102 lines
2.9 KiB
R
102 lines
2.9 KiB
R
# 11_investigate-variants.R
|
|
#
|
|
# content: (1) Read data
|
|
# (2) Extract characteristics for cases
|
|
# (3) Select features for navigation behavior
|
|
# (4) Export data frames
|
|
#
|
|
# input: results/haum/event_logfiles_2024-02-21_16-07-33.csv
|
|
# output: results/haum/eventlogs_pre-corona_case-clusters.csv
|
|
#
|
|
# last mod: 2024-03-08
|
|
|
|
# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
|
|
|
|
#--------------- (1) Read data ---------------
|
|
|
|
load("results/haum/eventlogs_pre-corona_cleaned.RData")
|
|
|
|
#--------------- (4) Investigate 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 = 25)
|
|
# --> sequences of artworks are just too rare
|
|
|
|
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$absolute_frequency)
|
|
x <- as.numeric(tab)
|
|
y <- as.numeric(names(tab))
|
|
|
|
plot(x, y, log = "xy")
|
|
p1 <- lm(log(y) ~ log(x))
|
|
pre <- exp(coef(p1)[1]) * x^coef(p1)[2]
|
|
lines(x, pre)
|
|
|
|
|
|
# Look at individual traces as examples
|
|
tr[trace_varied == 5 & trace_length > 50, ]
|
|
# --> every variant exists only once, of course
|
|
datcase[datcase$nitems == 5 & datcase$length > 50,]
|
|
|
|
pbapply::pbsapply(datcase[, -c(1, 9)], median)
|
|
|
|
#ex <- datcase[datcase$nitems == 4 & datcase$length == 15,]
|
|
ex <- datcase[datcase$nitems == 5,]
|
|
ex <- ex[sample(1:nrow(ex), 20), ]
|
|
# --> pretty randomly chosen... TODO:
|
|
|
|
case_ids <- NULL
|
|
|
|
for (case in ex$case) {
|
|
if ("080" %in% res$item[res$case == case] | "503" %in% res$item[res$case == case]) {
|
|
case_ids <- c(case_ids, TRUE)
|
|
} else {
|
|
case_ids <- c(case_ids, FALSE)
|
|
}
|
|
}
|
|
|
|
cases <- ex$case[case_ids]
|
|
|
|
|
|
for (case in cases) {
|
|
|
|
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))
|
|
|
|
|
|
}
|
|
|