# 09_case-clustering.R
#
# content: (1) Read data
#           (1.1) Read log event data
#           (1.2) Extract additional infos for clustering
#          (2) Clustering
#
# input:  results/haum/event_logfiles_2024-01-18_09-58-52.csv
# output: results/haum/event_logfiles_pre-corona_with-clusters_cases.csv
#
# last mod: 2024-02-04


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

library(bupaverse)
library(factoextra)

#--------------- (1) Read data ---------------

#--------------- (1.1) Read log event data ---------------

dat0 <- read.table("results/haum/event_logfiles_2024-01-18_09-58-52.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)
dat0$event <- factor(dat0$event, levels = c("move", "flipCard", "openTopic",
                                          "openPopup"))

dat0$weekdays <- factor(weekdays(dat0$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 <- dat0[as.Date(dat0$date.start) < "2020-03-13", ]
dat <- dat[dat$path != 106098, ]

#--------------- (1.2) Extract additional infos for clustering ---------------

datcase <- aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~
                     case, dat, function(x) mean(x, na.rm = TRUE), na.action = NULL)

datcase$length <- aggregate(item ~ case, dat, length)$item
datcase$nitems <- aggregate(item ~ case, dat, function(x)
                            length(unique(x)), na.action = NULL)$item
datcase$npaths <- aggregate(path ~ case, dat, function(x)
                            length(unique(x)), na.action = NULL)$path

# datcase$ntopics <- aggregate(topic ~ case, dat,
#                              function(x) ifelse(all(is.na(x)), NA, length(unique(na.omit(x)))),
#                              na.action = NULL)$topic
# 
datcase$vacation <- aggregate(vacation ~ case, dat,
                              function(x) ifelse(all(is.na(x)), 0, 1),
                              na.action = NULL)$vacation
datcase$holiday <- aggregate(holiday ~ case, dat,
                             function(x) ifelse(all(is.na(x)), 0, 1),
                             na.action = NULL)$holiday
datcase$weekend <- aggregate(weekdays ~ case, dat,
                             function(x) ifelse(any(x %in% c("Saturday", "Sunday")), 1, 0),
                             na.action = NULL)$weekdays
datcase$morning <- aggregate(date.start ~ case, dat,
                             function(x) ifelse(lubridate::hour(x[1]) > 13, 0, 1),
                             na.action = NULL)$date.start

datcase <- na.omit(datcase)

#--------------- (2) Clustering ---------------

df <- datcase[, c("duration", "distance", "scaleSize", "rotationDegree",
                  "length", "nitems", "npaths")] |>
       scale()
df <- cbind(df, datcase[, c("vacation", "holiday", "weekend", "morning")])       
mat <- dist(df)

hc <- hclust(mat, method = "ward.D2")
hc <- hclust(mat)

grp <- cutree(hc, k = 3)
datcase$grp <- grp

table(grp)

# k1 <- kmeans(mat, 4)
# datcase$kcluster <- k1$cluster

fviz_cluster(list(data = df, cluster = grp),
             palette = c("#78004B", "#000000", "#3CB4DC", "#91C86E",
                         "#FF6900", "#434F4F"),
             ellipse.type = "convex",
             show.clust.cent = FALSE, ggtheme = theme_bw())

aggregate(cbind(duration, distance, scaleSize , rotationDegree, length,
                nitems, npaths) ~ grp, datcase, mean)
aggregate(cbind(duration, distance, scaleSize , rotationDegree, length,
                nitems, npaths) ~ grp, datcase, median)
aggregate(cbind(duration, distance, scaleSize , rotationDegree, length,
                nitems, npaths) ~ grp, datcase, max)

res <- merge(dat, datcase[, c("case", "grp")], by = "case", all.x = TRUE)
res <- res[order(res$fileId.start, res$date.start, res$timeMs.start), ]

xtabs( ~ item + grp, res)

# Look at clusters
vioplot::vioplot(duration ~ grp, res)
vioplot::vioplot(distance ~ grp, res)
vioplot::vioplot(scaleSize ~ grp, res)
vioplot::vioplot(rotationDegree ~ grp, res)

write.table(res,
            file = "results/haum/event_logfiles_pre-corona_with-clusters_cases.csv",
            sep = ";",
            quote = FALSE,
            row.names = FALSE)

# Look at variants
res$start <- res$date.start
res$complete <- res$date.stop

alog <- activitylog(res,
                    case_id     = "case",
                    activity_id = "item",
                    resource_id = "path",
                    timestamps  = c("start", "complete"))

trace_explorer(alog, n_traces = 30)
# --> sequences of artworks are just too rare

tr <- traces(alog)
trace_length <- sapply(strsplit(tr$trace, ","), length)
tr[trace_length > 10, ]

trace_varied <- sapply(strsplit(tr$trace, ","), function(x) length(unique(x)))
tr[trace_varied > 1, ]
table(tr[trace_varied > 2, "absolute_frequency"])
table(tr[trace_varied > 3, "absolute_frequency"])

longest_case <- datcase[datcase$length == max(datcase$length), "case"]

alog_often <- activitylog(res[res$case == longest_case, ],
                          case_id     = "case",
                          activity_id = "item",
                          resource_id = "path",
                          timestamps  = c("start", "complete"))

process_map(alog_often)

# Power law for frequencies of traces
tab <- table(tr$absolute_frequency)
x <- as.numeric(tab)
y <- as.numeric(names(tab))
plot(log(y) ~ log(x))
abline(lm(log(y) ~ log(x)))

# Look at individual traces as examples
tr[trace_varied == 5 & trace_length > 50, ]
# --> every variant exists only once, of course
datcase[datcase$nitems == 5 & datcase$length > 50,]

sapply(datcase[, -c(1, 9)], median)

ex <- datcase[datcase$nitems == 10 & datcase$length == 30,]
# --> pretty randomly chosen... TODO:

for (case in ex$case) {

  alog <- activitylog(res[res$case == case, ],
                      case_id     = "case",
                      activity_id = "item",
                      resource_id = "path",
                      timestamps  = c("start", "complete"))
  
  dfg <- process_map(alog,
                     type_nodes = frequency("absolute", color_scale = "Greys"),
                     type_edges = frequency("absolute", color_edges = "#FF6900"),
                     rankdir    = "LR",
                     render     = FALSE)
  export_map(dfg,
             file_name = paste0("results/processmaps/dfg_example_cases_", case, "_R.pdf"),
             file_type = "pdf",
             title     = paste("Case", case))


}

## --> not interesting!
# Just "flipCard"
res_case <- res[!duplicated(res[, c("case", "path")]), ]

for (case in ex$case) {

  alog <- activitylog(res_case[res_case$case == case, ],
                      case_id     = "case",
                      activity_id = "item",
                      resource_id = "path",
                      timestamps  = c("start", "complete"))
  
  dfg <- process_map(alog,
                     type_nodes = frequency("absolute", color_scale = "Greys"),
                     type_edges = frequency("absolute", color_edges = "#FF6900"),
                     rankdir    = "LR",
                     render     = FALSE)
  export_map(dfg,
             file_name = paste0("results/processmaps/dfg_example_cases_", case, "_fc_R.pdf"),
             file_type = "pdf",
             title     = paste("Single case", case))


}