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

Worked some more on clustering of cases; removed DBSCAN and only selects cases from 2019 now

Browse Source
This commit is contained in:
Nora Wickelmaier 2024-03-06 18:38:56 +01:00
parent 6cfc19a874
commit 4eca6c81d6
1 changed files with 95 additions and 198 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

293
code/09_user-navigation.R
View File

@ -1,17 +1,16 @@
# 09_user_navigation.R # 09_user-navigation.R
# #
# content: (1) Read data # content: (1) Read data
# (1.1) Read log event data # (1.1) Read log event data
# (1.2) Extract additional infos for clustering # (1.2) Extract additional infos for clustering
# (2) Clustering # (2) Clustering
# (3) Fit tree # (3) Fit tree
# (3) Investigate variants # (4) Investigate variants
# #
# input: results/haum/event_logfiles_2024-02-21_16-07-33.csv # input: results/haum/event_logfiles_2024-02-21_16-07-33.csv
# output: results/haum/event_logfiles_pre-corona_with-clusters_cases.csv # output: results/haum/eventlogs_pre-corona_case-clusters.csv
# results/haum/dattree.csv
# #
# last mod: 2024-02-27 # last mod: 2024-03-06
# 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")
@ -23,33 +22,11 @@ library(factoextra)
#--------------- (1.1) Read log event data --------------- #--------------- (1.1) Read log event data ---------------
dat0 <- read.table("results/haum/event_logfiles_2024-02-21_16-07-33.csv", load("results/haum/eventlogs_pre-corona_cleaned.RData")
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", # Select one year to handle number of cases
"openPopup")) dat <- dat[as.Date(dat$date.start) > "2018-12-31" &
dat0$topic <- factor(dat0$topic) as.Date(dat$date.start) < "2020-01-01", ]
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, ]
rm(dat0)
#--------------- (1.2) Extract additional infos for clustering --------------- #--------------- (1.2) Extract additional infos for clustering ---------------
@ -107,7 +84,7 @@ datcase$morning <- aggregate(date.start ~ case, dat,
dat_split <- split(dat, ~ case) dat_split <- split(dat, ~ case)
time_minmax <- function(subdata) { time_minmax_ms <- function(subdata) {
subdata$min_time <- min(subdata$timeMs.start) subdata$min_time <- min(subdata$timeMs.start)
if (all(is.na(subdata$timeMs.stop))) { if (all(is.na(subdata$timeMs.stop))) {
subdata$max_time <- NA subdata$max_time <- NA
@ -116,9 +93,9 @@ time_minmax <- function(subdata) {
} }
subdata subdata
} }
# TODO: Export from package mtt # TODO: Move to helper file
dat_list <- pbapply::pblapply(dat_split, time_minmax) dat_list <- pbapply::pblapply(dat_split, time_minmax_ms)
dat_minmax <- dplyr::bind_rows(dat_list) dat_minmax <- dplyr::bind_rows(dat_list)
datcase$min_time <- aggregate(min_time ~ case, dat_minmax, unique)$min_time datcase$min_time <- aggregate(min_time ~ case, dat_minmax, unique)$min_time
@ -160,8 +137,6 @@ datcase$thema <- ifelse(is.na(datcase$thema), 0, datcase$thema)
datcase$ntopics <- ifelse(is.na(datcase$ntopics), 0, datcase$ntopics) datcase$ntopics <- ifelse(is.na(datcase$ntopics), 0, datcase$ntopics)
datcase$ntopiccards <- ifelse(is.na(datcase$ntopiccards), 0, datcase$ntopiccards) datcase$ntopiccards <- ifelse(is.na(datcase$ntopiccards), 0, datcase$ntopiccards)
cor_mat <- cor(datcase[, -1], use = "pairwise") cor_mat <- cor(datcase[, -1], use = "pairwise")
diag(cor_mat) <- NA diag(cor_mat) <- NA
heatmap(cor_mat) heatmap(cor_mat)
@ -216,26 +191,24 @@ get_centrality <- function(case, data) {
net <- process_map(alog, render = FALSE) net <- process_map(alog, render = FALSE)
inet <- DiagrammeR::to_igraph(net) inet <- DiagrammeR::to_igraph(net)
c(igraph::centr_degree(inet, loops = FALSE)$centralization, #c(igraph::centr_degree(inet, loops = FALSE)$centralization,
igraph::centr_degree(inet, loops = TRUE)$centralization, # igraph::centr_degree(inet, loops = TRUE)$centralization,
igraph::centr_betw(inet)$centralization) # igraph::centr_betw(inet)$centralization)
igraph::centr_betw(inet)$centralization
} }
# TODO: Move to helper file # TODO: Move to helper file
# centrality <- lapply(dattree$case, get_centrality, data = dat) centrality <- pbapply::pblapply(dattree$case, get_centrality, data = dat)
# centrality <- do.call(rbind, centrality) centrality <- do.call(rbind, centrality)
#
# save(centrality, file = "results/haum/tmp_centrality.RData") # save(centrality, file = "results/haum/tmp_centrality.RData")
load("results/haum/tmp_centrality.RData") #load("results/haum/tmp_centrality.RData")
#dattree$DegreeCentrality <- centrality[, 2] dattree$BetweenCentrality <- unlist(centrality)
dattree$BetweenCentrality <- centrality[, 3]
## Add average duration per item
# Average duration per item
dat_split <- split(dat[, c("item", "case", "path", "timeMs.start", "timeMs.stop")], ~ path) dat_split <- split(dat[, c("item", "case", "path", "timeMs.start", "timeMs.stop")], ~ path)
dat_list <- pbapply::pblapply(dat_split, time_minmax_ms)
dat_list <- pbapply::pblapply(dat_split, time_minmax)
dat_minmax <- dplyr::bind_rows(dat_list) dat_minmax <- dplyr::bind_rows(dat_list)
tmp <- aggregate(min_time ~ path, dat_minmax, unique) tmp <- aggregate(min_time ~ path, dat_minmax, unique)
@ -244,10 +217,23 @@ tmp$duration <- tmp$max_time - tmp$min_time
tmp$case <- aggregate(case ~ path, dat_minmax, unique)$case tmp$case <- aggregate(case ~ path, dat_minmax, unique)$case
dattree$AvDurItem <- aggregate(duration ~ case, tmp, mean)$duration dattree$AvDurItem <- aggregate(duration ~ case, tmp, mean)$duration
#dattree$AvDurItem <- dattree$AvDurItem / datcase$duration
rm(tmp) rm(tmp)
# Indicator variable if table was used as info terminal only
dattree$InfocardOnly <- factor(datcase$infocardOnly, levels = 0:1,
labels = c("no", "yes"))
# Add pattern to datcase; loosely based on Bousbia et al. (2009)
dattree$Pattern <- "Dispersion"
dattree$Pattern <- ifelse(dattree$PathLinearity > 0.8 & dattree$Singularity > 0.8, "Scholar",
dattree$Pattern)
dattree$Pattern <- ifelse(dattree$PathLinearity <= 0.8 &
dattree$BetweenCentrality > 0.5, "Star",
dattree$Pattern)
dattree$Pattern <- factor(dattree$Pattern)
summary(dattree) summary(dattree)
plot(dattree[, -1], pch = ".") plot(dattree[, -1], pch = ".")
@ -262,19 +248,6 @@ hist(dattree$PathLinearity, breaks = 50, main = "")
hist(dattree$Singularity, breaks = 50, main = "") hist(dattree$Singularity, breaks = 50, main = "")
hist(dattree$BetweenCentrality, breaks = 50, main = "") hist(dattree$BetweenCentrality, breaks = 50, main = "")
# Indicator variable if table was used as info terminal only
dattree$InfocardOnly <- factor(datcase$infocardOnly, levels = 0:1, labels = c("no", "yes"))
# Add pattern to datcase; loosely based on Bousbia et al. (2009)
dattree$Pattern <- "Dispersion"
dattree$Pattern <- ifelse(dattree$PathLinearity > 0.8 & dattree$Singularity > 0.8, "Scholar",
dattree$Pattern)
dattree$Pattern <- ifelse(dattree$PathLinearity <= 0.8 &
dattree$BetweenCentrality > 0.5, "Star",
dattree$Pattern)
dattree$Pattern <- factor(dattree$Pattern)
# Remove cases with extreme outliers # Remove cases with extreme outliers
# TODO: Do I want this??? # TODO: Do I want this???
@ -298,9 +271,9 @@ hist(dattree$BetweenCentrality, breaks = 50, main = "")
#--------------- (2) Clustering --------------- #--------------- (2) Clustering ---------------
library(cluster) #library(cluster)
df <- dattree[1:10000, -1] # remove case variable #df <- dattree[, -1] # remove case variable
# TODO: Do I need to scale or does normalization also work? # TODO: Do I need to scale or does normalization also work?
# Normalize Duration and Numbers # Normalize Duration and Numbers
@ -312,42 +285,51 @@ df <- dattree[1:10000, -1] # remove case variable
# summary(df) # summary(df)
# Look at collinearity # Look at collinearity
cor_mat <- cor(df) # cor_mat <- cor(df)
diag(cor_mat) <- NA # diag(cor_mat) <- NA
heatmap(cor_mat) # heatmap(cor_mat)
#df <- as.data.frame(scale(dattree[, -1])) #df <- as.data.frame(scale(dattree[, -1]))
#--------------- (2.2) Hierarchical clustering --------------- #--------------- (2.2) Hierarchical clustering ---------------
mat <- daisy(df, metric = "gower") dist_mat <- cluster::daisy(dattree[, -1], metric = "gower")
# # "Flatten" with PCA
# mm <- model.matrix( ~ ., df)[, -1] # remove intercept
# tmp <- as.data.frame(lapply(as.data.frame(mm), normalize))
# pc <- prcomp(mm)
# coor_2d <- as.data.frame(pc$x[, 1:2])
# coor_3d <- as.data.frame(pc$x[, 1:3])
# "Flatten" with MDS # "Flatten" with MDS
coor_2d <- as.data.frame(cmdscale(mat, k = 2)) coor_2d <- as.data.frame(cmdscale(dist_mat, k = 2))
coor_3d <- as.data.frame(cmdscale(mat, k = 3)) coor_3d <- as.data.frame(cmdscale(dist_mat, k = 3))
# Idea from
# https://stats.stackexchange.com/questions/264912/mds-on-large-dataset-r-or-python
# https://www.inf.uni-konstanz.de/exalgo/software/mdsj/
write.table(as.matrix(dist_mat), file = "mds/dist_mat.txt", row.names = FALSE,
col.names = FALSE)
# Run java script
system("java -jar mdsj.jar -d2 mds/dist_mat.txt mds/mds_coor_2d.txt")
system("java -jar mdsj.jar -d3 mds/dist_mat.txt mds/mds_coor_3d.txt")
coor_2d_java <- read.table("mds/mds_coor_2d.txt", header = FALSE, sep = " ")
plot(coor_2d_java)
plot(coor_2d) plot(coor_2d)
rgl::plot3d(coor_3d) rgl::plot3d(coor_3d)
#mat <- dist(df)
# https://uc-r.github.io/hc_clustering
method <- c(average = "average", single = "single", complete = "complete", method <- c(average = "average", single = "single", complete = "complete",
ward = "ward.D2") ward = "ward")
hc_method <- function(x) { hcs <- pbapply::pblapply(method, function(x) cluster::agnes(dist_mat, method = x))
hclust(mat, method = x) acs <- pbapply::sapply(hcs, function(x) x$ac)
}
hcs <- lapply(method, hc_method) hc <- hcs$ward
cds <- lapply(hcs, cophenetic)
cors <- sapply(cds, cor, y = mat)
# https://en.wikipedia.org/wiki/Cophenetic_correlation
# https://stats.stackexchange.com/questions/195446/choosing-the-right-linkage-method-for-hierarchical-clustering
hc <- hcs$average
# Something like a scree plot (??) # Something like a scree plot (??)
plot(rev(hc$height)[1:100], type = "b", pch = 16, cex = .5) plot(rev(hc$height)[1:100], type = "b", pch = 16, cex = .5)
@ -356,72 +338,31 @@ k <- 4
mycols <- c("#78004B", "#FF6900", "#3CB4DC", "#91C86E") mycols <- c("#78004B", "#FF6900", "#3CB4DC", "#91C86E")
grp_hclust <- cutree(hc, k = k) cluster <- cutree(as.hclust(hc), k = k)
table(grp_hclust) table(cluster)
fviz_cluster(list(data = df, cluster = grp_hclust), plot(coor_2d, col = mycols[cluster])
palette = mycols,
ellipse.type = "convex",
show.clust.cent = FALSE,
ggtheme = theme_bw())
plot(coor_2d, col = mycols[grp_hclust])
legend("topleft", paste("Cl", 1:4), col = mycols, pch = 21) legend("topleft", paste("Cl", 1:4), col = mycols, pch = 21)
rgl::plot3d(coor_3d, col = mycols[grp_hclust]) rgl::plot3d(coor_3d, col = mycols[cluster])
table(datcase[grp_hclust == 1, "Pattern"]) table(dattree[cluster == 1, "Pattern"])
table(datcase[grp_hclust == 2, "Pattern"]) table(dattree[cluster == 2, "Pattern"])
table(datcase[grp_hclust == 3, "Pattern"]) table(dattree[cluster == 3, "Pattern"])
table(datcase[grp_hclust == 4, "Pattern"]) table(dattree[cluster == 4, "Pattern"])
aggregate(. ~ grp_hclust, df, mean) aggregate(. ~ cluster, df, mean)
aggregate(cbind(duration, distance, scaleSize, rotationDegree, length, aggregate(cbind(duration, distance, scaleSize, rotationDegree, length,
nmove, nflipCard, nopenTopic, nopenPopup) ~ grp_hclust, datcase, nmove, nflipCard, nopenTopic, nopenPopup) ~ cluster, datcase,
mean) mean)
#--------------- (2.3) DBSCAN clustering ---------------
library(dbscan)
d1 <- dbscan(df, eps = 1, minPts = ncol(df) + 1)
hullplot(df, d1)
grp_db <- d1$cluster
table(grp_db)
kNNdistplot(df, k = ncol(df))
abline(h = 0.2, col = "red")
abline(h = 1, col = "red")
fviz_cluster(list(data = df[grp_db != 0, ], cluster = grp_db[grp_db != 0]),
palette = mycols,
ellipse.type = "convex",
show.clust.cent = FALSE,
ggtheme = theme_bw())
mycols <- c("black", mycols)
plot(coor_2d, col = mycols[grp_db + 1])
legend("topleft", paste("Cl", 0:4), col = mycols, pch = 21)
rgl::plot3d(coor_3d, col = mycols[grp_db + 1])
aggregate(. ~ grp_db, df, mean)
table(datcase[grp_db == 0, "Pattern"])
table(datcase[grp_db == 1, "Pattern"])
table(datcase[grp_db == 2, "Pattern"])
table(datcase[grp_db == 3, "Pattern"])
table(datcase[grp_db == 4, "Pattern"])
### Look at selected cases ########################################### ### Look at selected cases ###########################################
dattree[grp_db == 0, ]
tmp <- dat tmp <- dat
tmp$start <- tmp$date.start tmp$start <- tmp$date.start
tmp$complete <- tmp$date.stop tmp$complete <- tmp$date.stop
alog <- activitylog(tmp[tmp$case == 15, ], alog <- activitylog(tmp[tmp$case == 24016, ],
case_id = "case", case_id = "case",
activity_id = "item", activity_id = "item",
resource_id = "path", resource_id = "path",
@ -433,30 +374,30 @@ rm(tmp)
###################################################################### ######################################################################
res <- merge(dat, data.frame(case = dattree$case, grp_km, grp_hclust, grp_db), res <- merge(dat, data.frame(case = dattree$case, cluster),
by = "case", all.x = TRUE) by = "case", all.x = TRUE)
res <- res[order(res$fileId.start, res$date.start, res$timeMs.start), ] res <- res[order(res$fileId.start, res$date.start, res$timeMs.start), ]
xtabs( ~ item + grp_db, res) xtabs( ~ item + cluster, res)
aggregate(event ~ grp_db, res, table) aggregate(event ~ cluster, res, table)
# Look at clusters # Look at clusters
par(mfrow = c(2, 2)) par(mfrow = c(2, 2))
vioplot::vioplot(duration ~ grp_db, res) vioplot::vioplot(duration ~ cluster, res)
vioplot::vioplot(distance ~ grp_db, res) vioplot::vioplot(distance ~ cluster, res)
vioplot::vioplot(scaleSize ~ grp_db, res) vioplot::vioplot(scaleSize ~ cluster, res)
vioplot::vioplot(rotationDegree ~ grp_db, res) vioplot::vioplot(rotationDegree ~ cluster, res)
aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~ grp_db, res, mean) aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~ cluster, res, mean)
aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~ grp_db, res, median) aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~ cluster, res, median)
write.table(res, write.table(res,
file = "results/haum/event_logfiles_pre-corona_with-clusters_cases.csv", file = "results/haum/eventlogs_2019_case-clusters.csv",
sep = ";", sep = ";",
quote = FALSE, quote = FALSE,
row.names = FALSE) row.names = FALSE)
save(res, mat, h1, h2, h3, h4, h5, c1, c2, c3, c4, c5, datcase, dattree, df, save(res, dist_mat, hcs, acs, datcase, dattree,
file = "results/haum/tmp_user-navigation.RData") file = "results/haum/tmp_user-navigation.RData")
#--------------- (3) Fit tree --------------- #--------------- (3) Fit tree ---------------
@ -464,28 +405,13 @@ save(res, mat, h1, h2, h3, h4, h5, c1, c2, c3, c4, c5, datcase, dattree, df,
library(rpart) library(rpart)
library(partykit) library(partykit)
dattree_db <- dattree[grp_db != 0, -1] c1 <- rpart(as.factor(cluster) ~ ., data = dattree[, -1], method = "class")
dattree_db$grp <- factor(grp_db[grp_db != 0])
c1 <- rpart(grp ~ ., data = dattree_db, method = "class")
plot(as.party(c1)) plot(as.party(c1))
c2 <- rpart(as.factor(grp_hclust) ~ ., data = dattree[, -1], method = "class")
plot(as.party(c2))
# with conditional tree # with conditional tree
c2 <- ctree(grp ~ ., data = dattree_db, alpha = 0.05) c2 <- ctree(as.factor(cluster) ~ ., data = dattree[, -1], alpha = 0)
plot(c2) plot(c2)
# with excluded points
c5 <- ctree(factor(grp_db) ~ ., data = dattree[, -1], alpha = 0)
plot(c5)
# with excluded points
c6 <- ctree(factor(grp_db) ~ ., data = df, alpha = 0)
plot(c6)
# --> just checking
#--------------- (4) Investigate variants --------------- #--------------- (4) Investigate variants ---------------
res$start <- res$date.start res$start <- res$date.start
@ -501,10 +427,10 @@ trace_explorer(alog, n_traces = 25)
# --> sequences of artworks are just too rare # --> sequences of artworks are just too rare
tr <- traces(alog) tr <- traces(alog)
trace_length <- sapply(strsplit(tr$trace, ","), length) trace_length <- pbapply::pbsapply(strsplit(tr$trace, ","), length)
tr[trace_length > 10, ] tr[trace_length > 10, ]
trace_varied <- sapply(strsplit(tr$trace, ","), function(x) length(unique(x))) trace_varied <- pbapply::pbsapply(strsplit(tr$trace, ","), function(x) length(unique(x)))
tr[trace_varied > 1, ] tr[trace_varied > 1, ]
table(tr[trace_varied > 2, "absolute_frequency"]) table(tr[trace_varied > 2, "absolute_frequency"])
table(tr[trace_varied > 3, "absolute_frequency"]) table(tr[trace_varied > 3, "absolute_frequency"])
@ -528,7 +454,7 @@ tr[trace_varied == 5 & trace_length > 50, ]
# --> every variant exists only once, of course # --> every variant exists only once, of course
datcase[datcase$nitems == 5 & datcase$length > 50,] datcase[datcase$nitems == 5 & datcase$length > 50,]
sapply(datcase[, -c(1, 9)], median) pbapply::pbsapply(datcase[, -c(1, 9)], median)
#ex <- datcase[datcase$nitems == 4 & datcase$length == 15,] #ex <- datcase[datcase$nitems == 4 & datcase$length == 15,]
ex <- datcase[datcase$nitems == 5,] ex <- datcase[datcase$nitems == 5,]
@ -569,32 +495,3 @@ for (case in cases) {
} }
########################### TODO: Still need it?
net <- process_map(alog, render = FALSE)
#DiagrammeR::get_node_df(net)
DiagrammeR::get_node_info(net)
DiagrammeR::get_degree_distribution(net)
DiagrammeR::get_degree_in(net)
DiagrammeR::get_degree_out(net)
DiagrammeR::get_degree_total(net)
N <- DiagrammeR::count_nodes(net) - 2 # Do not count start and stop nodes
dc <- DiagrammeR::get_degree_total(net)[1:N, "total_degree"] / (N - 1)
inet <- DiagrammeR::to_igraph(net)
igraph::centr_degree(inet, loops = FALSE)
igraph::centr_betw(inet)
igraph::centr_clo(inet)