nwickelmaier/mtt_haum
nwickelmaier/mtt_haum
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Mostly updated file paths

Browse Source
This commit is contained in:
Nora Wickelmaier 2024-03-22 12:33:58 +01:00
parent 24c7967246
commit cba441f08b
4 changed files with 33 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
code/09_user-navigation.R
View File

@ -4,18 +4,18 @@
# (2) Clustering # (2) Clustering
# (3) Fit tree # (3) Fit tree
# #
# input: results/haum/dataframes_case_2019.RData # input: results/dataframes_case_2019.RData
# output: results/haum/eventlogs_2019_case-clusters.csv # output: results/eventlogs_2019_case-clusters.csv
# results/haum/tmp_user-navigation.RData # results/user-navigation.RData
# ../../thesis/figures/data/clustering_cases.RData # ../../thesis/figures/data/clustering_cases.RData
# #
# last mod: 2024-03-15 # last mod: 2024-03-22
# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code") # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
#--------------- (1) Load data --------------- #--------------- (1) Load data ---------------
load("results/haum/dataframes_case_2019.RData") load("results/dataframes_case_2019.RData")
#--------------- (2) Clustering --------------- #--------------- (2) Clustering ---------------
@ -119,13 +119,13 @@ aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~ cluster, res, m
aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~ cluster, res, median) aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~ cluster, res, median)
write.table(res, write.table(res,
file = "results/haum/eventlogs_2019_case-clusters.csv", file = "results/eventlogs_2019_case-clusters.csv",
sep = ";", sep = ";",
quote = FALSE, quote = FALSE,
row.names = FALSE) row.names = FALSE)
save(res, dist_mat, hcs, acs, coor_2d, coor_3d, save(res, dist_mat, hcs, acs, coor_2d, coor_3d,
file = "results/haum/tmp_user-navigation.RData") file = "results/user-navigation.RData")
save(coor_2d, coor_3d, cluster, dattree, save(coor_2d, coor_3d, cluster, dattree,
file = "../../thesis/figures/data/clustering_cases.RData") file = "../../thesis/figures/data/clustering_cases.RData")

12
code/10_validation.R
View File

@ -6,10 +6,10 @@
# (4) Clustering # (4) Clustering
# (5) Fit tree # (5) Fit tree
# #
# input: results/haum/event_logfiles_2024-02-21_16-07-33.csv # input: results/event_logfiles_2024-02-21_16-07-33.csv
# output: results/haum/eventlogs_pre-corona_case-clusters.csv # output: --
# #
# last mod: 2024-03-15 # last mod: 2024-03-22
# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code") # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
@ -17,7 +17,7 @@ source("R_helpers.R")
#--------------- (1) Read data --------------- #--------------- (1) Read data ---------------
load("results/haum/eventlogs_pre-corona_cleaned.RData") load("results/eventlogs_pre-corona_cleaned.RData")
# Select one year to handle number of cases # Select one year to handle number of cases
dat <- dat[as.Date(dat$date.start) > "2017-12-31" & dat <- dat[as.Date(dat$date.start) > "2017-12-31" &
@ -77,8 +77,8 @@ dattree18 <- data.frame(case = datcase18$case,
) )
# centrality <- pbapply::pbsapply(dattree18$case, get_centrality, data = dat) # centrality <- pbapply::pbsapply(dattree18$case, get_centrality, data = dat)
# save(centrality, file = "results/haum/tmp_centrality_2018.RData") # save(centrality, file = "results/centrality_2018.RData")
load("results/haum/tmp_centrality_2018.RData") load("results/centrality_2018.RData")
dattree18$BetweenCentrality <- centrality dattree18$BetweenCentrality <- centrality

13
code/11_investigate-variants.R
View File

@ -3,10 +3,11 @@
# content: (1) Read data # content: (1) Read data
# (2) Investigate variants # (2) Investigate variants
# #
# input: results/haum/eventlogs_pre-corona_case-clusters.RData # input: results/eventlogs_pre-corona_cleaned.RData
# output: # output: ../../thesis/figures/freq-traces.pdf
# ../../thesis/figures/freq-traces_powerlaw.pdf
# #
# last mod: 2024-03-12 # last mod: 2024-03-22
# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code") # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
@ -14,7 +15,7 @@ library(bupaverse)
#--------------- (1) Read data --------------- #--------------- (1) Read data ---------------
load("results/haum/eventlogs_pre-corona_cleaned.RData") load("results/eventlogs_pre-corona_cleaned.RData")
#--------------- (2) Investigate variants --------------- #--------------- (2) Investigate variants ---------------
@ -27,7 +28,7 @@ alog <- activitylog(dat,
resource_id = "path", resource_id = "path",
timestamps = c("start", "complete")) timestamps = c("start", "complete"))
pdf("results/figures/freq-traces.pdf", height = 7, width = 6, pointsize = 10) pdf("../../thesis/figures/freq-traces.pdf", height = 7, width = 6, pointsize = 10)
trace_explorer(alog, n_traces = 25) trace_explorer(alog, n_traces = 25)
# --> sequences of artworks are just too rare # --> sequences of artworks are just too rare
dev.off() dev.off()
@ -54,7 +55,7 @@ y <- as.numeric(tab)
p1 <- lm(log(y) ~ log(x)) p1 <- lm(log(y) ~ log(x))
pre <- exp(coef(p1)[1]) * x^coef(p1)[2] pre <- exp(coef(p1)[1]) * x^coef(p1)[2]
pdf("results/figures/freq-traces_powerlaw.pdf", height = 3.375, pdf("../../thesis/figures/freq-traces_powerlaw.pdf", height = 3.375,
width = 3.375, pointsize = 10) width = 3.375, pointsize = 10)
par(mai = c(.6,.6,.1,.1), mgp = c(2.4, 1, 0)) par(mai = c(.6,.6,.1,.1), mgp = c(2.4, 1, 0))

29
code/12_dfgs-case-clusters.R
View File

@ -1,25 +1,28 @@
# 13_dfgs-case-clusters.R # 13_dfgs-case-clusters.R
# #
# content: # content: (1) Read data
# (2) Export DFGs for clusters
# #
# input: results/haum/tmp_user-navigation.RData # input: results/user-navigation.RData
# output: # output: ../../thesis/figures/dfg_cases_cluster1_R.pdf
# ../../thesis/figures/dfg_cases_cluster2_R.pdf
# ../../thesis/figures/dfg_cases_cluster3_R.pdf
# ../../thesis/figures/dfg_cases_cluster4_R.pdf
# ../../thesis/figures/dfg_cases_cluster5_R.pdf
# #
# last mod: 2024-03-19 # last mod: 2024-03-22
# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code") # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
load("results/haum/tmp_user-navigation.RData") #--------------- (1) Read data ---------------
#dat <- read.table("results/haum/eventlogs_2019_case-clusters.csv", header = TRUE, sep = ";") load("results/user-navigation.RData")
dat <- res dat <- res
dat$start <- as.POSIXct(dat$date.start) dat$start <- as.POSIXct(dat$date.start)
dat$complete <- as.POSIXct(dat$date.stop) dat$complete <- as.POSIXct(dat$date.stop)
alog <- bupaR::activitylog(dat[dat$cluster == cluster, ], alog <- bupaR::activitylog(dat[dat$cluster == cluster, ],
case_id = "case", case_id = "case",
activity_id = "item", activity_id = "item",
@ -33,13 +36,9 @@ tab <- table(tr$absolute_frequency)
tab[1] / nrow(tr) tab[1] / nrow(tr)
alog |> edeaR::filter_infrequent_flows(min_n = 20) |> processmapR::process_map() alog |> edeaR::filter_infrequent_flows(min_n = 20) |> processmapR::process_map()
#--------------- (2) Export DFGs for clusters ---------------
## Export DFGs for clusters
mycols <- c("#3CB4DC", "#FF6900", "#78004B", "#91C86E", "#434F4F") mycols <- c("#3CB4DC", "#FF6900", "#78004B", "#91C86E", "#434F4F")
cl_names <- c("Scanning", "Exploring", "Flitting", "Searching", "Info") cl_names <- c("Scanning", "Exploring", "Flitting", "Searching", "Info")
@ -63,12 +62,11 @@ for (i in 1:5) {
render = FALSE) render = FALSE)
processmapR::export_map(dfg, processmapR::export_map(dfg,
file_name = paste0("results/processmaps/dfg_cases_cluster", i, "_R.pdf"), file_name = paste0("../../thesis/figures/dfg_cases_cluster", i, "_R.pdf"),
file_type = "pdf", file_type = "pdf",
title = cl_names[i]) title = cl_names[i])
} }
# cluster 1: 50 # cluster 1: 50
# cluster 2: 30 o. 20 # cluster 2: 30 o. 20
# cluster 3: 20 - 30 # cluster 3: 20 - 30
@ -87,7 +85,6 @@ get_percent_variants <- function(log, cluster, min_n) {
nrow(alog) nrow(alog)
} }
perc <- numeric(5) perc <- numeric(5)
for (i in 1:5) { for (i in 1:5) {