clear

*Create paths to folders 
global data "C:\Users\aapo.kivinen\Dropbox (Aalto)\PhD\teaching\Principles_of_Economic_Analysis\aapo\session one\data"
global output "C:\Users\aapo.kivinen\Dropbox (Aalto)\PhD\teaching\Principles_of_Economic_Analysis\aapo\session one\output"

*To make nicer graphs 
*ssc install grstyle (Run this if you have not downloaded it yet)
set scheme s2color
grstyle init
grstyle set plain

use "$data\cleaned_data.dta", replace 

*Calculate total 
egen total = rowtotal(population1524-population6574)

tabstat total, by(main_activity) stats(mean max min)

* Make numbers into millions:
replace total = total / 1000000


*Lets do the plotting step by step:
twoway connected total year if main_activity == "Employed"
*Change x-axis:
twoway connected total year if main_activity == "Employed", xlabel(1989(10)2019) 

*Add title for y-axis:
twoway connected total year if main_activity == "Employed", xlabel(1989(10)2019) ytitle("# of people in millions") legend(order(1 "Employed" 2 "Labour force" 3 "Total")) 

* Add other lines and legend:

twoway (connected total year if main_activity == "Employed") (connected total year if main_activity == "Labour force") (connected total year if main_activity == "Total"), xlabel(1989(10)2019) ytitle("# of people in millions") legend(order(1 "Employed" 2 "Labour force" 3 "Total")) 

* Save output as a pdf-file
graph export "$output\development.pdf", replace  

* Add another y-axis:

twoway (connected total year if main_activity == "Employed") (connected total year if main_activity == "Labour force", yaxis(2)), xlabel(1989(10)2019) ytitle("# of people in millions") legend(order(1 "Employed (left axis)" 2 "Labour force (right axis)")) ytitle("# of people in millions", axis(2))
graph export "$output\development2.pdf", replace  


*Calculate change in gdp and in employment
gen change_in_gdp = ((gdp-gdp[_n-1])/gdp[_n-1])*100 if year!=1987
gen change_in_Employed = ((total-total[_n-1])/total[_n-1])*100 if main_activity == "Employed" & main_activity[_n-1] == "Employed" & year!=1987

sum change_in_Employed change_in_gdp 

*Plot results 
twoway (scatter change_in_gdp change_in_Employed, mlabel(year) mlabsize(vsmall)) (lfit change_in_gdp change_in_Employed) if year>1987, ylabel(-10(5)10) xlabel(-10(5)10) legend(off) ytitle(%-change in gdp)  xtitle(%-change in Employment)
graph export "$output\correlation.pdf", replace