/*
Purpose: assign the latest industry classification to all years 
*/
clear all

if "`1'"==""{
	global CMF_pipeline "../.."
}

global strings "${CMF_pipeline}/2_string_cleaning/crosswalks"
global industry "${CMF_pipeline}/5_industry_assignment"
global interm "${industry}/intermediate_files"
global county_assigned "${CMF_pipeline}/4_county_assignment/output"
global output "${industry}/output"



// -------- Assign industries to reshaped data (1850–1870) --------
foreach y in 1850 1860 1870 {
    use "${county_assigned}/`y'_county_fips_assigned.dta", clear
	cap drop ind_detailed ind_broadest ind_leontief ind_granular //var kept in prev data.
	cap drop _merge
	do "${industry}/code/industry_raw_clean" //generate `industry'
	cap drop _m
	merge m:1 industry using "${industry}/intermediate_files/industry_to_merge.dta", nogen keep(1 3)
    compress
	sort file_name firm_number
	
	do "${industry}/code/infer_industry_classification.do"
    save "${output}/`y'_industry_assigned.dta", replace
}

// -------- General 1880 schedule --------
use "${county_assigned}/1880_general_schedule_county_fips_assigned.dta", clear
cap drop industry ind_detailed ind_broadest ind_leontief ind_granular 
cap drop file_name6
do "${industry}/code/industry_raw_clean" //generate `industry'
merge m:1 industry using "$industry/intermediate_files/industry_to_merge.dta", nogen keep(1 3)
compress
missings dropvars, force
do "${industry}/code/infer_industry_classification.do"
save "${output}/1880_general_schedule_industry_assigned.dta", replace

// -------- Special schedules (SS1–SS12, 1880) --------
// Each block loads county-assigned data, drops old classifications,
// creates/assigns industry labels, merges with crosswalks, then saves output.

use "${county_assigned}/1880_SS1_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "agriculture implements"
gen ind_detailed = "agricultural implements"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop  _merge
save "${output}/1880_SS1_industry_assigned.dta", replace

use "${county_assigned}/1880_SS2_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "paper"
gen ind_detailed = "paper"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS2_industry_assigned.dta", replace

use "${county_assigned}/1880_SS3_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "boots and shoes"
gen ind_detailed = "boots and shoes"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS3_industry_assigned.dta", replace

use "${county_assigned}/1880_SS4_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "leather (tanned and curried)"
gen ind_detailed1 = "leather, tanned"
gen ind_detailed2 = "leather, curried"
forvalues i = 1/2 {
        rename ind_detailed`i' ind_detailed
        merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
        rename ind_leontief ind_leontief`i'
        rename ind_granular ind_granular`i'
		rename ind_broadest ind_broadest`i'
        rename ind_detailed ind_detailed`i'
		drop if _merge==2
        drop _merge
}
save "${output}/1880_SS4_industry_assigned.dta", replace

use "${county_assigned}/1880_SS5_county_fips_assigned.dta", clear
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
cap drop file_name6
gen industry_recorded = "lumber mills and saw mills"
gen ind_detailed = "lumber, sawed"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS5_industry_assigned.dta", replace

use "${county_assigned}/1880_SS6_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "brick yards and tile works"
gen ind_detailed1 = "brick"
gen ind_detailed2 = "brick, stone, and tile, n.s."
forvalues i = 1/2 {
        rename ind_detailed`i' ind_detailed
        merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
        rename ind_leontief ind_leontief`i'
        rename ind_granular ind_granular`i'
		rename ind_broadest ind_broadest`i'
        rename ind_detailed ind_detailed`i'
		drop if _merge==2
        drop _merge
}
save "${output}/1880_SS6_industry_assigned.dta", replace

use "${county_assigned}/1880_SS7_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "flour and grist mills"
gen ind_detailed = "flour and grist mills"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS7_industry_assigned.dta", replace

use "${county_assigned}/1880_SS8_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "cheese, butter and condensed milk factory"
gen ind_detailed = "butter and cheese"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS8_industry_assigned.dta", replace

use "${county_assigned}/1880_SS9_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "slaughtering and meat-packing"
gen ind_detailed = "slaughter and meat packing"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS9_industry_assigned.dta", replace

use "${county_assigned}/1880_SS10_county_fips_assigned.dta", clear
cap drop file_name6
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen industry_recorded = "salt works"
gen ind_detailed = "salt"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS10_industry_assigned.dta", replace


use "${county_assigned}/1880_SS11_county_fips_assigned.dta", clear
gen industry_recorded = "small coal mines"
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen ind_detailed = "mining, coal"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS11_industry_assigned.dta", replace


use "${county_assigned}/1880_SS12_county_fips_assigned.dta", clear
gen industry_recorded = "quarries"
cap drop ind_detailed ind_broadest ind_leontief ind_granular    
gen ind_detailed = "quarrying"
merge m:1 ind_detailed using "$interm/new_industry_crosswalk.dta"
drop if _merge==2
drop _merge
save "${output}/1880_SS12_industry_assigned.dta", replace