# 05_check-traces.R
#
# content: (1) Look at broken trace
#          (2) Function to find broken traces
#          (3) DFG for complete data
#          (4) Export data frame for analyses
#
# input:  results/event_logfiles_2024-02-21_16-07-33.csv
#         results/raw_logfiles_2024-02-21_16-07-33.csv
# output: results/eventlogs_pre-corona_cleaned.RData
#         results/eventlogs_pre-corona_cleaned.csv
#         ../../thesis/figures/dfg_complete_WFnet_R.pdf
#
# last mod: 2024-03-23

# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")

#--------------- (1) Look at broken trace ---------------

datraw <- read.table("results/raw_logfiles_2024-02-21_16-07-33.csv",
                     header = TRUE, sep = ";")


datlogs <- read.table("results/event_logfiles_2024-02-21_16-07-33.csv",
                      colClasses = c("character", "character", "POSIXct",
                                     "POSIXct", "character", "integer",
                                     "numeric", "character", "character",
                                     rep("numeric", 3), "character",
                                     "character", rep("numeric", 11),
                                     "character", "character"),
                      sep = ";", header = TRUE)

artwork <- "176"
fileId <- c('2017_06_16-13_49_00.log', '2017_06_16-13_59_00.log')
path <- 106098

datraw[datraw$item == artwork & datraw$fileId %in% fileId, ]

datlogs[datlogs$path == path, ]

#--------------- (2) Function to find broken traces ---------------

tmp <- datlogs[datlogs$event != "move", ]

check_traces <- function(data) {

  datagg <- aggregate(event ~ path, data,
                      function(x) ifelse("openPopup" %in% x, T, F))
  paths <- datagg$path[datagg$event]
  datcheck <- data[data$path %in% paths, c("path", "event")]
  datcheck <- datcheck[!duplicated(datcheck), ]
  datcheck <- datcheck[order(datcheck$path), ]

  retval <- NULL
  for (path in unique(datcheck$path)) {
    check <- !all(as.character(datcheck$event[datcheck$path == path]) ==
                 c("flipCard", "openTopic", "openPopup"))
    retval <- rbind(retval, data.frame(path, check))
  }
  retval
}

check <- check_traces(tmp)

check[check$check, ]

#--------------- (3) DFG for complete data ---------------

tmp <- datlogs[datlogs$path != 106098, ]
tmp$start <- tmp$date.start
tmp$complete <- tmp$date.stop

alog <- bupaR::activitylog(tmp,
  case_id     = "path",
  activity_id = "event",
  resource_id = "item",
  timestamps  = c("start", "complete"))

dfg <- processmapR::process_map(alog,
  type_nodes = processmapR::frequency("relative", color_scale = "Greys"),
  sec_nodes  = processmapR::frequency("absolute"),
  type_edges = processmapR::frequency("relative", color_edges = "#FF6900"),
  sec_edges  = processmapR::frequency("absolute"),
  rankdir    = "LR",
  render     = FALSE)

processmapR::export_map(dfg,
  file_name = paste0("../../thesis/figures/dfg_complete_WFnet_R.pdf"),
  file_type = "pdf")

rm(tmp)

#--------------- (4) Export data frame for analyses ---------------

datlogs$event <- factor(datlogs$event, levels = c("move", "flipCard",
                                                  "openTopic",
                                                  "openPopup"))
datlogs$topic <- factor(datlogs$topic)

datlogs$weekdays <- factor(weekdays(datlogs$date.start),
                        levels = c("Montag", "Dienstag", "Mittwoch",
                                   "Donnerstag", "Freitag", "Samstag",
                                   "Sonntag"),
                        labels = c("Monday", "Tuesday", "Wednesday",
                                   "Thursday", "Friday", "Saturday",
                                   "Sunday"))

# Select data pre Corona
dat <- datlogs[as.Date(datlogs$date.start) < "2020-03-13", ]
# Remove corrupt trace
dat <- dat[dat$path != 106098, ]

save(dat, file = "results/eventlogs_pre-corona_cleaned.RData")

write.table(dat,
            file = "results/eventlogs_pre-corona_cleaned.csv",
            sep = ";",
            quote = FALSE,
            row.names = FALSE)