Data Cleaning

Data Cleaning

Scopus merge with Web of Science

Merging Scopus and Web of Science data.

All Open Access

common_col_all_oa_names <- intersect(names(scopus_all_oa), names(wos_all_oa)) #Find common column names
scopus_wos_all_oa <- merge(scopus_all_oa, wos_all_oa, by=common_col_all_oa_names, all.x=TRUE) # Merge data by common column names to check if scopus missed any publications wos has.

Green

common_col_green_names <- intersect(names(scopus_green), names(wos_green)) #Find common column names
scopus_wos_green <- merge(scopus_green, wos_green, by=common_col_green_names, all.x=TRUE) # Merge data by common column names to check if scopus missed any publications wos has.

Green Final

common_col_green_final_names <- intersect(names(scopus_green_final), names(wos_green_final)) #Find common column names
scopus_wos_green_final <- merge(scopus_green_final, wos_green_final, by=common_col_green_final_names, all.x=TRUE) # Merge data by common column names to check if scopus missed any publications wos has.

Green Accepted

common_col_green_accepted_names <- intersect(names(scopus_green_accepted), names(wos_green_accepted)) #Find common column names
scopus_wos_green_accepted <- merge(scopus_green_accepted, wos_green_accepted, by=common_col_green_accepted_names, all.x=TRUE) # Merge data by common column names to check if scopus missed any publications wos has.

Not Green

common_col_not_green_names <- intersect(names(scopus_not_green), names(wos_not_green)) #Find common column names
scopus_wos_not_green <- merge(scopus_not_green, wos_not_green, by=common_col_not_green_names, all.x=TRUE) # Merge data by common column names to check if scopus missed any publications wos has.

Just Corresponding authors

Cleaning to just corresponding authors

all_oa_corr <- scopus_wos_all_oa %>% dplyr::filter(grepl("@northumbria",RP, ignore.case = TRUE))
all_oa_single_authors<- all_oa_corr %>% 
    mutate(AU = strsplit(as.character(AU), ";")) %>%  
    unnest(AU) #Individual authors

green_corr <- scopus_wos_green %>% dplyr::filter(grepl("@northumbria",RP, ignore.case = TRUE))
green_single_authors<- green_corr %>% 
    mutate(AU = strsplit(as.character(AU), ";")) %>%  
    unnest(AU) #Individual authors

green_final_corr <- scopus_wos_green_final %>% dplyr::filter(grepl("@northumbria",RP, ignore.case = TRUE))
green_final_single_authors<- green_final_corr %>% 
    mutate(AU = strsplit(as.character(AU), ";")) %>%  
    unnest(AU) #Individual authors

green_accepted_corr <- scopus_wos_green_accepted %>% dplyr::filter(grepl("@northumbria",RP, ignore.case = TRUE))
green_accepted_single_authors<- green_accepted_corr %>% 
    mutate(AU = strsplit(as.character(AU), ";")) %>%  
    unnest(AU) #Individual authors

not_green_corr <- scopus_wos_not_green %>% dplyr::filter(grepl("@northumbria",RP, ignore.case = TRUE))
not_green_single_authors<- not_green_corr %>% 
    mutate(AU = strsplit(as.character(AU), ";")) %>%  
    unnest(AU) #Individual authors

all_oa_single_authors$RP <- sub(';.*', "" , as.character(all_oa_single_authors$RP))
all_oa_single_authors$RP <- gsub(',',"", as.character(all_oa_single_authors$RP))
all_oa_single_authors$RP <- gsub('\\.',"", as.character(all_oa_single_authors$RP))
#Removing problem characters fo filtering to just corresponding authors.
rp_single_author_all_oa <- subset(all_oa_single_authors, AU == RP)

green_single_authors$RP <- sub(';.*', "" , as.character(green_single_authors$RP))
green_single_authors$RP <- gsub(',',"", as.character(green_single_authors$RP))
green_single_authors$RP <- gsub('\\.',"", as.character(green_single_authors$RP))
#Removing problem characters fo filtering to just corresponding authors.
rp_single_author_green <- subset(green_single_authors, AU == RP)

green_final_single_authors$RP <- sub(';.*', "" , as.character(green_final_single_authors$RP))
green_final_single_authors$RP <- gsub(',',"", as.character(green_final_single_authors$RP))
green_final_single_authors$RP <- gsub('\\.',"", as.character(green_final_single_authors$RP))
#Removing problem characters fo filtering to just corresponding authors.
rp_single_author_green_final <- subset(green_final_single_authors, AU == RP)

green_accepted_single_authors$RP <- sub(';.*', "" , as.character(green_accepted_single_authors$RP))
green_accepted_single_authors$RP <- gsub(',',"", as.character(green_accepted_single_authors$RP))
green_accepted_single_authors$RP <- gsub('\\.',"", as.character(green_accepted_single_authors$RP))
#Removing problem characters fo filtering to just corresponding authors.
rp_single_author_green_accepted <- subset(green_accepted_single_authors, AU == RP)

not_green_single_authors$RP <- sub(';.*', "" , as.character(not_green_single_authors$RP))
not_green_single_authors$RP <- gsub(',',"", as.character(not_green_single_authors$RP))
not_green_single_authors$RP <- gsub('\\.',"", as.character(not_green_single_authors$RP))
#Removing problem characters fo filtering to just corresponding authors.
rp_single_author_not_green <- subset(not_green_single_authors, AU == RP)

Check for duplicates!

duplicates_green_green<-inner_join(scopus_wos_not_green, scopus_wos_green_final, scopus_wos_green_accepted, by='DI')

duplicates_not_green_green_final<-inner_join(scopus_wos_not_green, scopus_wos_green_final, scopus_wos_green, by='DI')

duplicates_not_green_green_acccepted<-inner_join(scopus_wos_not_green, scopus_wos_green_accepted, scopus_wos_green, by='DI')

duplicates_green_final_green_acccepted<-inner_join(scopus_green_final, scopus_wos_green_accepted, scopus_wos_green, by='DI')