mtt_haum/code/07_item-clustering.R

169 lines
5.8 KiB
R

# 07_item-clustering.R
#
# content: (1) Read data
# (1.1) Read log event data
# (1.2) Read infos for PM for infos
# (1.3) Extract additional infos for clustering
# (2) Clustering
# (3) Visualization with pictures
#
# input: results/eventlogs_pre-corona_cleaned.RData
# results/pn_infos_items.csv
# output: results/eventlogs_pre-corona_item-clusters.csv
# ../thesis/results/clustering_items.RData"
#
# last mod: 2024-03-22
# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/")
source("code/R_helpers.R")
#--------------- (1) Read data ---------------
#--------------- (1.1) Read log event data ---------------
load("results/eventlogs_pre-corona_cleaned.RData")
#--------------- (1.2) Read infos for PM for items ---------------
datitem <- read.table("results/pn_infos_items.csv", header = TRUE,
sep = ";", row.names = 1)
#--------------- (1.3) Extract additional infos for clustering ---------------
# Get average duration per path
dat_split <- split(dat, ~ path)
dat_list <- pbapply::pblapply(dat_split, time_minmax_ms)
dat_minmax <- dplyr::bind_rows(dat_list)
datpath <- aggregate(duration ~ item + path, dat, mean, na.action = NULL)
datpath$min_time <- aggregate(min_time ~ path, dat_minmax, unique, na.action = NULL)$min_time
datpath$max_time <- aggregate(max_time ~ path, dat_minmax, unique, na.action = NULL)$max_time
datpath$duration <- datpath$max_time - datpath$min_time
datitem$duration <- aggregate(duration ~ item, datpath, mean)$duration
datitem$distance <- aggregate(distance ~ item, dat, mean)$distance
datitem$scaleSize <- aggregate(scaleSize ~ item, dat, mean)$scaleSize
datitem$rotationDegree <- aggregate(rotationDegree ~ item, dat, mean)$rotationDegree
datitem$npaths <- aggregate(path ~ item, dat, function(x) length(unique(x)))$path
datitem$ncases <- aggregate(case ~ item, dat, function(x) length(unique(x)))$case
datitem$nmove <- aggregate(event ~ item, dat, table)$event[,"move"]
datitem$nflipCard <- aggregate(event ~ item, dat, table)$event[,"flipCard"]
datitem$nopenTopic <- aggregate(event ~ item, dat, table)$event[,"openTopic"]
datitem$nopenPopup <- aggregate(event ~ item, dat, table)$event[,"openPopup"]
rm(datpath)
#--------------- (2) Clustering ---------------
df <- datitem[, c("precision", "generalizability", "nvariants", "duration",
"distance", "scaleSize", "rotationDegree", "npaths",
"ncases", "nmove", "nflipCard", "nopenTopic",
"nopenPopup")] |>
scale()
dist_mat <- dist(df)
heatmap(as.matrix(dist_mat))
# Choosing best linkage method
method <- c(average = "average", single = "single", complete = "complete",
ward = "ward")
hcs <- lapply(method, function(x) cluster::agnes(dist_mat, method = x))
acs <- sapply(hcs, function(x) x$ac)
# Dendograms
par(mfrow=c(4,2))
for (hc in hcs) plot(hc, main = "")
hc <- hcs$ward
factoextra::fviz_nbclust(df, FUNcluster = factoextra::hcut, method = "wss")
factoextra::fviz_nbclust(df, FUNcluster = factoextra::hcut, method = "silhouette")
gap_stat <- cluster::clusGap(df, FUNcluster = factoextra::hcut,
hc_func = "agnes", hc_method = "ward",
K.max = 15)
factoextra::fviz_gap_stat(gap_stat)
k <- 6 # number of clusters
mycols <- c("#434F4F", "#78004B", "#FF6900", "#3CB4DC", "#91C86E", "Black")
cluster <- cutree(hc, k = k)
factoextra::fviz_dend(hc, k = k,
cex = 0.5,
k_colors = mycols,
#type = "phylogenic",
rect = TRUE,
main = "",
ylab = ""
#ggtheme = ggplot2::theme_bw()
)
factoextra::fviz_cluster(list(data = df, cluster = cluster),
palette = mycols,
ellipse.type = "convex",
repel = TRUE,
show.clust.cent = FALSE,
main = "",
ggtheme = ggplot2::theme_bw())
aggregate(cbind(precision, generalizability, nvariants, duration, distance,
scaleSize , rotationDegree, npaths, ncases, nmove,
nflipCard, nopenTopic, nopenPopup) ~ cluster, datitem,
mean)
aggregate(cbind(duration, distance, scaleSize , rotationDegree, npaths,
ncases, nmove, nflipCard, nopenTopic, nopenPopup) ~ cluster,
datitem, max)
item <- sprintf("%03d", as.numeric(gsub("item_([0-9]{3})", "\\1",
row.names(datitem))))
res <- merge(dat, data.frame(item, cluster), by = "item", all.x = TRUE)
res <- res[order(res$fileId.start, res$date.start, res$timeMs.start), ]
# DFGs for clusters
res$start <- res$date.start
res$complete <- res$date.stop
for (clst in sort(unique(res$cluster))) {
alog <- bupaR::activitylog(res[res$cluster == clst, ],
case_id = "path",
activity_id = "event",
resource_id = "item",
timestamps = c("start", "complete"))
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")
}
# Look at clusters
par(mfrow = c(2,2))
vioplot::vioplot(duration ~ cluster, res)
vioplot::vioplot(distance ~ cluster, res)
vioplot::vioplot(scaleSize ~ cluster, res)
vioplot::vioplot(rotationDegree ~ cluster, res)
write.table(res,
file = "results/eventlogs_pre-corona_item-clusters.csv",
sep = ";",
quote = FALSE,
row.names = FALSE)
# Save data for plots and tables
save(hc, k, res, dist_mat, datitem, df,
file = "../thesis/results/clustering_items.RData")