# 11_investigate-variants.R
#
# content: (1) Read data
#          (2) Investigate variants
#
# input:  results/haum/eventlogs_pre-corona_case-clusters.RData
# output: 
#
# last mod: 2024-03-12

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

library(bupaverse)

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

load("results/haum/eventlogs_pre-corona_cleaned.RData")

#--------------- (2) Investigate variants ---------------

dat$start <- dat$date.start
dat$complete <- dat$date.stop

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

pdf("results/figures/freq-traces.pdf", height = 7, width = 6, pointsize = 10)
trace_explorer(alog, n_traces = 25)
# --> sequences of artworks are just too rare
dev.off()

trace_explorer(alog, n_traces = 10, type = "infrequent")

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

trace_varied <- pbapply::pbsapply(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"])

summary(tr$absolute_frequency)
vioplot::vioplot(tr$absolute_frequency)

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

plot(x, y, log = "xy")
p1 <- lm(log(y) ~ log(x))
pre <- exp(coef(p1)[1]) * x^coef(p1)[2]
lines(x, pre)

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