# Specifying needed data collection files
data_source <- c(
  "PASE_rev_v13.dta",
  "MFI_rev_v13.dta",
  "mdi_rev_v13.dta",
  "mmse_rev_v13.dta",
  "mrs_rev_v13.dta",
  "SDMT_rev_v13.dta",
  "who_rev_v13.dta"
)

## Cumulated data
dta<-read.csv("/Volumes/Data/exercise/source/background.csv",colClasses = "character", na.strings = c("NA","","unknown"))

# Getting full filenames
file_nms <- list.files("/Volumes/Data/STATA13",full.names = TRUE)[match(data_source,list.files("/Volumes/Data/STATA13"))]

# Loading datafiles

dta<-read.csv("/Volumes/Data/exercise/source/background.csv",colClasses = "character", na.strings = c("NA","","unknown"))

ls <- lapply(file_nms,function(i){
  d <- read_dta(i)
  colnames(d) <- tolower(gsub("instance","INSTANCE",colnames(d))) #in the sdmt dataset, instance column is lower case
  d
})

# Selecting desired variables
ls_sel <- lapply(seq_along(ls), function(i) {
  ls[[i]] |> select(cpr,
                    SYS_SITE,
                    INSTANCE,
                    starts_with("TALOS_")) |> as_factor() |> 
    full_join(select(dta,cpr, rnumb)) |> select(rnumb,everything())
})

# Naming lists according to file names
names(ls_sel) <- tolower(unlist(lapply(data_source,function(x){strsplit(x,"_")[[1]][1]})))

## Screening list and EOS data
subjects <- read_dta("/Volumes/Data/STATA13/inkl_rev_v13.dta") |>
  select(c("cpr", "rnumb", "rdate", "rtreat")) |>
  filter(rnumb != 999) |>
  left_join(read_dta("/Volumes/Data/STATA13/end_rev_v13.dta") |>
              select(c("cpr", "TALOS_end00", "TALOS_end01"))
            ) |>
  rename(enddate = TALOS_end00,
         eos_early = TALOS_end01) |>
  as_factor()