 3
##    country    average_avh   wwk
##    <chr>            <dbl> <dbl>
##  1 Argentina        1905.  36.6
##  2 Australia        1891.  36.4
##  3 Austria          1856.  35.7
##  4 Bangladesh       2502.  48.1
##  5 Belgium          1745.  33.6
##  6 Brazil           1945.  37.4
##  7 Bulgaria         1658.  31.9
##  8 Cambodia         2352.  45.2
##  9 Canada           1872.  36.0
## 10 Chile            2267.  43.6
## # ℹ 59 more rows

Neighboring Countries

Below operations are done on countries like India, china, pakistan,bangladesh.

country1=c("India","China","Pakistan","Sri Lanka","Nepal")
penn%>%
  group_by(country)%>%
  select(country,pop,year)%>%
  filter(country==country1)%>%
  filter(year>2010)%>%
  summarize(average_pop=mean(pop))
## # A tibble: 5 × 2
##   country   average_pop
##   <chr>           <dbl>
## 1 China          1395. 
## 2 India          1310. 
## 3 Nepal            27.8
## 4 Pakistan        198. 
## 5 Sri Lanka        20.9