############################## # countries for green pillar # ############################# # library(haven) # library(writexl) # library(dplyr) # library(countrycode) # library(openxlsx) # library(questionr) # library(sjPlot) library(labelled) library(stringr) # library(purrr) # ---- Function to rename all countries ---- # Create a function to recode the country samples: # country abbreviations follow ISO codes 3166-1 alpha 2 as shown here: # https://www.iso.org/obp/ui/#search recoded_country <- function(df, country_variable) { df %>% mutate(country_new = case_when( str_detect(df[[country_variable]], "AL|29") ~ "AL", str_detect(df[[country_variable]], "AM") ~ "AM", str_detect(df[[country_variable]], "AR|AR-Argentina") ~ "AR", str_detect(df[[country_variable]], "AUS|AU|AUS-Australia|Australia") ~ "AU", str_detect(df[[country_variable]], "AT|AT-Austria|A-Austria|^1$") ~ "AT", str_detect(df[[country_variable]], "AZ") ~ "AZ", str_detect(df[[country_variable]], "BA") ~ "BA", str_detect(df[[country_variable]], "^BE$|BE-Belgium|^2$") ~ "BE", str_detect(df[[country_variable]], "BG|BG-Bulgaria|^3$") ~ "BG", str_detect(df[[country_variable]], "BY") ~ "BY", str_detect(df[[country_variable]], "CA|CA-Canada|CDN-Canada|Canada - CDN") ~ "CA", str_detect(df[[country_variable]], "CH|CH-Switzerland") ~ "CH", str_detect(df[[country_variable]], "CL|CL-Chile|RCH-Chile") ~ "CL", str_detect(df[[country_variable]], "CN|CN-China") ~ "CN", str_detect(df[[country_variable]], "^CY_TCC$|^CY$|^4$|^CY-TCC$") ~ "CY", str_detect(df[[country_variable]], "CZ|CZ-Czech Republic|CR-Czech Republic|Czech Republic - CR|^5$") ~ "CZ", str_detect(df[[country_variable]], "DE|DE-Germany|^6$|D-E|Germany-East|DE-E|D-W|Germany-West|DE-W|^DE_E$|^DE_W$") ~ "DE", str_detect(df[[country_variable]], "DK|DK-Denmark|^7$") ~ "DK", str_detect(df[[country_variable]], "EE|^8$") ~ "EE", str_detect(df[[country_variable]], "ES|ES-Spain|E-Spain|Spain - E|10") ~ "ES", str_detect(df[[country_variable]], "FI|FI-Finland|SF-Finland|11") ~ "FI", str_detect(df[[country_variable]], "FR|FR-France|12") ~ "FR", str_detect(df[[country_variable]], "^GB$|GB-Great Britain|GB-GBN|Great Britain") ~ "GB_GBN", str_detect(df[[country_variable]], "28") ~ "GB_UK", str_detect(df[[country_variable]], "GE") ~ "GE", str_detect(df[[country_variable]], "GR|GR-Greece|Greece - GR|^9$") ~ "GR", str_detect(df[[country_variable]], "HR|HR-Croatia|13") ~ "HR", str_detect(df[[country_variable]], "HU|HU-Hungary|H-Hungary|Hungary - H|14") ~ "HU", str_detect(df[[country_variable]], "IE|IRL-Ireland|Ireland - IRL|15") ~ "IE", str_detect(df[[country_variable]], "IL|IL-Israel") ~ "IL", str_detect(df[[country_variable]], "IN|IN-India") ~ "IN", str_detect(df[[country_variable]], "IS|IS-Iceland|30") ~ "IS", str_detect(df[[country_variable]], "IT|IT-Italy|I-Italy|Italy - I|16") ~ "IT", str_detect(df[[country_variable]], "JP|JP-Japan|J-Japan|Japan - J") ~ "JP", str_detect(df[[country_variable]], "KR|KR-Korea") ~ "KR", str_detect(df[[country_variable]], "LU|LU-Luxembourg|Luxembourg - LU|18") ~ "LU", str_detect(df[[country_variable]], "LV|LV-Latvia|19") ~ "LV", str_detect(df[[country_variable]], "LT|LT-Lithuania|17") ~ "LT", str_detect(df[[country_variable]], "ME|32") ~ "ME", str_detect(df[[country_variable]], "MK|FYR of Macedonia|33") ~ "MK", str_detect(df[[country_variable]], "MD") ~ "MD", str_detect(df[[country_variable]], "MX|MX-Mexico|MEX-Mexico") ~ "MX", str_detect(df[[country_variable]], "MT|20") ~ "MT", str_detect(df[[country_variable]], "NL|NL-Netherlands|21") ~ "NL", str_detect(df[[country_variable]], "NO|NO-Norway|N-Norway|Norway - N|34") ~ "NO", str_detect(df[[country_variable]], "NIRL|NIRL-Northern Ireland|GB-NIR") ~ "GB_NIR", str_detect(df[[country_variable]], "NZ|NZ-New Zealand") ~ "NZ", str_detect(df[[country_variable]], "PH|PH-Philippines|RP-Philippines|Philippines - RP") ~ "PH", str_detect(df[[country_variable]], "PL|PL-Poland|Poland - PL|22") ~ "PL", str_detect(df[[country_variable]], "PT|PT-Portugal|P-Portugal|23") ~ "PT", str_detect(df[[country_variable]], "RO|24") ~ "RO", str_detect(df[[country_variable]], "RS|35") ~ "RS", str_detect(df[[country_variable]], "RU|RU-Russia|RUS-Russia") ~ "RU", str_detect(df[[country_variable]], "SE|SE-Sweden|S-Sweden|25") ~ "SE", str_detect(df[[country_variable]], "SI|SI-Slovenia|SLO-Slovenia|Slovenia - SLO|26") ~ "SI", str_detect(df[[country_variable]], "SK|SK-Slovakia|27") ~ "SK", str_detect(df[[country_variable]], "TH|TH-Thailand") ~ "TH", str_detect(df[[country_variable]], "TR|TR-Turkey|36") ~ "TR", str_detect(df[[country_variable]], "TW") ~ "TW", str_detect(df[[country_variable]], "UA") ~ "UA", str_detect(df[[country_variable]], "US|US-United States|USA-United States") ~ "US", str_detect(df[[country_variable]], "XK|31") ~ "XK", str_detect(df[[country_variable]], "ZA|ZA-South Africa") ~ "ZA", str_detect(df[[country_variable]], "^BE-FLA$") ~ "BE_FLA", TRUE ~ df[[country_variable]] ), country_lng = case_when( str_detect(df[[country_variable]], "AL|29") ~ "Albania", str_detect(df[[country_variable]], "AM") ~ "Armenia", str_detect(df[[country_variable]], "AR|AR-Argentina") ~ "Argentina", str_detect(df[[country_variable]], "AUS|AU|AUS-Australia|Australia") ~ "Australia", str_detect(df[[country_variable]], "AT|AT-Austria|A-Austria|^1$") ~ "Austria", str_detect(df[[country_variable]], "AZ") ~ "Azerbaijan", str_detect(df[[country_variable]], "BA") ~ "Bosnia and Herzegovina", str_detect(df[[country_variable]], "^BE-FLA$") ~ "Belgium Flanders", str_detect(df[[country_variable]], "^BE$|BE-Belgium|^2$") ~ "Belgium", str_detect(df[[country_variable]], "BG|BG-Bulgaria|^3$") ~ "Bulgaria", str_detect(df[[country_variable]], "BY") ~ "Belarus", str_detect(df[[country_variable]], "CA|CA-Canada|CDN-Canada|Canada - CDN") ~ "Canada", str_detect(df[[country_variable]], "CH|CH-Switzerland") ~ "Switzerland", str_detect(df[[country_variable]], "CL|CL-Chile|RCH-Chile") ~ "Chile", str_detect(df[[country_variable]], "CN|CN-China") ~ "China", str_detect(df[[country_variable]], "^CY_TCC$|^CY$|^4$") ~ "Cyprus", str_detect(df[[country_variable]], "CZ|CZ-Czech Republic|CR-Czech Republic|Czech Republic - CR|^5$") ~ "Czech Republic", str_detect(df[[country_variable]], "DE|DE-Germany|^6$|D-E|Germany-East|DE-E|D-W|Germany-West|DE-W") ~ "Germany", str_detect(df[[country_variable]], "^DK$|DK-Denmark|^7$") ~ "Denmark", str_detect(df[[country_variable]], "EE|^8$") ~ "Estonia", str_detect(df[[country_variable]], "ES|ES-Spain|E-Spain|Spain - E|^10$") ~ "Spain", str_detect(df[[country_variable]], "FI|FI-Finland|SF-Finland|11") ~ "Finland", str_detect(df[[country_variable]], "FR|FR-France|12") ~ "France", str_detect(df[[country_variable]], "GB|GB-Great Britain|GB-GBN|Great Britain|28") ~ "Great Britain", str_detect(df[[country_variable]], "GE") ~ "Georgia", str_detect(df[[country_variable]], "GR|GR-Greece|Greece - GR|^9$") ~ "Greece", str_detect(df[[country_variable]], "HR|HR-Croatia|13") ~ "Croatia", str_detect(df[[country_variable]], "HU|HU-Hungary|H-Hungary|Hungary - H|14") ~ "Hungary", str_detect(df[[country_variable]], "IE|IRL-Ireland|Ireland - IRL|15") ~ "Ireland", str_detect(df[[country_variable]], "IL|IL-Israel") ~ "Israel", str_detect(df[[country_variable]], "IN|IN-India") ~ "India", str_detect(df[[country_variable]], "IS|IS-Iceland|30") ~ "Iceland", str_detect(df[[country_variable]], "IT|IT-Italy|I-Italy|Italy - I|16") ~ "Italy", str_detect(df[[country_variable]], "JP|JP-Japan|J-Japan|Japan - J") ~ "Japan", str_detect(df[[country_variable]], "KR|KR-Korea") ~ "Korea", str_detect(df[[country_variable]], "LU|LU-Luxembourg|Luxembourg - LU|18") ~ "Luxembourg", str_detect(df[[country_variable]], "LV|LV-Latvia|19") ~ "Latvia", str_detect(df[[country_variable]], "LT|LT-Lithuania|17") ~ "Lithuania", str_detect(df[[country_variable]], "^ME$|^32$") ~ "Montenegro", str_detect(df[[country_variable]], "MK|FYR of Macedonia|33") ~ "North Macedonia", str_detect(df[[country_variable]], "MD") ~ "Moldova", str_detect(df[[country_variable]], "MX|MX-Mexico|MEX-Mexico") ~ "Mexico", str_detect(df[[country_variable]], "MT|20") ~ "Malta", str_detect(df[[country_variable]], "NL|NL-Netherlands|21") ~ "Netherlands", str_detect(df[[country_variable]], "NO|NO-Norway|N-Norway|Norway - N|34") ~ "Norway", str_detect(df[[country_variable]], "GB-NIR|NIRL|NIRL-Northern Ireland") ~ "Northern Ireland", str_detect(df[[country_variable]], "NZ|NZ-New Zealand") ~ "New Zealand", str_detect(df[[country_variable]], "PH|PH-Philippines|RP-Philippines|Philippines - RP") ~ "Philippines", str_detect(df[[country_variable]], "PL|PL-Poland|Poland - PL|22") ~ "Poland", str_detect(df[[country_variable]], "PT|PT-Portugal|P-Portugal|23") ~ "Portugal", str_detect(df[[country_variable]], "RO|24") ~ "Romania", str_detect(df[[country_variable]], "RS|35") ~ "Serbia", str_detect(df[[country_variable]], "RU|RU-Russia|RUS-Russia") ~ "Russia", str_detect(df[[country_variable]], "SE|SE-Sweden|S-Sweden|25") ~ "Sweden", str_detect(df[[country_variable]], "SI|SI-Slovenia|SLO-Slovenia|Slovenia - SLO|26") ~ "Slovenia", str_detect(df[[country_variable]], "SK|SK-Slovakia|27") ~ "Slovakia", str_detect(df[[country_variable]], "TH|TH-Thailand") ~ "Thailand", str_detect(df[[country_variable]], "TR|TR-Turkey|36") ~ "Turkey", str_detect(df[[country_variable]], "TW") ~ "Taiwan", str_detect(df[[country_variable]], "UA") ~ "Ukraine", str_detect(df[[country_variable]], "US|US-United States|USA-United States") ~ "United States", str_detect(df[[country_variable]], "ZA|ZA-South Africa") ~ "South Africa", str_detect(df[[country_variable]], "XK|31") ~ "Kosovo", TRUE ~ df[[country_variable]] ) ) } # func_country <- function(df, country_variable) { # df %>% # mutate(country = case_when( # # Dynamically apply all country patterns using the list # str_detect(df[[country_variable]], "AL|29") ~ "AL", # str_detect(df[[country_variable]], "AM") ~ "AM", # str_detect(df[[country_variable]], "AR|AR-Argentina") ~ "AR", # str_detect(df[[country_variable]], "AUS|AU|AUS-Australia|Australia") ~ "AU", # str_detect(df[[country_variable]], "AT|AT-Austria|A-Austria|^1$") ~ "AT", # str_detect(df[[country_variable]], "AZ") ~ "AZ", # str_detect(df[[country_variable]], "BA") ~ "BA", # str_detect(df[[country_variable]], "^BE$|BE-Belgium|^2$") ~ "BE", # str_detect(df[[country_variable]], "BG|BG-Bulgaria|^3$") ~ "BG", # str_detect(df[[country_variable]], "BY") ~ "BY", # str_detect(df[[country_variable]], "CA|CA-Canada|CDN-Canada|Canada - CDN") ~ "CA", # str_detect(df[[country_variable]], "CH|CH-Switzerland") ~ "CH", # str_detect(df[[country_variable]], "CL|CL-Chile|RCH-Chile") ~ "CL", # str_detect(df[[country_variable]], "CN|CN-China") ~ "CN", # str_detect(df[[country_variable]], "^CY_TCC$|^CY$|^4$") ~ "CY", # str_detect(df[[country_variable]], "CZ|CZ-Czech Republic|CR-Czech Republic|Czech Republic - CR|^5$") ~ "CZ", # str_detect(df[[country_variable]], "DE|DE-Germany|^6$|D-E|Germany-East|DE-E|D-W|Germany-West|DE-W") ~ "DE", # str_detect(df[[country_variable]], "DK|DK-Denmark|^7$") ~ "DK", # str_detect(df[[country_variable]], "EE|^8$") ~ "EE", # str_detect(df[[country_variable]], "ES|ES-Spain|E-Spain|Spain - E|10") ~ "ES", # str_detect(df[[country_variable]], "FI|FI-Finland|SF-Finland|11") ~ "FI", # str_detect(df[[country_variable]], "FR|FR-France|12") ~ "FR", # str_detect(df[[country_variable]], "^GB$|GB-Great Britain|GB-GBN|Great Britain|28") ~ "GB", # str_detect(df[[country_variable]], "GE") ~ "GE", # str_detect(df[[country_variable]], "GR|GR-Greece|Greece - GR|^9$") ~ "GR", # str_detect(df[[country_variable]], "HR|HR-Croatia|13") ~ "HR", # str_detect(df[[country_variable]], "HU|HU-Hungary|H-Hungary|Hungary - H|14") ~ "HU", # str_detect(df[[country_variable]], "IE|IRL-Ireland|Ireland - IRL|15") ~ "IE", # str_detect(df[[country_variable]], "IL|IL-Israel") ~ "IL", # str_detect(df[[country_variable]], "IN|IN-India") ~ "IN", # str_detect(df[[country_variable]], "IS|IS-Iceland|30") ~ "IS", # str_detect(df[[country_variable]], "IT|IT-Italy|I-Italy|Italy - I|16") ~ "IT", # str_detect(df[[country_variable]], "JP|JP-Japan|J-Japan|Japan - J") ~ "JP", # str_detect(df[[country_variable]], "KR|KR-Korea") ~ "KR", # str_detect(df[[country_variable]], "LU|LU-Luxembourg|Luxembourg - LU|18") ~ "LU", # str_detect(df[[country_variable]], "LV|LV-Latvia|19") ~ "LV", # str_detect(df[[country_variable]], "LT|LT-Lithuania|17") ~ "LT", # str_detect(df[[country_variable]], "ME|32") ~ "ME", # str_detect(df[[country_variable]], "MK|FYR of Macedonia|33") ~ "MK", # str_detect(df[[country_variable]], "MD") ~ "MD", # str_detect(df[[country_variable]], "MX|MX-Mexico|MEX-Mexico") ~ "MX", # str_detect(df[[country_variable]], "MT|20") ~ "MT", # str_detect(df[[country_variable]], "NL|NL-Netherlands|21") ~ "NL", # str_detect(df[[country_variable]], "NO|NO-Norway|N-Norway|Norway - N|34") ~ "NO", # str_detect(df[[country_variable]], "NIRL|NIRL-Northern Ireland|GB-NIR") ~ "GB_IRL", # str_detect(df[[country_variable]], "NZ|NZ-New Zealand") ~ "NZ", # str_detect(df[[country_variable]], "PH|PH-Philippines|RP-Philippines|Philippines - RP") ~ "PH", # str_detect(df[[country_variable]], "PL|PL-Poland|Poland - PL|22") ~ "PL", # str_detect(df[[country_variable]], "PT|PT-Portugal|P-Portugal|23") ~ "PT", # str_detect(df[[country_variable]], "RO|24") ~ "RO", # str_detect(df[[country_variable]], "RS|35") ~ "RS", # str_detect(df[[country_variable]], "RU|RU-Russia|RUS-Russia") ~ "RU", # str_detect(df[[country_variable]], "SE|SE-Sweden|S-Sweden|25") ~ "SE", # str_detect(df[[country_variable]], "SI|SI-Slovenia|SLO-Slovenia|Slovenia - SLO|26") ~ "SI", # str_detect(df[[country_variable]], "SK|SK-Slovakia|27") ~ "SK", # str_detect(df[[country_variable]], "TH|TH-Thailand") ~ "TH", # str_detect(df[[country_variable]], "TR|TR-Turkey|36") ~ "TR", # str_detect(df[[country_variable]], "TW") ~ "TW", # str_detect(df[[country_variable]], "UA") ~ "UA", # str_detect(df[[country_variable]], "US|US-United States|USA-United States") ~ "US", # str_detect(df[[country_variable]], "XK|31") ~ "XK", # str_detect(df[[country_variable]], "ZA|ZA-South Africa") ~ "ZA", # str_detect(df[[country_variable]], "^BE-FLA$") ~ "BE_FLA", # TRUE ~ df[[country_variable]] # )) # } func_country_x <- function(df, country_variable) { df %>% mutate(country_source_recoded = case_when( str_detect(df[[country_variable]], "AL|29") ~ "AL", str_detect(df[[country_variable]], "AM") ~ "AM", str_detect(df[[country_variable]], "AR|AR-Argentina") ~ "AR", str_detect(df[[country_variable]], "AUS|AU|AUS-Australia|Australia") ~ "AU", str_detect(df[[country_variable]], "AT|AT-Austria|A-Austria|^1$") ~ "AT", str_detect(df[[country_variable]], "AZ") ~ "AZ", str_detect(df[[country_variable]], "BA") ~ "BA", str_detect(df[[country_variable]], "^BE$|BE-Belgium|^2$") ~ "BE", str_detect(df[[country_variable]], "BG|BG-Bulgaria|^3$") ~ "BG", str_detect(df[[country_variable]], "BY") ~ "BY", str_detect(df[[country_variable]], "CA|CA-Canada|CDN-Canada|Canada - CDN") ~ "CA", str_detect(df[[country_variable]], "CH|CH-Switzerland") ~ "CH", str_detect(df[[country_variable]], "CL|CL-Chile|RCH-Chile") ~ "CL", str_detect(df[[country_variable]], "CN|CN-China") ~ "CN", str_detect(df[[country_variable]], "^CY_TCC$|^CY$|^4$") ~ "CY", str_detect(df[[country_variable]], "CZ|CZ-Czech Republic|CR-Czech Republic|Czech Republic - CR|^5$") ~ "CZ", str_detect(df[[country_variable]], "DE|DE-Germany|^6$|D-E|Germany-East|DE-E|D-W|Germany-West|DE-W") ~ "DE", str_detect(df[[country_variable]], "DK|DK-Denmark|^7$") ~ "DK", str_detect(df[[country_variable]], "EE|^8$") ~ "EE", str_detect(df[[country_variable]], "ES|ES-Spain|E-Spain|Spain - E|10") ~ "ES", str_detect(df[[country_variable]], "FI|FI-Finland|SF-Finland|11") ~ "FI", str_detect(df[[country_variable]], "FR|FR-France|12") ~ "FR", str_detect(df[[country_variable]], "^GB$|GB-Great Britain|GB-GBN|Great Britain|28") ~ "GB", str_detect(df[[country_variable]], "GE") ~ "GE", str_detect(df[[country_variable]], "GR|GR-Greece|Greece - GR|^9$") ~ "GR", str_detect(df[[country_variable]], "HR|HR-Croatia|13") ~ "HR", str_detect(df[[country_variable]], "HU|HU-Hungary|H-Hungary|Hungary - H|14") ~ "HU", str_detect(df[[country_variable]], "IE|IRL-Ireland|Ireland - IRL|15") ~ "IE", str_detect(df[[country_variable]], "IL|IL-Israel") ~ "IL", str_detect(df[[country_variable]], "IN|IN-India") ~ "IN", str_detect(df[[country_variable]], "IS|IS-Iceland|30") ~ "IS", str_detect(df[[country_variable]], "IT|IT-Italy|I-Italy|Italy - I|16") ~ "IT", str_detect(df[[country_variable]], "JP|JP-Japan|J-Japan|Japan - J") ~ "JP", str_detect(df[[country_variable]], "KR|KR-Korea") ~ "KR", str_detect(df[[country_variable]], "LU|LU-Luxembourg|Luxembourg - LU|18") ~ "LU", str_detect(df[[country_variable]], "LV|LV-Latvia|19") ~ "LV", str_detect(df[[country_variable]], "LT|LT-Lithuania|17") ~ "LT", str_detect(df[[country_variable]], "ME|32") ~ "ME", str_detect(df[[country_variable]], "MK|FYR of Macedonia|33") ~ "MK", str_detect(df[[country_variable]], "MD") ~ "MD", str_detect(df[[country_variable]], "MX|MX-Mexico|MEX-Mexico") ~ "MX", str_detect(df[[country_variable]], "MT|20") ~ "MT", str_detect(df[[country_variable]], "NL|NL-Netherlands|21") ~ "NL", str_detect(df[[country_variable]], "NO|NO-Norway|N-Norway|Norway - N|34") ~ "NO", str_detect(df[[country_variable]], "NIRL|NIRL-Northern Ireland|GB-NIR") ~ "GB_IRL", str_detect(df[[country_variable]], "NZ|NZ-New Zealand") ~ "NZ", str_detect(df[[country_variable]], "PH|PH-Philippines|RP-Philippines|Philippines - RP") ~ "PH", str_detect(df[[country_variable]], "PL|PL-Poland|Poland - PL|22") ~ "PL", str_detect(df[[country_variable]], "PT|PT-Portugal|P-Portugal|23") ~ "PT", str_detect(df[[country_variable]], "RO|24") ~ "RO", str_detect(df[[country_variable]], "RS|35") ~ "RS", str_detect(df[[country_variable]], "RU|RU-Russia|RUS-Russia") ~ "RU", str_detect(df[[country_variable]], "SE|SE-Sweden|S-Sweden|25") ~ "SE", str_detect(df[[country_variable]], "SI|SI-Slovenia|SLO-Slovenia|Slovenia - SLO|26") ~ "SI", str_detect(df[[country_variable]], "SK|SK-Slovakia|27") ~ "SK", str_detect(df[[country_variable]], "TH|TH-Thailand") ~ "TH", str_detect(df[[country_variable]], "TR|TR-Turkey|36") ~ "TR", str_detect(df[[country_variable]], "TW") ~ "TW", str_detect(df[[country_variable]], "UA") ~ "UA", str_detect(df[[country_variable]], "US|US-United States|USA-United States") ~ "US", str_detect(df[[country_variable]], "XK|31") ~ "XK", str_detect(df[[country_variable]], "ZA|ZA-South Africa") ~ "ZA", str_detect(df[[country_variable]], "^BE-FLA$") ~ "BE_FLA", TRUE ~ df[[country_variable]] )) } func_country_sample <- function(df, country_variable) { df %>% mutate(country_source_recoded = case_when( str_detect(df[[country_variable]], "D-W|Germany-West|DE-W|DE_W") ~ "DE_W", str_detect(df[[country_variable]], "AL|29") ~ "AL", str_detect(df[[country_variable]], "AM") ~ "AM", str_detect(df[[country_variable]], "AR|AR-Argentina") ~ "AR", str_detect(df[[country_variable]], "AUS|AU|AUS-Australia|Australia") ~ "AU", str_detect(df[[country_variable]], "AT|AT-Austria|A-Austria|^1$") ~ "AT", str_detect(df[[country_variable]], "AZ") ~ "AZ", str_detect(df[[country_variable]], "BA") ~ "BA", str_detect(df[[country_variable]], "^BE$|BE-Belgium|^2$") ~ "BE", str_detect(df[[country_variable]], "BG|BG-Bulgaria|^3$") ~ "BG", str_detect(df[[country_variable]], "BY") ~ "BY", str_detect(df[[country_variable]], "CA|CA-Canada|CDN-Canada|Canada - CDN") ~ "CA", str_detect(df[[country_variable]], "CH|CH-Switzerland") ~ "CH", str_detect(df[[country_variable]], "CL|CL-Chile|RCH-Chile") ~ "CL", str_detect(df[[country_variable]], "CN|CN-China") ~ "CN", str_detect(df[[country_variable]], "^CY$|^4$") ~ "CY", str_detect(df[[country_variable]], "^CY-TCC$|CY-TCC") ~ "CY_TCC", str_detect(df[[country_variable]], "CZ|CZ-Czech Republic|CR-Czech Republic|Czech Republic - CR|^5$") ~ "CZ", str_detect(df[[country_variable]], "D-E|Germany-East|DE-E|DE_E") ~ "DE_E", str_detect(df[[country_variable]], "DE|DE-Germany|^6$") ~ "DE", str_detect(df[[country_variable]], "DK|DK-Denmark|^7$") ~ "DK", str_detect(df[[country_variable]], "EE|^8$") ~ "EE", str_detect(df[[country_variable]], "ES|ES-Spain|E-Spain|Spain - E|10") ~ "ES", str_detect(df[[country_variable]], "FI|FI-Finland|SF-Finland|11") ~ "FI", str_detect(df[[country_variable]], "FR|FR-France|12") ~ "FR", str_detect(df[[country_variable]], "^GB$|GB-Great Britain|GB-GBN|Great Britain") ~ "GB_GBN", str_detect(df[[country_variable]], "GE") ~ "GE", str_detect(df[[country_variable]], "GR|GR-Greece|Greece - GR|^9$") ~ "GR", str_detect(df[[country_variable]], "HR|HR-Croatia|13") ~ "HR", str_detect(df[[country_variable]], "HU|HU-Hungary|H-Hungary|Hungary - H|14") ~ "HU", str_detect(df[[country_variable]], "IE|IRL-Ireland|Ireland - IRL|15") ~ "IE", str_detect(df[[country_variable]], "IL|IL-Israel") ~ "IL", str_detect(df[[country_variable]], "IN|IN-India") ~ "IN", str_detect(df[[country_variable]], "IS|IS-Iceland|30") ~ "IS", str_detect(df[[country_variable]], "IT|IT-Italy|I-Italy|Italy - I|16") ~ "IT", str_detect(df[[country_variable]], "JP|JP-Japan|J-Japan|Japan - J") ~ "JP", str_detect(df[[country_variable]], "KR|KR-Korea") ~ "KR", str_detect(df[[country_variable]], "LU|LU-Luxembourg|Luxembourg - LU|18") ~ "LU", str_detect(df[[country_variable]], "LV|LV-Latvia|19") ~ "LV", str_detect(df[[country_variable]], "LT|LT-Lithuania|17") ~ "LT", str_detect(df[[country_variable]], "ME|32") ~ "ME", str_detect(df[[country_variable]], "MK|FYR of Macedonia|33") ~ "MK", str_detect(df[[country_variable]], "MD") ~ "MD", str_detect(df[[country_variable]], "MX|MX-Mexico|MEX-Mexico") ~ "MX", str_detect(df[[country_variable]], "MT|20") ~ "MT", str_detect(df[[country_variable]], "NL|NL-Netherlands|21") ~ "NL", str_detect(df[[country_variable]], "NO|NO-Norway|N-Norway|Norway - N|34") ~ "NO", str_detect(df[[country_variable]], "NIRL|NIRL-Northern Ireland|GB-NIR") ~ "GB_NIR", str_detect(df[[country_variable]], "NZ|NZ-New Zealand") ~ "NZ", str_detect(df[[country_variable]], "PH|PH-Philippines|RP-Philippines|Philippines - RP") ~ "PH", str_detect(df[[country_variable]], "PL|PL-Poland|Poland - PL|22") ~ "PL", str_detect(df[[country_variable]], "PT|PT-Portugal|P-Portugal|23") ~ "PT", str_detect(df[[country_variable]], "RO|24") ~ "RO", str_detect(df[[country_variable]], "RS|35") ~ "RS", str_detect(df[[country_variable]], "RU|RU-Russia|RUS-Russia") ~ "RU", str_detect(df[[country_variable]], "SE|SE-Sweden|S-Sweden|25") ~ "SE", str_detect(df[[country_variable]], "SI|SI-Slovenia|SLO-Slovenia|Slovenia - SLO|26") ~ "SI", str_detect(df[[country_variable]], "SK|SK-Slovakia|27") ~ "SK", str_detect(df[[country_variable]], "TH|TH-Thailand") ~ "TH", str_detect(df[[country_variable]], "TR|TR-Turkey|36") ~ "TR", str_detect(df[[country_variable]], "TW") ~ "TW", str_detect(df[[country_variable]], "UA") ~ "UA", str_detect(df[[country_variable]], "28") ~ "GB_UK", str_detect(df[[country_variable]], "US|US-United States|USA-United States") ~ "US", str_detect(df[[country_variable]], "XK|31") ~ "XK", str_detect(df[[country_variable]], "ZA|ZA-South Africa") ~ "ZA", str_detect(df[[country_variable]], "^BE-FLA$") ~ "BE_FLA", TRUE ~ df[[country_variable]] )) } # func_country <- function(df, country_variable) { # df %>% # mutate(country_source_rec = case_when( # # Dynamically apply all country patterns using the list # str_detect(df[[country_variable]], "AL|29") ~ "AL", # str_detect(df[[country_variable]], "AM") ~ "AM", # str_detect(df[[country_variable]], "AR|AR-Argentina") ~ "AR", # str_detect(df[[country_variable]], "AUS|AU|AUS-Australia|Australia") ~ "AU", # str_detect(df[[country_variable]], "AT|AT-Austria|A-Austria|^1$") ~ "AT", # str_detect(df[[country_variable]], "AZ") ~ "AZ", # str_detect(df[[country_variable]], "BA") ~ "BA", # str_detect(df[[country_variable]], "^BE$|BE-Belgium|^2$") ~ "BE", # str_detect(df[[country_variable]], "BG|BG-Bulgaria|^3$") ~ "BG", # str_detect(df[[country_variable]], "BY") ~ "BY", # str_detect(df[[country_variable]], "CA|CA-Canada|CDN-Canada|Canada - CDN") ~ "CA", # str_detect(df[[country_variable]], "CH|CH-Switzerland") ~ "CH", # str_detect(df[[country_variable]], "CL|CL-Chile|RCH-Chile") ~ "CL", # str_detect(df[[country_variable]], "CN|CN-China") ~ "CN", # str_detect(df[[country_variable]], "^CY$|^4$") ~ "CY", # str_detect(df[[country_variable]], "^CY_TCC$") ~ "CY_TCC", # str_detect(df[[country_variable]], "CZ|CZ-Czech Republic|CR-Czech Republic|Czech Republic - CR|^5$") ~ "CZ", # str_detect(df[[country_variable]], "DE|DE-Germany|^6$|D-E|Germany-East|DE-E|D-W|Germany-West|DE-W") ~ "DE", # str_detect(df[[country_variable]], "D-E|Germany-East|DE-E") ~ "DE_E", # str_detect(df[[country_variable]], "D-W|Germany-West|DE-W") ~ "DE_W", # str_detect(df[[country_variable]], "DK|DK-Denmark|^7$") ~ "DK", # str_detect(df[[country_variable]], "EE|^8$") ~ "EE", # str_detect(df[[country_variable]], "ES|ES-Spain|E-Spain|Spain - E|10") ~ "ES", # str_detect(df[[country_variable]], "FI|FI-Finland|SF-Finland|11") ~ "FI", # str_detect(df[[country_variable]], "FR|FR-France|12") ~ "FR", # str_detect(df[[country_variable]], "^GB$|GB-Great Britain|GB-GBN|Great Britain") ~ "GB_GBN", # str_detect(df[[country_variable]], "GE") ~ "GE", # str_detect(df[[country_variable]], "GR|GR-Greece|Greece - GR|^9$") ~ "GR", # str_detect(df[[country_variable]], "HR|HR-Croatia|13") ~ "HR", # str_detect(df[[country_variable]], "HU|HU-Hungary|H-Hungary|Hungary - H|14") ~ "HU", # str_detect(df[[country_variable]], "IE|IRL-Ireland|Ireland - IRL|15") ~ "IE", # str_detect(df[[country_variable]], "IL|IL-Israel") ~ "IL", # str_detect(df[[country_variable]], "IN|IN-India") ~ "IN", # str_detect(df[[country_variable]], "IS|IS-Iceland|30") ~ "IS", # str_detect(df[[country_variable]], "IT|IT-Italy|I-Italy|Italy - I|16") ~ "IT", # str_detect(df[[country_variable]], "JP|JP-Japan|J-Japan|Japan - J") ~ "JP", # str_detect(df[[country_variable]], "KR|KR-Korea") ~ "KR", # str_detect(df[[country_variable]], "LU|LU-Luxembourg|Luxembourg - LU|18") ~ "LU", # str_detect(df[[country_variable]], "LV|LV-Latvia|19") ~ "LV", # str_detect(df[[country_variable]], "LT|LT-Lithuania|17") ~ "LT", # str_detect(df[[country_variable]], "ME|32") ~ "ME", # str_detect(df[[country_variable]], "MK|FYR of Macedonia|33") ~ "MK", # str_detect(df[[country_variable]], "MD") ~ "MD", # str_detect(df[[country_variable]], "MX|MX-Mexico|MEX-Mexico") ~ "MX", # str_detect(df[[country_variable]], "MT|20") ~ "MT", # str_detect(df[[country_variable]], "NL|NL-Netherlands|21") ~ "NL", # str_detect(df[[country_variable]], "NO|NO-Norway|N-Norway|Norway - N|34") ~ "NO", # str_detect(df[[country_variable]], "NIRL|NIRL-Northern Ireland|GB-NIR") ~ "GB_IRL", # str_detect(df[[country_variable]], "NZ|NZ-New Zealand") ~ "NZ", # str_detect(df[[country_variable]], "PH|PH-Philippines|RP-Philippines|Philippines - RP") ~ "PH", # str_detect(df[[country_variable]], "PL|PL-Poland|Poland - PL|22") ~ "PL", # str_detect(df[[country_variable]], "PT|PT-Portugal|P-Portugal|23") ~ "PT", # str_detect(df[[country_variable]], "RO|24") ~ "RO", # str_detect(df[[country_variable]], "RS|35") ~ "RS", # str_detect(df[[country_variable]], "RU|RU-Russia|RUS-Russia") ~ "RU", # str_detect(df[[country_variable]], "SE|SE-Sweden|S-Sweden|25") ~ "SE", # str_detect(df[[country_variable]], "SI|SI-Slovenia|SLO-Slovenia|Slovenia - SLO|26") ~ "SI", # str_detect(df[[country_variable]], "SK|SK-Slovakia|27") ~ "SK", # str_detect(df[[country_variable]], "TH|TH-Thailand") ~ "TH", # str_detect(df[[country_variable]], "TR|TR-Turkey|36") ~ "TR", # str_detect(df[[country_variable]], "TW") ~ "TW", # str_detect(df[[country_variable]], "UA") ~ "UA", # str_detect(df[[country_variable]], "28") ~ "GB_UK", # str_detect(df[[country_variable]], "US|US-United States|USA-United States") ~ "US", # str_detect(df[[country_variable]], "XK|31") ~ "XK", # str_detect(df[[country_variable]], "ZA|ZA-South Africa") ~ "ZA", # str_detect(df[[country_variable]], "^BE-FLA$") ~ "BE_FLA", # TRUE ~ df[[country_variable]] # )) # } # TRUE ~ df[[country_variable]] # )) # } #function to create labels country_new_labels <- function(df, country_variable) { df %>% mutate(country_new = labelled( .data[[country_variable]], labels = c( "AL" = "Albania", "AM" = "Armenia", "AR" = "Argentina", "AU" = "Australia", "AT" = "Austria", "AZ" = "Azerbaijan", "BA" = "Bosnia and Herzegovina", "BE" = "Belgium", "BG" = "Bulgaria", "BY" = "Belarus", "CA" = "Canada", "CH" = "Switzerland", "CL" = "Chile", "CN" = "China", "CY" = "Cyprus", "CZ" = "Czech Republic", "DE" = "Germany", "DK" = "Denmark", "EE" = "Estonia", "ES" = "Spain", "FI" = "Finland", "FR" = "France", "GB_GBN" = "Great Britian", "GB_UK" = "United Kingdom", "GE" = "Georgia", "GR" = "Greece", "HR" = "Croatia", "HU" = "Hungary", "IE" = "Ireland", "IL" = "Israel", "IN" = "India", "IS" = "Iceland", "IT" = "Italy", "JP" = "Japan", "KR" = "Korea", "LU" = "Luxembourg", "LV" = "Latvia", "LT" = "Lithuania", "ME" = "Montenegro", "MK" = "North Macedonia", "MD" = "Moldova", "MX" = "Mexico", "MT" = "Malta", "NL" = "Netherlands", "NO" = "Norway", "GB_IRL" = "Northern Ireland", "NZ" = "New Zealand", "PH" = "Philippines", "PL" = "Poland", "PT" = "Portugal", "RO" = "Romania", "RS" = "Serbia", "RU" = "Russia", "SE" = "Sweden", "SI" = "Slovenia", "SK" = "Slovakia", "TH" = "Thailand", "TR" = "Turkey", "TW" = "Taiwan", "UA" = "Ukraine", "US" = "United States", "ZA" = "South Africa", "XK" = "Kosovo" ) )) } #function to create labels of country_source_recoded country_source_recoded_labels <- function(df, country_variable) { df %>% mutate(country_source_recoded = labelled( .data[[country_variable]], labels = c( "AL" = "Albania", "AM" = "Armenia", "AR" = "Argentina", "AU" = "Australia", "AT" = "Austria", "AZ" = "Azerbaijan", "BA" = "Bosnia and Herzegovina", "BE" = "Belgium", "BG" = "Bulgaria", "BY" = "Belarus", "CA" = "Canada", "CH" = "Switzerland", "CL" = "Chile", "CN" = "China", "CY" = "Cyprus", "CY_TCC" = "Northern Cyprus", "CZ" = "Czech Republic", "DE" = "Germany", "DE_E" = "East Germany", "DE_W" = "West Germany", "DK" = "Denmark", "EE" = "Estonia", "ES" = "Spain", "FI" = "Finland", "FR" = "France", "GB_GBN" = "Great Britian", "GB_UK" = "United Kingdom", "GE" = "Georgia", "GR" = "Greece", "HR" = "Croatia", "HU" = "Hungary", "IE" = "Ireland", "IL" = "Israel", "IN" = "India", "IS" = "Iceland", "IT" = "Italy", "JP" = "Japan", "KR" = "Korea", "LU" = "Luxembourg", "LV" = "Latvia", "LT" = "Lithuania", "ME" = "Montenegro", "MK" = "North Macedonia", "MD" = "Moldova", "MX" = "Mexico", "MT" = "Malta", "NL" = "Netherlands", "NO" = "Norway", "GB_NIR" = "Northern Ireland", "NZ" = "New Zealand", "PH" = "Philippines", "PL" = "Poland", "PT" = "Portugal", "RO" = "Romania", "RS" = "Serbia", "RU" = "Russia", "SE" = "Sweden", "SI" = "Slovenia", "SK" = "Slovakia", "TH" = "Thailand", "TR" = "Turkey", "TW" = "Taiwan", "UA" = "Ukraine", "US" = "United States", "ZA" = "South Africa", "XK" = "Kosovo" ) )) } labels_check <- c( "AL" = "Albania", "AM" = "Armenia", "AR" = "Argentina", "AU" = "Australia", "AT" = "Austria", "AZ" = "Azerbaijan", "BA" = "Bosnia and Herzegovina", "BE" = "Belgium", "BE_FLA" = "Belgium FLanders", "BG" = "Bulgaria", "BY" = "Belarus", "CA" = "Canada", "CH" = "Switzerland", "CL" = "Chile", "CN" = "China", "CY" = "Cyprus", "CZ" = "Czech Republic", "DE_E" = "East Germany after unification", "DE_W" = "West Germany after unification", "DE" = "Germany", "DK" = "Denmark", "EE" = "Estonia", "ES" = "Spain", "FI" = "Finland", "FR" = "France", "GB" = "Great Britain", "GE" = "Georgia", "GR" = "Greece", "HR" = "Croatia", "HU" = "Hungary", "IE" = "Ireland", "IL" = "Israel", "IN" = "India", "IS" = "Iceland", "IT" = "Italy", "JP" = "Japan", "KR" = "Korea", "LU" = "Luxembourg", "LV" = "Latvia", "LT" = "Lithuania", "ME" = "Montenegro", "MK" = "North Macedonia", "MD" = "Moldova", "MX" = "Mexico", "MT" = "Malta", "NL" = "Netherlands", "NO" = "Norway", "GB_IRL" = "Northern Ireland", "NZ" = "New Zealand", "PH" = "Philippines", "PL" = "Poland", "PT" = "Portugal", "RO" = "Romania", "RS" = "Serbia", "RU" = "Russia", "SE" = "Sweden", "SI" = "Slovenia", "SK" = "Slovakia", "TH" = "Thailand", "TR" = "Turkey", "TW" = "Taiwan", "UA" = "Ukraine", "US" = "United States", "ZA" = "South Africa", "XK" = "Kosovo" ) # Function to create numeric country variable num_recoded_country <- function(df, country_variable) { df %>% mutate(num_country_new = case_when( # Dynamically apply all country patterns using the list str_detect(df[[country_variable]], "Albania") ~ "008", str_detect(df[[country_variable]], "Argentina") ~ "032", str_detect(df[[country_variable]], "Armenia") ~ "051", str_detect(df[[country_variable]], "Australia") ~ "036", str_detect(df[[country_variable]], "Austria") ~ "040", str_detect(df[[country_variable]], "Azerbaijan") ~ "031", str_detect(df[[country_variable]], "Belgium") ~ "056", str_detect(df[[country_variable]], "Belarus") ~ "112", str_detect(df[[country_variable]], "Bosnia and Herzegovina") ~ "070", str_detect(df[[country_variable]], "Bulgaria") ~ "100", str_detect(df[[country_variable]], "Canada") ~ "124", str_detect(df[[country_variable]], "Chile") ~ "152", str_detect(df[[country_variable]], "China") ~ "156", str_detect(df[[country_variable]], "Croatia") ~ "191", str_detect(df[[country_variable]], "Cyprus") ~ "196", str_detect(df[[country_variable]], "Czechia") ~ "203", str_detect(df[[country_variable]], "Denmark") ~ "208", str_detect(df[[country_variable]], "Estonia") ~ "233", str_detect(df[[country_variable]], "Finland") ~ "246", str_detect(df[[country_variable]], "France") ~ "250", str_detect(df[[country_variable]], "Georgia") ~ "268", str_detect(df[[country_variable]], "Germany") ~ "276", str_detect(df[[country_variable]], "East Germany") ~ "27602", str_detect(df[[country_variable]], "West Germany") ~ "27601", str_detect(df[[country_variable]], "Greece") ~ "300", str_detect(df[[country_variable]], "Hungary") ~ "348", str_detect(df[[country_variable]], "Iceland") ~ "352", str_detect(df[[country_variable]], "India") ~ "356", str_detect(df[[country_variable]], "Ireland") ~ "372", str_detect(df[[country_variable]], "Israel") ~ "376", str_detect(df[[country_variable]], "Italy") ~ "380", str_detect(df[[country_variable]], "Japan") ~ "392", str_detect(df[[country_variable]], "Korea") ~ "410", str_detect(df[[country_variable]], "Latvia") ~ "428", str_detect(df[[country_variable]], "Lithuania") ~ "438", str_detect(df[[country_variable]], "Luxembourg") ~ "442", str_detect(df[[country_variable]], "Malta") ~ "470", str_detect(df[[country_variable]], "Mexico") ~ "484", str_detect(df[[country_variable]], "Moldova") ~ "498", str_detect(df[[country_variable]], "Montenegro") ~ "499", str_detect(df[[country_variable]], "Netherlands") ~ "528", str_detect(df[[country_variable]], "New Zealand") ~ "554", str_detect(df[[country_variable]], "Norway") ~ "578", str_detect(df[[country_variable]], "North Macedonia") ~ "807", str_detect(df[[country_variable]], "Philippines") ~ "608", str_detect(df[[country_variable]], "Poland") ~ "616", str_detect(df[[country_variable]], "Portugal") ~ "620", str_detect(df[[country_variable]], "Romania") ~ "642", str_detect(df[[country_variable]], "Russia") ~ "643", str_detect(df[[country_variable]], "Serbia") ~ "688", str_detect(df[[country_variable]], "Slovakia") ~ "703", str_detect(df[[country_variable]], "Slovenia") ~ "705", str_detect(df[[country_variable]], "South Africa") ~ "710", str_detect(df[[country_variable]], "Spain") ~ "724", str_detect(df[[country_variable]], "Sweden") ~ "752", str_detect(df[[country_variable]], "Switzerland") ~ "756", str_detect(df[[country_variable]], "Taiwan") ~ "158", str_detect(df[[country_variable]], "Thailand") ~ "764", str_detect(df[[country_variable]], "Turkey") ~ "792", str_detect(df[[country_variable]], "Ukraine") ~ "804", str_detect(df[[country_variable]], "United Kingdom") ~ "826", str_detect(df[[country_variable]], "Northern Ireland") ~ "82602", str_detect(df[[country_variable]], "United States") ~ "840", TRUE ~ df[[country_variable]] # Default if no match ))%>% mutate(num_country_new = as.numeric(as.character(num_country_new))) # Ensure num_country_new is numeric here } # Object to assign labels lab <- c( Albania = 8, Argentina = 32, Armenia = 51, Australia = 36, Austria = 40, Azerbaijan = 31, `Bosnia and Herzegovina` = 70, Belgium = 56, Bulgaria = 100, Belarus = 112, Canada = 124, Switzerland = 756, Chile = 152, China = 156, Cyprus = 196, `Czech Republic` = 203, `East Germany` = 27602, `West Germany` = 27601, Germany = 276, Denmark = 208, Estonia = 233, Spain = 724, Finland = 246, France = 250, `United Kingdom` = 826, Georgia = 268, Greece = 300, Croatia = 191, Hungary = 348, Ireland = 372, Israel = 376, India = 356, Iceland = 352, Italy = 380, Japan = 392, Korea = 410, Luxembourg = 442, Latvia = 428, Lithuania = 440, Montenegro = 499, `North Macedonia` = 807, Moldova = 498, Mexico = 484, Malta = 470, Netherlands = 528, Norway = 578, `Northern Ireland` = 82602, `New Zealand` = 554, Philippines = 608, Poland = 616, Portugal = 620, Romania = 642, Serbia = 688, Russia = 643, Sweden = 752, Slovenia = 705, Slovakia = 703, Thailand = 764, Turkey = 792, Taiwan = 158, Ukraine = 804, `United States` = 840, `South Africa` = 710 ) #code snippet to use for a country sample function (country selection comes form green pillar) # #function to create labels # country_new_labels <- function(df, country_variable) { # df %>% # mutate(country_new = labelled( # .data[[country_variable]], # labels = c( # "AL" = "Albania", # "AM" = "Armenia", # "AR" = "Argentina", # "AU" = "Australia", # "AT" = "Austria", # "AZ" = "Azerbaijan", # "BA" = "Bosnia and Herzegovina", # "BE" = "Belgium", # "BE_FLA" = "Belgium Flanders", # "BG" = "Bulgaria", # "BY" = "Belarus", # "CA" = "Canada", # "CH" = "Switzerland", # "CL" = "Chile", # "CN" = "China", # "CY_TCC" = "Nothern Cyprus", # "CY" = "Cyprus", # "CZ" = "Czech Republic", # "DE_E" = "East Germany after unification", # "DE_W" = "West Germany after unification", # "DE" = "Germany", # "DK" = "Denmark", # "EE" = "Estonia", # "ES" = "Spain", # "FI" = "Finland", # "FR" = "France", # "GB" = "Great Britian", # "GE" = "Georgia", # "GR" = "Greece", # "HR" = "Croatia", # "HU" = "Hungary", # "IE" = "Ireland", # "IL" = "Israel", # "IN" = "India", # "IS" = "Iceland", # "IT" = "Italy", # "JP" = "Japan", # "KR" = "Korea", # "LU" = "Luxembourg", # "LV" = "Latvia", # "LT" = "Lithuania", # "ME" = "Montenegro", # "MK" = "North Macedonia", # "MD" = "Moldova", # "MX" = "Mexico", # "MT" = "Malta", # "NL" = "Netherlands", # "NO" = "Norway", # "GB_IRL" = "Northern Ireland", # "NZ" = "New Zealand", # "PH" = "Philippines", # "PL" = "Poland", # "PT" = "Portugal", # "RO" = "Romania", # "RS" = "Serbia", # "RU" = "Russia", # "SE" = "Sweden", # "SI" = "Slovenia", # "SK" = "Slovakia", # "TH" = "Thailand", # "TR" = "Turkey", # "TW" = "Taiwan", # "UA" = "Ukraine", # "US" = "United States", # "ZA" = "South Africa", # "XK" = "Kosovo" # ) # )) # } # country_new_labels <- function(df, country_variable) { # df %>% # mutate(country_new = labelled( # country_new, # labels = c( # "AL" = "Albania", # "AM" = "Armenia", # "AR" = "Argentina", # "AU" = "Australia", # "AT" = "Austria", # "AZ" = "Azerbaijan", # "BA" = "Bosnia and Herzegovina", # "BE" = "Belgium", # "BE_FLA" = "Belgium FLanders", # "BG" = "Bulgaria", # "BY" = "Belarus", # "CA" = "Canada", # "CH" = "Switzerland", # "CL" = "Chile", # "CN" = "China", # "CY" = "Cyprus", # "CZ" = "Czech Republic", # "DE_E" = "East Germany after unification", # "DE_W" = "West Germany after unification", # "DE" = "Germany", # "DK" = "Denmark", # "EE" = "Estonia", # "ES" = "Spain", # "FI" = "Finland", # "FR" = "France", # "GB" = "Great Britian", # "GE" = "Georgia", # "GR" = "Greece", # "HR" = "Croatia", # "HU" = "Hungary", # "IE" = "Ireland", # "IL" = "Israel", # "IN" = "India", # "IS" = "Iceland", # "IT" = "Italy", # "JP" = "Japan", # "KR" = "Korea", # "LU" = "Luxembourg", # "LV" = "Latvia", # "LT" = "Lithuania", # "ME" = "Montenegro", # "MK" = "North Macedonia", # "MD" = "Moldova", # "MX" = "Mexico", # "MT" = "Malta", # "NL" = "Netherlands", # "NO" = "Norway", # "GB_IRL" = "Northern Ireland", # "NZ" = "New Zealand", # "PH" = "Philippines", # "PL" = "Poland", # "PT" = "Portugal", # "RO" = "Romania", # "RS" = "Serbia", # "RU" = "Russia", # "SE" = "Sweden", # "SI" = "Slovenia", # "SK" = "Slovakia", # "TH" = "Thailand", # "TR" = "Turkey", # "TW" = "Taiwan", # "UA" = "Ukraine", # "US" = "United States", # "ZA" = "South Africa", # "XK" = "Kosovo" # ), # default = "Unknown" # )) # } # code snippet of the country_sample code: problem: DE-W gets overwritten by DE # Dynamically apply all country patterns using the list # str_detect(df[[country_variable]], "AL|29") ~ "AL", # str_detect(df[[country_variable]], "AM") ~ "AM", # str_detect(df[[country_variable]], "AR|AR-Argentina") ~ "AR", # str_detect(df[[country_variable]], "AUS|AU|AUS-Australia|Australia") ~ "AU", # str_detect(df[[country_variable]], "AT|AT-Austria|A-Austria|^1$") ~ "AT", # str_detect(df[[country_variable]], "AZ") ~ "AZ", # str_detect(df[[country_variable]], "BA") ~ "BA", # str_detect(df[[country_variable]], "^BE-FLA$") ~ "BE_FLA", # str_detect(df[[country_variable]], "^BE$|BE-Belgium|^2$") ~ "BE", # str_detect(df[[country_variable]], "BG|BG-Bulgaria|^3$") ~ "BG", # str_detect(df[[country_variable]], "BY") ~ "BY", # str_detect(df[[country_variable]], "CA|CA-Canada|CDN-Canada|Canada - CDN") ~ "CA", # str_detect(df[[country_variable]], "CH|CH-Switzerland") ~ "CH", # str_detect(df[[country_variable]], "CL|CL-Chile|RCH-Chile") ~ "CL", # str_detect(df[[country_variable]], "CN|CN-China") ~ "CN", # str_detect(df[[country_variable]], "^CY_TCC$") ~ "CY_TCC", # str_detect(df[[country_variable]], "^CY$|^4$") ~ "CY", # str_detect(df[[country_variable]], "CZ|CZ-Czech Republic|CR-Czech Republic|Czech Republic - CR|^5$") ~ "CZ", # str_detect(df[[country_variable]], "^D-W$|Germany-West|^DE-W$") ~ "DE_W", # str_detect(df[[country_variable]], "^D-E$|Germany-East|^DE-E$") ~ "DE_E", # str_detect(df[[country_variable]], "^DE$|DE-Germany|^6$") ~ "DE", # str_detect(df[[country_variable]], "DK|DK-Denmark|^7$") ~ "DK", # str_detect(df[[country_variable]], "EE|^8$") ~ "EE", # str_detect(df[[country_variable]], "ES|ES-Spain|E-Spain|Spain - E|10") ~ "ES", # str_detect(df[[country_variable]], "FI|FI-Finland|SF-Finland|11") ~ "FI", # str_detect(df[[country_variable]], "FR|FR-France|12") ~ "FR", # str_detect(df[[country_variable]], "GB-NIR") ~ "GB_NIR", # str_detect(df[[country_variable]], "^GB$|GB-Great Britain|GB-GBN|Great Britain|28") ~ "GB", # str_detect(df[[country_variable]], "GE") ~ "GE", # str_detect(df[[country_variable]], "GR|GR-Greece|Greece - GR|^9$") ~ "GR", # str_detect(df[[country_variable]], "HR|HR-Croatia|13") ~ "HR", # str_detect(df[[country_variable]], "HU|HU-Hungary|H-Hungary|Hungary - H|14") ~ "HU", # str_detect(df[[country_variable]], "IE|IRL-Ireland|Ireland - IRL|15") ~ "IE", # str_detect(df[[country_variable]], "IL|IL-Israel") ~ "IL", # str_detect(df[[country_variable]], "IN|IN-India") ~ "IN", # str_detect(df[[country_variable]], "IS|IS-Iceland|30") ~ "IS", # str_detect(df[[country_variable]], "IT|IT-Italy|I-Italy|Italy - I|16") ~ "IT", # str_detect(df[[country_variable]], "JP|JP-Japan|J-Japan|Japan - J") ~ "JP", # str_detect(df[[country_variable]], "KR|KR-Korea") ~ "KR", # str_detect(df[[country_variable]], "LU|LU-Luxembourg|Luxembourg - LU|18") ~ "LU", # str_detect(df[[country_variable]], "LV|LV-Latvia|19") ~ "LV", # str_detect(df[[country_variable]], "LT|LT-Lithuania|17") ~ "LT", # str_detect(df[[country_variable]], "ME|32") ~ "ME", # str_detect(df[[country_variable]], "MK|FYR of Macedonia|33") ~ "MK", # str_detect(df[[country_variable]], "MD") ~ "MD", # str_detect(df[[country_variable]], "MX|MX-Mexico|MEX-Mexico") ~ "MX", # str_detect(df[[country_variable]], "MT|20") ~ "MT", # str_detect(df[[country_variable]], "NL|NL-Netherlands|21") ~ "NL", # str_detect(df[[country_variable]], "NO|NO-Norway|N-Norway|Norway - N|34") ~ "NO", # str_detect(df[[country_variable]], "NIRL|NIRL-Northern Ireland") ~ "GB_IRL", # str_detect(df[[country_variable]], "NZ|NZ-New Zealand") ~ "NZ", # str_detect(df[[country_variable]], "PH|PH-Philippines|RP-Philippines|Philippines - RP") ~ "PH", # str_detect(df[[country_variable]], "PL|PL-Poland|Poland - PL|22") ~ "PL", # str_detect(df[[country_variable]], "PT|PT-Portugal|P-Portugal|23") ~ "PT", # str_detect(df[[country_variable]], "RO|24") ~ "RO", # str_detect(df[[country_variable]], "RS|35") ~ "RS", # str_detect(df[[country_variable]], "RU|RU-Russia|RUS-Russia") ~ "RU", # str_detect(df[[country_variable]], "SE|SE-Sweden|S-Sweden|25") ~ "SE", # str_detect(df[[country_variable]], "SI|SI-Slovenia|SLO-Slovenia|Slovenia - SLO|26") ~ "SI", # str_detect(df[[country_variable]], "SK|SK-Slovakia|27") ~ "SK", # str_detect(df[[country_variable]], "TH|TH-Thailand") ~ "TH", # str_detect(df[[country_variable]], "TR|TR-Turkey|36") ~ "TR", # str_detect(df[[country_variable]], "TW") ~ "TW", # str_detect(df[[country_variable]], "UA") ~ "UA", # str_detect(df[[country_variable]], "US|US-United States|USA-United States") ~ "US", # str_detect(df[[country_variable]], "XK|31") ~ "XK", # str_detect(df[[country_variable]], "ZA|ZA-South Africa") ~ "ZA", # TRUE ~ df[[country_variable]] # ), # country_lng = case_when( # str_detect(df[[country_variable]], "AL|29") ~ "Albania", # str_detect(df[[country_variable]], "AM") ~ "Armenia", # str_detect(df[[country_variable]], "AR|AR-Argentina") ~ "Argentina", # str_detect(df[[country_variable]], "AUS|AU|AUS-Australia|Australia") ~ "Australia", # str_detect(df[[country_variable]], "AT|AT-Austria|A-Austria|^1$") ~ "Austria", # str_detect(df[[country_variable]], "AZ") ~ "Azerbaijan", # str_detect(df[[country_variable]], "BA") ~ "Bosnia and Herzegovina", # str_detect(df[[country_variable]], "^BE-FLA$") ~ "Belgium Flanders", # str_detect(df[[country_variable]], "^BE$|BE-Belgium|^2$") ~ "Belgium", # str_detect(df[[country_variable]], "BG|BG-Bulgaria|^3$") ~ "Bulgaria", # str_detect(df[[country_variable]], "BY") ~ "Belarus", # str_detect(df[[country_variable]], "CA|CA-Canada|CDN-Canada|Canada - CDN") ~ "Canada", # str_detect(df[[country_variable]], "CH|CH-Switzerland") ~ "Switzerland", # str_detect(df[[country_variable]], "CL|CL-Chile|RCH-Chile") ~ "Chile", # str_detect(df[[country_variable]], "CN|CN-China") ~ "China", # str_detect(df[[country_variable]], "^CY_TCC$") ~ "Nothern Cyprus", # str_detect(df[[country_variable]], "CY|^4$") ~ "Cyprus", # str_detect(df[[country_variable]], "CZ|CZ-Czech Republic|CR-Czech Republic|Czech Republic - CR|^5$") ~ "Czech Republic", # str_detect(df[[country_variable]], "D-E|Germany-East") ~ "East Germany", # str_detect(df[[country_variable]], "D-W|Germany-West") ~ "West Germany", # str_detect(df[[country_variable]], "DE|DE-Germany|^6$") ~ "Germany", # str_detect(df[[country_variable]], "^DK$|DK-Denmark|^7$") ~ "Denmark", # str_detect(df[[country_variable]], "EE|^8$") ~ "Estonia", # str_detect(df[[country_variable]], "ES|ES-Spain|E-Spain|Spain - E|^10$") ~ "Spain", # str_detect(df[[country_variable]], "FI|FI-Finland|SF-Finland|11") ~ "Finland", # str_detect(df[[country_variable]], "FR|FR-France|12") ~ "France", # str_detect(df[[country_variable]], "GB|GB-Great Britain|GB-GBN|Great Britain|28") ~ "Great Britain", # str_detect(df[[country_variable]], "GE") ~ "Georgia", # str_detect(df[[country_variable]], "GR|GR-Greece|Greece - GR|^9$") ~ "Greece", # str_detect(df[[country_variable]], "HR|HR-Croatia|13") ~ "Croatia", # str_detect(df[[country_variable]], "HU|HU-Hungary|H-Hungary|Hungary - H|14") ~ "Hungary", # str_detect(df[[country_variable]], "IE|IRL-Ireland|Ireland - IRL|15") ~ "Ireland", # str_detect(df[[country_variable]], "IL|IL-Israel") ~ "Israel", # str_detect(df[[country_variable]], "IN|IN-India") ~ "India", # str_detect(df[[country_variable]], "IS|IS-Iceland|30") ~ "Iceland", # str_detect(df[[country_variable]], "IT|IT-Italy|I-Italy|Italy - I|16") ~ "Italy", # str_detect(df[[country_variable]], "JP|JP-Japan|J-Japan|Japan - J") ~ "Japan", # str_detect(df[[country_variable]], "KR|KR-Korea") ~ "Korea", # str_detect(df[[country_variable]], "LU|LU-Luxembourg|Luxembourg - LU|18") ~ "Luxembourg", # str_detect(df[[country_variable]], "LV|LV-Latvia|19") ~ "Latvia", # str_detect(df[[country_variable]], "LT|LT-Lithuania|17") ~ "Lithuania", # str_detect(df[[country_variable]], "^ME$|^32$") ~ "Montenegro", # str_detect(df[[country_variable]], "MK|FYR of Macedonia|33") ~ "North Macedonia", # str_detect(df[[country_variable]], "MD") ~ "Moldova", # str_detect(df[[country_variable]], "MX|MX-Mexico|MEX-Mexico") ~ "Mexico", # str_detect(df[[country_variable]], "MT|20") ~ "Malta", # str_detect(df[[country_variable]], "NL|NL-Netherlands|21") ~ "Netherlands", # str_detect(df[[country_variable]], "NO|NO-Norway|N-Norway|Norway - N|34") ~ "Norway", # str_detect(df[[country_variable]], "GB-NIR|NIRL|NIRL-Northern Ireland") ~ "Northern Ireland", # str_detect(df[[country_variable]], "NZ|NZ-New Zealand") ~ "New Zealand", # str_detect(df[[country_variable]], "PH|PH-Philippines|RP-Philippines|Philippines - RP") ~ "Philippines", # str_detect(df[[country_variable]], "PL|PL-Poland|Poland - PL|22") ~ "Poland", # str_detect(df[[country_variable]], "PT|PT-Portugal|P-Portugal|23") ~ "Portugal", # str_detect(df[[country_variable]], "RO|24") ~ "Romania", # str_detect(df[[country_variable]], "RS|35") ~ "Serbia", # str_detect(df[[country_variable]], "RU|RU-Russia|RUS-Russia") ~ "Russia", # str_detect(df[[country_variable]], "SE|SE-Sweden|S-Sweden|25") ~ "Sweden", # str_detect(df[[country_variable]], "SI|SI-Slovenia|SLO-Slovenia|Slovenia - SLO|26") ~ "Slovenia", # str_detect(df[[country_variable]], "SK|SK-Slovakia|27") ~ "Slovakia", # str_detect(df[[country_variable]], "TH|TH-Thailand") ~ "Thailand", # str_detect(df[[country_variable]], "TR|TR-Turkey|36") ~ "Turkey", # str_detect(df[[country_variable]], "TW") ~ "Taiwan", # str_detect(df[[country_variable]], "UA") ~ "Ukraine", # str_detect(df[[country_variable]], "US|US-United States|USA-United States") ~ "United States", # str_detect(df[[country_variable]], "ZA|ZA-South Africa") ~ "South Africa", # str_detect(df[[country_variable]], "XK|31") ~ "Kosovo", # TRUE ~ df[[country_variable]] # ) # ) # } # Example of how to apply recoded_country, num_recoded_country and the labels # # Load data # ESS1 <- read_sav("I:/Team_IntUm/Infra4NextGen/Survey_Programmes/ESS/data/ESS1e06_7.sav") # # # Apply recoded_country function # # (change "cntry" if country variable named differently in source data) # ESS1_new_cntry <- recoded_country(ESS1, "cntry") # # # Apply num_recoded_country function # ESS1_new_cntry <- num_recoded_country(ESS1_new_cntry, "country_new") # # # Set labels # ESS1_new_cntry <- ESS1_new_cntry %>% # labelled::set_value_labels(num_country_new = lab) # labelled::val_labels(ESS1_new_cntry$num_country_new)