Mostly updated file paths

code/01_preprocessing.R

@@ -8,8 +8,8 @@
 #         ../data/metadata/feiertage.csv
 #         ../data/metadata/schulferien_2016-2018_NI.csv
 #         ../data/metadata/schulferien_2019-2025_NI.csv
-# output: raw_logfiles_<timestamp>.csv
+# output: results/raw_logfiles_<timestamp>.csv
-#         event_logfiles_<timestamp>.csv
+#         results/event_logfiles_<timestamp>.csv
 #
 # last mod: 2024-02-23, NW
 
@@ -29,12 +29,12 @@ folders <- dir(path)
 datraw <- parse_logfiles(folders, path)
 # 91 corrupt lines have been found and removed from the data set
 
-# datraw <- read.table("results/haum/raw_logfiles_2023-10-25_16-20-45.csv",
+# datraw <- read.table("results/raw_logfiles_2023-10-25_16-20-45.csv",
 #                      sep = ";", header = TRUE)
 
 ## Export data
 
-write.table(datraw, paste0("results/haum/raw_logfiles_", now, ".csv"),
+write.table(datraw, paste0("results/raw_logfiles_", now, ".csv"),
             sep = ";", row.names = FALSE)
 
 #--------------- (2) Create event logs ---------------
@@ -131,6 +131,6 @@ dat2 <- dat2[order(dat2$fileId.start, dat2$date.start, dat2$timeMs.start), ]
 
 ## Export data
 
-write.table(dat2, paste0("results/haum/event_logfiles_", now, ".csv"),
+write.table(dat2, paste0("results/event_logfiles_", now, ".csv"),
             sep = ";", row.names = FALSE)
 

code/02_descriptives.R

@@ -9,16 +9,30 @@
 #           (3.4) Artwork sequences
 #           (3.5) Topics
 #
-# 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/raw_logfiles_2024-02-21_16-07-33.csv
+# output: results/figures/counts_item.pdf
+#         results/figures/counts_item_firsttouch.pdf
+#         results/figures/duration.pdf
+#         results/figures/heatmap_start.pdf
+#         results/figures/heatmap_stop.pdf
+#         results/figures/cases_per_day.pdf
+#         results/figures/timeMs.pdf
+#         results/figures/xycoord.pdf
+#         results/figures/event-dist.pdf
+#         results/figures/traceexplore_trace-event.pdf
+#         results/figures/ra_trace-event.pdf
+#         results/figures/traceexplore_case-event.pdf
+#         results/figures/bp_tod.pdf
+#         results/figures/bp_wd.pdf
+#         results/figures/bp_wds.pdf
+#         results/figures/bp_corona.pdf
+#         results/figures/traceexplore_case-artwork_often080.pdf
 #
-# last mod: 2024-03-13
+# last mod: 2024-03-22
 
 # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
 
-library(lattice)
-library(bupaverse)
-
 # Overall Research Question: How do museum visitors interact with the
 # artworks presented on the MTT?
 
@@ -27,7 +41,7 @@ library(bupaverse)
 
 #--------------- (1) Read data ---------------
 
-datlogs <- read.table("results/haum/event_logfiles_2024-02-21_16-07-33.csv",
+datlogs <- read.table("results/event_logfiles_2024-02-21_16-07-33.csv",
                       colClasses = c("character", "character", "POSIXct",
                                      "POSIXct", "character", "integer",
                                      "numeric", "character", "character",
@@ -40,7 +54,7 @@ datlogs$event <- factor(datlogs$event, levels = c("move", "flipCard",
                                                   "openTopic",
                                                   "openPopup"))
 
-datraw <- read.table("results/haum/raw_logfiles_2024-02-21_16-07-33.csv",
+datraw <- read.table("results/raw_logfiles_2024-02-21_16-07-33.csv",
                      sep = ";", header = TRUE)
 
 # Add weekdays to data frame
@@ -74,43 +88,263 @@ lattice::dotplot(xtabs( ~ item + topic, datlogs), auto.key = TRUE)
 mat <- t(as.matrix(xtabs( ~ item + topic, datlogs)))
 mat[mat == 0] <- NA
 image(mat, axes = F, col = rainbow(100))
-heatmap(t(mat))
-
-
-datlogs$start <- datlogs$date.start
-datlogs$complete <- datlogs$date.stop
-
-
 
 #--------------- (2) Descriptives ---------------
+
+### Which item gets touched most often?
+
+counts_item <- table(datlogs$item)
+lattice::barchart(counts_item)
+
+items <- unique(datlogs$item)
+#items <- items[!items %in% c("504", "505")]
+datart <- mtt::extract_artworks(items,
+                           paste0(items, ".xml"),
+                           "../data/haum/ContentEyevisit/eyevisit_cards_light/")
+datart <- datart[order(datart$artwork), ]
+names(counts_item) <- datart$title
+
+pdf("results/figures/counts_item.pdf", width = 20, height = 10, pointsize = 10)
+par(mai = c(5, .6, .1, .1))
+tmp <- barplot(counts_item, las = 2, ylim = c(0, 60000),
+               border = NA, col = "#434F4F")
+text(tmp, counts_item + 1000, datart$artwork)
+dev.off()
+
+### Which item gets touched most often first?
+
+datcase <- datlogs[!duplicated(datlogs$case), ]
+counts_case <- table(datcase$item)
+names(counts_case) <- datart$title
+tmp <- barplot(counts_case, las = 2, border = "white")
+text(tmp, counts_case + 100, datart$item)
+
+counts <- rbind(counts_item, counts_case)
+
+pdf("results/figures/counts_item_firsttouch.pdf",
+    width = 20, height = 10, pointsize = 10)
+par(mai = c(5, .6, .1, .1))
+
+tmp <- barplot(counts, las = 2, border = NA, col = c("#434F4F", "#FF6900"), ylim = c(0, 65000))
+text(tmp, counts_item + counts_case + 1000, datart$artwork)
+legend("topleft", c("Total interactions", "First interactions"),
+       col = c("#434F4F", "#FF6900"), pch = 15, bty = "n")
+dev.off()
+
+### Which teasers seem to work well?
+barplot(table(datlogs$topic), las = 2)
+
+### Dwell times/duration
+datagg <- aggregate(duration ~ event + item, datlogs, mean)
+datagg$ds <- datagg$duration / 1000   # in secs
+
+lattice::bwplot(ds ~ event, datagg)
+
+# without aggregation
+lattice::bwplot(duration / 1000 / 60 ~ event, datlogs)
+# in min
+
+set.seed(1027)
+
+pdf("results/figures/duration.pdf", width = 5, height = 5, pointsize = 10)
+lattice::bwplot(I(duration/1000/60) ~ event, datlogs[sample(nrow(datlogs), 100000), ],
+       ylab = "Duration in min")
+dev.off()
+
+### Move events
+
+datmove <- aggregate(cbind(duration, scaleSize, rotationDegree, distance, x.start,
+                           y.start, x.stop, y.stop) ~ item, datlogs,
+                     mean)
+
+hist(log(datlogs$scaleSize))
+# --> better interpretable on logscale
+
+plot(y.start ~ x.start, datmove, pch = 16, col = "gray")
+points(y.start ~ x.start, datmove, col = "#3CB4DC", cex = datmove$scaleSize)
+
+
+plot(y.start ~ x.start, datmove, type = "n", xlab = "x", ylab = "y",
+     xlim = c(0, 3840), ylim = c(0, 2160))
+with(datmove, text(x.start, y.start, item, col = "gray", cex = 1.5))
+with(datmove,
+     arrows(x.start, y.start, x.stop, y.stop, length = 0.07, lwd = 2)
+     )
+abline(v = c(0, 3840), h = c(0, 2160), col = "#3CB4DC", lwd = 2)
+
+datscale <- aggregate(scaleSize ~ item, datlogs, max)
+plot(y.start ~ x.start, datmove, pch = 16, col = "gray")
+points(y.start ~ x.start, datmove, col = "#3CB4DC", cex = datscale$scaleSize)
+
+plot(y.start ~ x.start, datmove, type = "n", xlab = "x", ylab = "y",
+     xlim = c(0, 3840), ylim = c(0, 2160))
+#with(datmove, text(x.stop, y.stop, item))
+with(datmove, text(x.start, y.start, item))
+
+
+### Are there certain areas of the table that are touched most often?
+
+# heatmap
+cuts <- 100
+
+datlogs$x.start.cat <- cut(datlogs$x.start, cuts)
+datlogs$y.start.cat <- cut(datlogs$y.start, cuts)
+
+tab <- xtabs( ~ x.start.cat + y.start.cat, datlogs)
+
+colnames(tab) <- paste0("c", 1:cuts)
+rownames(tab) <- paste0("c", 1:cuts)
+
+heatmap(tab, Rowv = NA, Colv = NA)
+
+
+dattrim <- datlogs[datlogs$x.start < 3840 &
+                   datlogs$x.start > 0 &
+                   datlogs$y.start < 2160 &
+                   datlogs$y.start > 0 &
+                   datlogs$x.stop < 3840 &
+                   datlogs$x.stop > 0 &
+                   datlogs$y.stop < 2160 &
+                   datlogs$y.stop > 0, ]
+
+cuts <- 100 # 200, 100, 70, ...
+
+# start
+dattrim$x.start.cat <- cut(dattrim$x.start, cuts)
+dattrim$y.start.cat <- cut(dattrim$y.start, cuts)
+
+tab.start <- xtabs( ~ x.start.cat + y.start.cat, dattrim)
+colnames(tab.start) <- NULL
+rownames(tab.start) <- NULL
+
+pdf("results/figures/heatmap_start.pdf", width = 5, height = 5, pointsize = 10)
+heatmap(tab.start, Rowv = NA, Colv = NA)
+dev.off()
+
+# stop
+dattrim$x.stop.cat <- cut(dattrim$x.stop, cuts)
+dattrim$y.stop.cat <- cut(dattrim$y.stop, cuts)
+tab.stop <- xtabs( ~ x.stop.cat + y.stop.cat, dattrim)
+colnames(tab.stop) <- NULL
+rownames(tab.stop) <- NULL
+
+pdf("results/figures/heatmap_stop.pdf", width = 5, height = 5, pointsize = 10)
+heatmap(tab.stop, Rowv = NA, Colv = NA)
+dev.off()
+
+### How many visitors per day
+
+datlogs$date <- as.Date(datlogs$date.start)
+
+# Interactions per day
+datint <- aggregate(case ~ date, datlogs, length)
+plot(datint, type = "h")
+
+# Cases per day
+datcase <- aggregate(case ~ date, datlogs, function(x) length(unique(x)))
+plot(datcase, type = "h")
+
+# Paths per day
+datpath <- aggregate(path ~ date, datlogs, function(x) length(unique(x)))
+plot(datpath, type = "h")
+
+plot(path ~ date, datpath, type = "h", col = "#3CB4DC")
+points(case ~ date, datcase, type = "h")
+
+pdf("results/figures/cases_per_day.pdf", width = 9, height = 5, pointsize = 10)
+par(mai = c(.6, .6, .1, .1), mgp = c(2.4, 1, 0))
+plot(case ~ date, datcase, type = "h", col = "#434F4F")
+abline(v = datcase$date[datcase$date %in% c("2020-03-13", "2022-10-25")],
+       col = "#FF6900", lty = 2)
+text(datcase$date[datcase$date == "2020-03-13"]+470, 80,
+     "Corona gap from 2020-03-13 to 2022-10-25",
+     col = "#FF6900")
+dev.off()
+
+## weird behavior of timeMs
+
+pdf("results/figures/timeMs.pdf", width = 9, height = 6, pointsize = 10)
+#par(mai = c(.6, .6, .1, .1), mgp = c(2.4, 1, 0))
+#plot(timeMs.start ~ as.factor(fileId), datlogs[1:2000,], xlab = "fileId")
+lattice::bwplot(timeMs.start ~ as.factor(fileId.start), datlogs[1:2000,], xlab = "",
+       scales = list(x = list(rot = 90), y = list(rot = 90)))
+dev.off()
+
+## x,y-coordinates out of range
+
+set.seed(1522)
+
+pdf("results/figures/xycoord.pdf", width = 5, height = 5, pointsize = 10)
+par(mai = c(.6, .6, .1, .1), mgp = c(2.4, 1, 0))
+#par(mfrow = c(1, 2))
+plot(y.start ~ x.start, datlogs[sample(nrow(datlogs), 10000), ])
+abline(v = c(0, 3840), h = c(0, 2160), col = "#3CB4DC", lwd = 2)
+#plot(y.stop ~ x.stop, datlogs)
+#abline(v = c(0, 3840), h = c(0, 2160), col = "#3CB4DC", lwd = 2)
+legend("bottomleft", "Random sample of 10,000", bg = "white")
+legend("topleft", "4K-Display: 3840 x 2160", bg = "white")
+dev.off()
+
+## moves
+
+dat001 <- datlogs[which(datlogs$item == "001"), ]
+
+index <- as.numeric(as.factor(dat001$path))
+cc <- sample(colors(), 100)
+
+plot(y.start ~ x.start, dat001, type = "n", xlab = "x", ylab = "y",
+     xlim = c(0, 3840), ylim = c(0, 2160))
+with(dat001[1:200,], arrows(x.start, y.start, x.stop, y.stop,
+                            length = .07, col = cc[index]))
+
+plot(y.start ~ x.start, dat001, xlab = "x", ylab = "y",
+     xlim = c(0, 3840), ylim = c(0, 2160), pch = 16, col = "gray")
+points(y.start ~ x.start, dat001, xlab = "x", ylab = "y",
+     xlim = c(0, 3840), ylim = c(0, 2160), cex = dat001$scaleSize,
+     col = "blue")
+
+
+
+cc <- sample(colors(), 70)
+
+dat1 <- datlogs[!duplicated(datlogs$item), ]
+dat1 <- dat1[order(dat1$item), ]
+
+plot(y.start ~ x.start, dat1, type = "n", xlim = c(-100, 4500), ylim = c(-100, 2500))
+abline(h = c(0, 2160), v = c(0, 3840), col = "lightgray")
+with(dat1, points(x.start, y.start, col = cc, pch = 16))
+with(dat1, points(x.stop, y.stop, col = cc, pch = 16))
+with(dat1, arrows(x.start, y.start, x.stop, y.stop, length = .07, col = cc))
+
+
 # How many events per topic, per path, ...
 # How many popups per artwork?
 
 # Number of events per artwork
-tab <- xtabs( ~ artwork + event, datlogs)
+tab <- xtabs( ~ item + event, datlogs)
 addmargins(tab)
 
-proportions(tab, margin = "artwork")
+proportions(tab, margin = "item")
 proportions(tab, margin = "event")
 
 cc <- palette.colors(palette = "Okabe-Ito")[c(3,2,4,8)]
 
-pdf("../figures/event-dist.pdf", height = 3.375, width = 12, pointsize = 10)
+pdf("results/figures/event-dist.pdf", height = 3.375, width = 12, pointsize = 10)
 par(mai = c(.4,.4,.1,.1), mgp = c(2.4, 1, 0))
 
-barplot(t(proportions(tab, margin = "artwork")), las = 2, col = cc,
+barplot(t(proportions(tab, margin = "item")), las = 2, col = c("#78004B", "#3CB4DC", "#91C86E", "#FF6900"),
         legend.text = levels(datlogs$event), args.legend = list(x = "bottomleft", bg = "white"))
 
 dev.off()
 
-#barchart(proportions(tab, margin = "artwork"), las = 2)
+#lattice::barchart(proportions(tab, margin = "item"), las = 2)
 
 # Proportion of events
 proportions(xtabs( ~ event, datlogs))
 # Mean proportion of event per path
 colMeans(proportions(xtabs( ~ path + event, datlogs), margin = "path"))
-# Mean proportion of event per artwork
+# Mean proportion of event per item
-colMeans(proportions(tab, margin = "artwork"))
+colMeans(proportions(tab, margin = "item"))
 
 # Proportion of unclosed events
 
@@ -126,15 +360,17 @@ sum(datlogs$fileId.start != datlogs$fileId.stop, na.rm = TRUE) / nrow(datlogs)
 
 #--------------- (3.1) Check data quality ---------------
 
-alog <- activitylog(datlogs,
+datlogs$start <- datlogs$date.start
+datlogs$complete <- datlogs$date.stop
+
+alog <- bupaR::activitylog(datlogs,
                     case_id = "path",
                     activity_id = "event",
                     #resource_id = "case",
-                    resource_id = "artwork",
+                    resource_id = "item",
                     timestamps = c("start", "complete"))
 
-# process_map(alog, frequency("relative"))
+processmapR::process_map(alog, processmapR::frequency("relative"))
-map_as_pdf(alog, file = "../figures/pm_trace-event.pdf")
 
 alogf <- edeaR::filter_trace_frequency(alog, percentage = 0.9)
 
@@ -147,7 +383,7 @@ processmapR::process_map(alogf,   # alog,
 
 alog_no_move <- alog[alog$event != "move", ]
 
-pdf("../figures/traceexplore_trace-event.pdf", height = 8, width = 12, pointsize = 10)
+pdf("results/figures/traceexplore_trace-event.pdf", height = 8, width = 12, pointsize = 10)
 set.seed(1447)
 processmapR::trace_explorer(alog_no_move[alog_no_move$path %in%
                             sample(unique(alog_no_move$path), 400),],
@@ -155,7 +391,7 @@ processmapR::trace_explorer(alog_no_move[alog_no_move$path %in%
                             abbreviate = T)
 dev.off()
 
-pdf("../figures/ra_trace-event.pdf", height = 8, width = 12, pointsize = 10)
+pdf("results/figures/ra_trace-event.pdf", height = 8, width = 12, pointsize = 10)
 
 ra_no_move <- edeaR::resource_frequency(alog_no_move, "resource-activity")
 levels(ra_no_move$event) <- c("flipCard", "flipCard", "openTopic", "openPopup")
@@ -182,29 +418,29 @@ which.max(table(datlogs$artwork))
 which.min(table(datlogs$artwork))
 which.min(table(datlogs$artwork)[-c(71,72)])
 
-alog080 <- activitylog(datlogs[datlogs$artwork == "080",],
+alog080 <- bupaR::activitylog(datlogs[datlogs$artwork == "080",],
                     case_id = "path",
                     activity_id = "event",
                     resource_id = "artwork",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog080, file = "../figures/pm_trace-event_080.pdf")
+processmapR::process_map(alog80, processmapR::frequency("relative"))
 
-alog087 <- activitylog(datlogs[datlogs$artwork == "087",],
+alog087 <- bupaR::activitylog(datlogs[datlogs$artwork == "087",],
                     case_id = "path",
                     activity_id = "event",
                     resource_id = "artwork",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog087, file = "../figures/pm_trace-event_087.pdf")
+processmapR::process_map(alog087, processmapR::frequency("relative"))
 
-alog504 <- activitylog(datlogs[datlogs$artwork == "504",],
+alog504 <- bupaR::activitylog(datlogs[datlogs$artwork == "504",],
                     case_id = "path",
                     activity_id = "event",
                     resource_id = "artwork",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog504, file = "../figures/pm_trace-event_504.pdf")
+processmapR::process_map(alog504, processmapR::frequency("relative"))
 
 #--------------- (3.3) Patterns of cases ---------------
 
@@ -215,17 +451,17 @@ map_as_pdf(alog504, file = "../figures/pm_trace-event_504.pdf")
 # ... weekdays for "normal" and school vacation days?
 # ... pre and post corona?
 
-alog <- activitylog(datlogs,
+alog <- bupaR::activitylog(datlogs,
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
 alog_no_move <- alog[alog$event != "move", ]
 
-pdf("../figures/traceexplore_case-event.pdf", height = 8, width = 12, pointsize = 10)
+pdf("results/figures/traceexplore_case-event.pdf", height = 8, width = 12, pointsize = 10)
 set.seed(1050)
 processmapR::trace_explorer(alog_no_move[alog_no_move$path %in%
                             sample(unique(alog_no_move$path), 300),],
@@ -233,38 +469,38 @@ processmapR::trace_explorer(alog_no_move[alog_no_move$path %in%
                             abbreviate = T)
 dev.off()
 
-map_as_pdf(alog080, file = "../figures/pm_case-event_080.pdf")
+processmapR::process_map(alog080, processmapR::frequency("relative"))
 
-alog087 <- activitylog(datlogs[datlogs$artwork == "087",],
+alog087 <- bupaR::activitylog(datlogs[datlogs$artwork == "087",],
                        case_id = "case",
                        activity_id = "event",
                        resource_id = "path",
                        timestamps = c("start", "complete"))
 
-map_as_pdf(alog087, file = "../figures/pm_case-event_087.pdf")
+processmapR::process_map(alog087, processmapR::frequency("relative"))
 
 ### Mornings and afternoons
 
 datlogs$tod <- ifelse(lubridate::hour(datlogs$start) > 13, "afternoon", "morning")
 
-alog <- activitylog(datlogs[datlogs$tod == "morning",],
+alog <- bupaR::activitylog(datlogs[datlogs$tod == "morning",],
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event_morning.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
-alog <- activitylog(datlogs[datlogs$tod == "afternoon",],
+alog <- bupaR::activitylog(datlogs[datlogs$tod == "afternoon",],
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event_afternoon.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
 # Are the same artworks looked at?
-pdf("../figures/bp_tod.pdf", height = 3.375, width = 12, pointsize = 10)
+pdf("results/figures/bp_tod.pdf", height = 3.375, width = 12, pointsize = 10)
 par(mai = c(.5,.6,.1,.1), mgp = c(2.4, 1, 0))
 
 barplot(proportions(xtabs( ~ tod + artwork, datlogs), margin = "tod"), #col = cc[1:2],
@@ -277,24 +513,24 @@ dev.off()
 
 datlogs$wd <- ifelse(datlogs$weekdays %in% c("Saturday", "Sunday"), "weekend", "weekday")
 
-alog <- activitylog(datlogs[datlogs$wd == "weekend",],
+alog <- bupaR::activitylog(datlogs[datlogs$wd == "weekend",],
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event_weekend.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
-alog <- activitylog(datlogs[datlogs$wd == "weekday",],
+alog <- bupaR::activitylog(datlogs[datlogs$wd == "weekday",],
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event_weekday.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
 # Are the same artworks looked at?
-pdf("../figures/bp_wd.pdf", height = 3.375, width = 12, pointsize = 10)
+pdf("results/figures/bp_wd.pdf", height = 3.375, width = 12, pointsize = 10)
 par(mai = c(.5,.6,.1,.1), mgp = c(2.4, 1, 0))
 
 barplot(proportions(xtabs( ~ wd + artwork, datlogs), margin = "wd"),
@@ -308,24 +544,24 @@ dev.off()
 datlogs$wds <- ifelse(!is.na(datlogs$vacation), "vacation", "school")
 datlogs$wds[datlogs$wd == "weekend"] <- NA
 
-alog <- activitylog(datlogs[which(datlogs$wds == "school"),],
+alog <- bupaR::activitylog(datlogs[which(datlogs$wds == "school"),],
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event_school.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
-alog <- activitylog(datlogs[which(datlogs$wds == "vacation"),],
+alog <- bupaR::activitylog(datlogs[which(datlogs$wds == "vacation"),],
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event_vacation.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
 # Are the same artworks looked at?
-pdf("../figures/bp_wds.pdf", height = 3.375, width = 12, pointsize = 10)
+pdf("results/figures/bp_wds.pdf", height = 3.375, width = 12, pointsize = 10)
 par(mai = c(.5,.6,.1,.1), mgp = c(2.4, 1, 0))
 
 #barplot(xtabs( ~ wds + artwork, datlogs), las = 2, beside = TRUE,
@@ -339,24 +575,24 @@ dev.off()
 
 datlogs$corona <- ifelse(datlogs$date < "2020-03-14", "pre", "post")
 
-alog <- activitylog(datlogs[which(datlogs$corona == "pre"),],
+alog <- bupaR::activitylog(datlogs[which(datlogs$corona == "pre"),],
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event_pre-corona.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
-alog <- activitylog(datlogs[which(datlogs$corona == "post"),],
+alog <- bupaR::activitylog(datlogs[which(datlogs$corona == "post"),],
                     case_id = "case",
                     activity_id = "event",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-event_post-corona.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
 # Are the same artworks looked at?
-pdf("../figures/bp_corona.pdf", height = 3.375, width = 12, pointsize = 10)
+pdf("results/figures/bp_corona.pdf", height = 3.375, width = 12, pointsize = 10)
 par(mai = c(.5,.6,.1,.1), mgp = c(2.4, 1, 0))
 
 barplot(proportions(xtabs( ~ corona + artwork, datlogs), margin = "corona"),
@@ -369,13 +605,13 @@ dev.off()
 # Order in which artworks are looked at
 
 nart <- 5     # select 5 artworks randomly
-alog <- activitylog(datlogs,#[datlogs$artwork %in% sample(unique(datlogs$artwork), nart), ],
+alog <- bupaR::activitylog(datlogs,#[datlogs$artwork %in% sample(unique(datlogs$artwork), nart), ],
                     case_id = "case",
                     activity_id = "artwork",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-#map <- process_map(alog, frequency("relative"))
+#map <- processmapR::process_map(alog, processmapR::frequency("relative"))
 
 ## select cases with Vermeer
 length(unique(datlogs[datlogs$artwork == "080", "case"]))
@@ -392,16 +628,16 @@ which(table(tmp$artwork) > 14000)
 
 often080 <- names(which(table(tmp$artwork) > 14000))
 
-alog <- activitylog(datlogs[datlogs$artwork %in% often080, ],
+alog <- bupaR::activitylog(datlogs[datlogs$artwork %in% often080, ],
                     case_id = "case",
                     activity_id = "artwork",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-artwork_often080.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
 
-pdf("../figures/traceexplore_case-artwork_often080.pdf", height = 8, width = 12, pointsize = 10)
+pdf("results/figures/traceexplore_case-artwork_often080.pdf", height = 8, width = 12, pointsize = 10)
 
 processmapR::trace_explorer(alog,
                             n_traces = 30, type = "frequent",
@@ -414,40 +650,35 @@ dev.off()
 # Are there certain topics that people are interested in more than others?
 # Do these topic distributions differ for comparable artworks?
 
-alog <- activitylog(datlogs[which(datlogs$event == "openTopic"),],
+alog <- bupaR::activitylog(datlogs[which(datlogs$event == "openTopic"),],
                     case_id = "case",
                     activity_id = "topic",
                     resource_id = "path",
                     timestamps = c("start", "complete"))
 
-map_as_pdf(alog, file = "../figures/pm_case-topic.pdf")
+processmapR::process_map(alog, processmapR::frequency("relative"))
 
 # Order of topics for Vermeer
-# alog080 <- activitylog(datlogs[datlogs$artwork == "080",],
+# alog080 <- bupaR::activitylog(datlogs[datlogs$artwork == "080",],
 #                     case_id = "case",
 #                     activity_id = "topic",
 #                     resource_id = "path",
 #                     timestamps = c("start", "complete"))
 #
-# map_as_pdf(alog080, file = "../figures/pm_case-topic_080.pdf")
+# alog080 <- bupaR::activitylog(datlogs[datlogs$artwork == "080",],
-#
-#
-# alog080 <- activitylog(datlogs[datlogs$artwork == "080",],
 #                        case_id = "case",
 #                        activity_id = "topicFile",
 #                        resource_id = "path",
 #                        timestamps = c("start", "complete"))
 #
-# #process_map(alog080, frequency("relative"))
+# #processmapR::process_map(alog080, processmapR::frequency("relative"))
 #
 # # Comparable artwork
-# alog083 <- activitylog(datlogs[datlogs$artwork == "083",],
+# alog083 <- bupaR::activitylog(datlogs[datlogs$artwork == "083",],
 #                        case_id = "case",
 #                        activity_id = "topic",
 #                        resource_id = "path",
 #                        timestamps = c("start", "complete"))
-#
-# map_as_pdf(alog083, file = "../figures/pm_case-topic_083.pdf")
 
 # artworks that have the same topics than Vermeer
 which(rowSums(xtabs( ~ artwork + topic, datlogs[datlogs$topic %in%
@@ -458,73 +689,13 @@ which(rowSums(xtabs( ~ artwork + topic, datlogs[datlogs$topic %in%
 
 for (art in c("037", "046", "062", "080", "083", "109")) {
 
-  alog <- activitylog(datlogs[datlogs$event == "openTopic" & datlogs$artwork == art,],
+  alog <- bupaR::activitylog(datlogs[datlogs$event == "openTopic" & datlogs$artwork == art,],
                       case_id = "case",
                       activity_id = "topic",
                       resource_id = "path",
                       timestamps = c("start", "complete"))
 
-  map_as_pdf(alog, file = paste0("../figures/pm_case-topic_", art, ".pdf"))
+  processmapR::process_map(alog, processmapR::frequency("relative"))
 }
 
 
-
-# Angewandte Kunst, Graphik, Gemälde, Kultur
-
-
-c("Kultur", "Kultur", "Graphik", "Gemälde", "Gemälde", "Gemälde",
-  "Gemälde", "Gemälde", "Graphik", "Gemälde", "Angewandte Kunst", "",
-  "Gemälde", "Angewandte Kunst", "", "", "Graphik", "Angewandte Kunst",
-  "Angewandte Kunst", "Gemälde", "Angewandte Kunst", "Gemälde", "",
-  "Gemälde", "Gemälde", "Gemälde", "Graphik", "Gemälde", "Gemälde",
-  "Gemälde", "", "Angewandte Kunst", "Angewandte Kunst", "Gemälde",
-  "Graphik", "Gemälde", "Gemälde", "Gemälde", "Gemälde",
-  "Angewandte Kunst", "Gemälde", "Gemälde", "Gemälde", "Kultur", "Kultur",
-  "Gemälde", "Kultur", "", "Gemälde", "", "Graphik", "Kultur", "Gemälde",
-  "", "Kultur", "Gemälde", "Kultur", "Gemälde", "Gemälde", "Gemälde",
-  "Kultur", "Kultur", "Kultur", "Kultur", "Kultur", "Kultur",
-  "Angewandte Kunst", "Info", "Info", "Info", "Kultur", "Kultur")
-
-
-
-# BURSTS
-which.max(table(datlogs$date))
-tmp <- datlogs[datlogs$date == "2017-02-12", ]
-
-# number of traces per case on 2017-02-12
-rowSums(xtabs( ~ case + path, tmp) != 0)
-
-range(tmp$start)
-hours <- lubridate::hour(tmp$start)
-xtabs( ~ case + hours, tmp)
-
-# distribution of cases over the day
-colSums(xtabs( ~ case + hours, tmp) != 0)
-barplot(colSums(xtabs( ~ case + hours, tmp) != 0))
-
-aggregate(path ~ case + hours, tmp, length)
-
-
-
-
-tmp <- aggregate(path ~ case, datlogs, length)
-tmp$date <- as.Date(datlogs[!duplicated(datlogs$case), "start"])
-tmp$time <- lubridate::hour(datlogs[!duplicated(datlogs$case), "start"])
-
-tmp[tmp$path > 200, ]
-
-plot(path ~ time, tmp, cex = 2, col = rgb(0,0,0,.3))
-
-lattice::barchart(path ~ time, tmp, horizontal=F)
-
-
-
-###########################################################################
-# HELPER
-
-map_as_pdf <- function(alog, file, type = frequency("relative")) {
-  map <- process_map(alog, type = type)
-  g <- DiagrammeR::grViz(map$x$diagram) |> DiagrammeRsvg::export_svg() |> charToRaw()
-  rsvg::rsvg_pdf(g, file)
-}
-

code/03_create-petrinet.py

@@ -1,18 +1,14 @@
 # 03_create-petrinet.py
 #
 # content: (1) Create places and transitions
-#          (2) Sequential net
+#          (2) Normative net
-#          (3) Concurrent net
 #
 # input:  --
-# output: results/haum/conformative_petrinet_con.pnml
+# output: results/normative_petrinet.pnml
-#         results/processmaps/conformative_petrinet_con.png
+#         results/processmaps/normative_petrinet.png
-#         results/processmaps/conformative_bpmn_con.png
+#         results/processmaps/normative_bpmn.png
-#         results/haum/conformative_petrinet_seq.pnml
-#         results/processmaps/conformative_petrinet_seq.png
-#         results/processmaps/conformative_bpmn_seq.png
 #
-# last mod: 2024-03-06
+# last mod: 2024-03-22
 
 import pm4py
 from pm4py.objects.petri_net.obj import PetriNet, Marking
@@ -62,93 +58,90 @@ t_16 = PetriNet.Transition("t_16")
 t_17 = PetriNet.Transition("t_17")
 t_18 = PetriNet.Transition("t_18")
 
-#--------------- (2) Sequential net ---------------
+#--------------- (2) Normative net ---------------
 
-net_seq = PetriNet("new_petri_net")
+net = PetriNet("new_petri_net")
 
 # Add places
-net_seq.places.add(source)
+net.places.add(source)
-net_seq.places.add(sink)
+net.places.add(sink)
-net_seq.places.add(p_1)
+net.places.add(p_1)
-net_seq.places.add(p_2)
+net.places.add(p_2)
-net_seq.places.add(p_3)
+net.places.add(p_3)
-net_seq.places.add(p_4)
+net.places.add(p_4)
-net_seq.places.add(p_5)
+net.places.add(p_5)
-net_seq.places.add(p_6)
+net.places.add(p_6)
-net_seq.places.add(p_7)
+net.places.add(p_7)
-net_seq.places.add(p_8)
+net.places.add(p_8)
+net.places.add(p_9)
+net.places.add(p_10)
+net.places.add(p_11)
+net.places.add(p_12)
 
 # Add transitions
-net_seq.transitions.add(mv)
+net.transitions.add(mv)
-net_seq.transitions.add(fc)
+net.transitions.add(fc)
-net_seq.transitions.add(ot)
+net.transitions.add(ot)
-net_seq.transitions.add(op)
+net.transitions.add(op)
 
 # Add hidden transitions
-net_seq.transitions.add(t_1)
+net.transitions.add(t_1)
-net_seq.transitions.add(t_2)
+net.transitions.add(t_2)
-net_seq.transitions.add(t_3)
+net.transitions.add(t_3)
-net_seq.transitions.add(t_4)
+net.transitions.add(t_4)
-net_seq.transitions.add(t_5)
+net.transitions.add(t_5)
-net_seq.transitions.add(t_6)
+net.transitions.add(t_6)
-net_seq.transitions.add(t_7)
+net.transitions.add(t_7)
-net_seq.transitions.add(t_8)
+net.transitions.add(t_8)
-net_seq.transitions.add(t_9)
+net.transitions.add(t_9)
-net_seq.transitions.add(t_10)
+net.transitions.add(t_10)
-net_seq.transitions.add(t_11)
+net.transitions.add(t_11)
-net_seq.transitions.add(t_12)
+net.transitions.add(t_12)
-net_seq.transitions.add(t_13)
+net.transitions.add(t_13)
-net_seq.transitions.add(t_14)
+net.transitions.add(t_14)
-net_seq.transitions.add(t_15)
+net.transitions.add(t_15)
-net_seq.transitions.add(t_16)
-net_seq.transitions.add(t_17)
-net_seq.transitions.add(t_18)
 
 # Add arcs
-petri_utils.add_arc_from_to(source, t_1, net_seq)
+petri_utils.add_arc_from_to(source, t_1, net)
-petri_utils.add_arc_from_to(source, t_2, net_seq)
+petri_utils.add_arc_from_to(t_1, p_1, net)
-petri_utils.add_arc_from_to(t_1, p_1, net_seq)
+petri_utils.add_arc_from_to(t_1, p_2, net)
-petri_utils.add_arc_from_to(t_2, p_2, net_seq)
+petri_utils.add_arc_from_to(p_1, t_2, net)
-petri_utils.add_arc_from_to(p_1, mv, net_seq)
+petri_utils.add_arc_from_to(p_1, t_3, net)
-petri_utils.add_arc_from_to(p_2, fc, net_seq)
+petri_utils.add_arc_from_to(t_3, p_5, net)
-petri_utils.add_arc_from_to(mv, p_3, net_seq)
+petri_utils.add_arc_from_to(t_2, p_3, net)
-petri_utils.add_arc_from_to(p_3, t_3, net_seq)
+petri_utils.add_arc_from_to(p_3, mv, net)
-petri_utils.add_arc_from_to(p_3, t_4, net_seq)
+petri_utils.add_arc_from_to(mv, p_4, net)
-petri_utils.add_arc_from_to(p_3, t_5, net_seq)
+petri_utils.add_arc_from_to(p_4, t_5, net)
-petri_utils.add_arc_from_to(p_3, t_6, net_seq)
+petri_utils.add_arc_from_to(p_4, t_6, net)
-petri_utils.add_arc_from_to(p_3, t_7, net_seq)
+petri_utils.add_arc_from_to(t_6, p_3, net)
-petri_utils.add_arc_from_to(t_7, p_1, net_seq)
+petri_utils.add_arc_from_to(t_5, p_5, net)
-petri_utils.add_arc_from_to(fc, p_4, net_seq)
+petri_utils.add_arc_from_to(p_5, t_15, net)
-petri_utils.add_arc_from_to(p_4, t_8, net_seq)
+petri_utils.add_arc_from_to(t_15, sink, net)
-petri_utils.add_arc_from_to(p_4, t_9, net_seq)
+petri_utils.add_arc_from_to(p_2, fc, net)
-petri_utils.add_arc_from_to(p_4, t_10, net_seq)
+petri_utils.add_arc_from_to(p_2, t_8, net)
-petri_utils.add_arc_from_to(t_9, p_1, net_seq)
+petri_utils.add_arc_from_to(t_8, p_12, net)
-petri_utils.add_arc_from_to(t_16, p_5, net_seq)
+petri_utils.add_arc_from_to(p_12, t_15, net)
-petri_utils.add_arc_from_to(t_3, p_2, net_seq)
+petri_utils.add_arc_from_to(fc, p_6, net)
-petri_utils.add_arc_from_to(t_5, p_6, net_seq)
+petri_utils.add_arc_from_to(p_6, t_9, net)
-petri_utils.add_arc_from_to(t_6, p_5, net_seq)
+petri_utils.add_arc_from_to(t_9, p_12, net)
-petri_utils.add_arc_from_to(p_6, ot, net_seq)
+petri_utils.add_arc_from_to(p_6, t_4, net)
-petri_utils.add_arc_from_to(p_5, op, net_seq)
+petri_utils.add_arc_from_to(t_4, p_7, net)
-petri_utils.add_arc_from_to(ot, p_8, net_seq)
+petri_utils.add_arc_from_to(p_7, ot, net)
-petri_utils.add_arc_from_to(op, p_7, net_seq)
+petri_utils.add_arc_from_to(ot, p_8, net)
-petri_utils.add_arc_from_to(p_8, t_11, net_seq)
+petri_utils.add_arc_from_to(p_8, t_10, net)
-petri_utils.add_arc_from_to(p_8, t_12, net_seq)
+petri_utils.add_arc_from_to(t_10, p_11, net)
-petri_utils.add_arc_from_to(p_8, t_13, net_seq)
+petri_utils.add_arc_from_to(p_11, t_13, net)
-petri_utils.add_arc_from_to(p_8, t_17, net_seq)
+petri_utils.add_arc_from_to(t_13, p_12, net)
-petri_utils.add_arc_from_to(t_10, p_6, net_seq)
+petri_utils.add_arc_from_to(p_8, t_7, net)
-petri_utils.add_arc_from_to(t_17, p_6, net_seq)
+petri_utils.add_arc_from_to(t_7, p_9, net)
-petri_utils.add_arc_from_to(p_7, t_14, net_seq)
+petri_utils.add_arc_from_to(p_9, op, net)
-petri_utils.add_arc_from_to(p_7, t_15, net_seq)
+petri_utils.add_arc_from_to(op, p_10, net)
-petri_utils.add_arc_from_to(p_7, t_16, net_seq)
+petri_utils.add_arc_from_to(p_10, t_11, net)
-petri_utils.add_arc_from_to(p_7, t_18, net_seq)
+petri_utils.add_arc_from_to(p_10, t_12, net)
-petri_utils.add_arc_from_to(t_18, p_6, net_seq)
+petri_utils.add_arc_from_to(t_12, p_9, net)
-petri_utils.add_arc_from_to(t_13, p_5, net_seq)
+petri_utils.add_arc_from_to(t_11, p_11, net)
-petri_utils.add_arc_from_to(t_15, p_1, net_seq)
+petri_utils.add_arc_from_to(p_11, t_14, net)
-petri_utils.add_arc_from_to(t_11, p_1, net_seq)
+petri_utils.add_arc_from_to(t_14, p_7, net)
-petri_utils.add_arc_from_to(t_4, sink, net_seq)
-petri_utils.add_arc_from_to(t_8, sink, net_seq)
-petri_utils.add_arc_from_to(t_12, sink, net_seq)
-petri_utils.add_arc_from_to(t_14, sink, net_seq)
 
 # Add tokens
 initial_marking = Marking()
@@ -156,116 +149,14 @@ initial_marking[source] = 1
 final_marking = Marking()
 final_marking[sink] = 1
 
-pm4py.view_petri_net(net_seq, initial_marking, final_marking)
+pm4py.view_petri_net(net, initial_marking, final_marking)
-pm4py.write_pnml(net_seq, initial_marking, final_marking, "results/haum/conformative_petrinet_seq.pnml")
+pm4py.write_pnml(net, initial_marking, final_marking,
+        "results/normative_petrinet.pnml")
 
-pm4py.vis.save_vis_petri_net(net_seq, initial_marking, final_marking,
+pm4py.vis.save_vis_petri_net(net, initial_marking, final_marking,
-        "results/processmaps/conformative_petrinet_seq.png")
+        "results/processmaps/normative_petrinet.png")
 
-bpmn = pm4py.convert.convert_to_bpmn(net_seq, initial_marking, final_marking)
+bpmn = pm4py.convert.convert_to_bpmn(net, initial_marking, final_marking)
 pm4py.view_bpmn(bpmn)
 
-pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/conformative_bpmn_seq.png")
+pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/normative_bpmn.png")
-
-
-#--------------- (3) Concurrent net ---------------
-
-net_con = PetriNet("new_petri_net")
-
-# Add places
-net_con.places.add(source)
-net_con.places.add(sink)
-net_con.places.add(p_1)
-net_con.places.add(p_2)
-net_con.places.add(p_3)
-net_con.places.add(p_4)
-net_con.places.add(p_5)
-net_con.places.add(p_6)
-net_con.places.add(p_7)
-net_con.places.add(p_8)
-net_con.places.add(p_9)
-net_con.places.add(p_10)
-net_con.places.add(p_11)
-net_con.places.add(p_12)
-
-# Add transitions
-net_con.transitions.add(mv)
-net_con.transitions.add(fc)
-net_con.transitions.add(ot)
-net_con.transitions.add(op)
-
-# Add hidden transitions
-net_con.transitions.add(t_1)
-net_con.transitions.add(t_2)
-net_con.transitions.add(t_3)
-net_con.transitions.add(t_4)
-net_con.transitions.add(t_5)
-net_con.transitions.add(t_6)
-net_con.transitions.add(t_7)
-net_con.transitions.add(t_8)
-net_con.transitions.add(t_9)
-net_con.transitions.add(t_10)
-net_con.transitions.add(t_11)
-net_con.transitions.add(t_12)
-net_con.transitions.add(t_13)
-net_con.transitions.add(t_14)
-net_con.transitions.add(t_15)
-
-# Add arcs
-petri_utils.add_arc_from_to(source, t_1, net_con)
-petri_utils.add_arc_from_to(t_1, p_1, net_con)
-petri_utils.add_arc_from_to(t_1, p_2, net_con)
-petri_utils.add_arc_from_to(p_1, t_2, net_con)
-petri_utils.add_arc_from_to(p_1, t_3, net_con)
-petri_utils.add_arc_from_to(t_3, p_5, net_con)
-petri_utils.add_arc_from_to(t_2, p_3, net_con)
-petri_utils.add_arc_from_to(p_3, mv, net_con)
-petri_utils.add_arc_from_to(mv, p_4, net_con)
-petri_utils.add_arc_from_to(p_4, t_5, net_con)
-petri_utils.add_arc_from_to(p_4, t_6, net_con)
-petri_utils.add_arc_from_to(t_6, p_3, net_con)
-petri_utils.add_arc_from_to(t_5, p_5, net_con)
-petri_utils.add_arc_from_to(p_5, t_15, net_con)
-petri_utils.add_arc_from_to(t_15, sink, net_con)
-petri_utils.add_arc_from_to(p_2, fc, net_con)
-petri_utils.add_arc_from_to(p_2, t_8, net_con)
-petri_utils.add_arc_from_to(t_8, p_12, net_con)
-petri_utils.add_arc_from_to(p_12, t_15, net_con)
-petri_utils.add_arc_from_to(fc, p_6, net_con)
-petri_utils.add_arc_from_to(p_6, t_9, net_con)
-petri_utils.add_arc_from_to(t_9, p_12, net_con)
-petri_utils.add_arc_from_to(p_6, t_4, net_con)
-petri_utils.add_arc_from_to(t_4, p_7, net_con)
-petri_utils.add_arc_from_to(p_7, ot, net_con)
-petri_utils.add_arc_from_to(ot, p_8, net_con)
-petri_utils.add_arc_from_to(p_8, t_10, net_con)
-petri_utils.add_arc_from_to(t_10, p_11, net_con)
-petri_utils.add_arc_from_to(p_11, t_13, net_con)
-petri_utils.add_arc_from_to(t_13, p_12, net_con)
-petri_utils.add_arc_from_to(p_8, t_7, net_con)
-petri_utils.add_arc_from_to(t_7, p_9, net_con)
-petri_utils.add_arc_from_to(p_9, op, net_con)
-petri_utils.add_arc_from_to(op, p_10, net_con)
-petri_utils.add_arc_from_to(p_10, t_11, net_con)
-petri_utils.add_arc_from_to(p_10, t_12, net_con)
-petri_utils.add_arc_from_to(t_12, p_9, net_con)
-petri_utils.add_arc_from_to(t_11, p_11, net_con)
-petri_utils.add_arc_from_to(p_11, t_14, net_con)
-petri_utils.add_arc_from_to(t_14, p_7, net_con)
-
-# Add tokens
-initial_marking = Marking()
-initial_marking[source] = 1
-final_marking = Marking()
-final_marking[sink] = 1
-
-pm4py.view_petri_net(net_con, initial_marking, final_marking)
-pm4py.write_pnml(net_con, initial_marking, final_marking, "results/haum/conformative_petrinet_con.pnml")
-
-pm4py.vis.save_vis_petri_net(net_con, initial_marking, final_marking,
-        "results/processmaps/conformative_petrinet_con.png")
-
-bpmn = pm4py.convert.convert_to_bpmn(net_con, initial_marking, final_marking)
-pm4py.view_bpmn(bpmn)
-
-pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/conformative_bpmn_con.png")

code/04_conformance-checking.py

@@ -1,25 +1,24 @@
 # 04_conformance-checking.py
 #
 # content: (1) Load data and create event log
-#          (2) Infos for items
+#          (2) Check against normative Petri Net
 #
-# input:  results/haum/event_logfiles_2024-02-21_16-07-33.csv
+# input:  results/event_logfiles_2024-02-21_16-07-33.csv
-#         results/haum/conformative_petrinet_con.pnml
+#         results/normative_petrinet.pnml
-# output: results/processmaps/dfg_complete_python.png
+# output: results/eval_all-miners_complete.csv
-#         results/eval_all-miners_complete.csv
 #         results/eval_all-miners_clean.csv
-#         results/processmaps/petrinet_conformative.png
+#         ../../thesis/figures/petrinet_normative.png
-#         results/processmaps/petrinet_heuristics_clean.png
+#         ../../thesis/figures/petrinet_heuristics_clean.png
-#         results/processmaps/petrinet_alpha_clean.png
+#         ../../thesis/figures/petrinet_alpha_clean.png
-#         results/processmaps/petrinet_inductive_clean.png
+#         ../../thesis/figures/petrinet_inductive_clean.png
-#         results/processmaps/petrinet_ilp_clean.png
+#         ../../thesis/figures/petrinet_ilp_clean.png
-#         results/processmaps/bpmn_conformative.png
+#         ../../thesis/figures/bpmn_normative.png
-#         results/processmaps/bpmn_inductive_clean.png
+#         ../../thesis/figures/bpmn_inductive_clean.png
-#         results/processmaps/bpmn_ilp_clean.png
+#         ../../thesis/figures/bpmn_ilp_clean.png
-#         results/processmaps/bpmn_alpha_clean.png
+#         ../../thesis/figures/bpmn_alpha_clean.png
-#         results/processmaps/bpmn_heuristics_clean.png
+#         ../../thesis/figures/bpmn_heuristics_clean.png
 #
-# last mod: 2024-03-06
+# last mod: 2024-03-22
 
 import pm4py
 import pandas as pd
@@ -29,13 +28,13 @@ from python_helpers import eval_pm, pn_infos_miner
 
 #--------------- (1) Load data and create event logs ---------------
 
-dat = pd.read_csv("results/haum/event_logfiles_2024-02-21_16-07-33.csv", sep = ";")
+dat = pd.read_csv("results/event_logfiles_2024-02-21_16-07-33.csv", sep = ";")
 
 event_log = pm4py.format_dataframe(dat, case_id = "path",
                                    activity_key = "event",
                                    timestamp_key = "date.start")
 
-###### Descriptives of log data ######
+## Descriptives of log data
 
 # Distribution of events
 event_log.event.value_counts()
@@ -57,9 +56,9 @@ len(variants_no_move)
 sorted_variants_no_move = dict(sorted(variants_no_move.items(), key=lambda item: item[1], reverse = True))
 {k: sorted_variants_no_move[k] for k in list(sorted_variants_no_move)[:20]}
 
-###### Check against "conformative" Petri Net ######
+#--------------- (2) Check against normative Petri Net ---------------
 
-basenet, initial_marking, final_marking = pm4py.read_pnml("results/haum/conformative_petrinet_con.pnml")
+basenet, initial_marking, final_marking = pm4py.read_pnml("results/normative_petrinet.pnml")
 
 # TBR
 replayed_traces = pm4py.conformance_diagnostics_token_based_replay(event_log, basenet, initial_marking, final_marking)
@@ -93,23 +92,13 @@ event_log[event_log["@@case_index"] == index_broken[0]].item.unique().tolist()
 event_log[event_log["@@case_index"] == index_broken[0]]["fileId.start"].unique().tolist()
 # --> logging error in raw file
 
-## Footprints                      
-from pm4py.algo.discovery.footprints import algorithm as footprints_discovery
-from pm4py.visualization.footprints import visualizer as fp_visualizer
-fp_log = footprints_discovery.apply(event_log, variant=footprints_discovery.Variants.ENTIRE_EVENT_LOG)
-fp_net = footprints_discovery.apply(basenet, initial_marking, final_marking)
-gviz = fp_visualizer.apply(fp_net, parameters={fp_visualizer.Variants.SINGLE.value.Parameters.FORMAT: "svg"})
-fp_visualizer.view(gviz)
-
-efg_graph = pm4py.discover_eventually_follows_graph(event_log)
-
 ## Fitting different miners
 
 eval = pd.DataFrame(columns = ["fitness", "precision", "generalizability",
                                "simplicity", "sound", "narcs", "ntrans",
                                "nplaces", "nvariants", "mostfreq"])
 
-for miner in ["conformative", "alpha", "heuristics", "inductive", "ilp"]:
+for miner in ["normative", "alpha", "heuristics", "inductive", "ilp"]:
     eval = pd.concat([eval, pn_infos_miner(event_log, miner)])
 
 eval.to_csv("results/eval_all-miners_complete.csv", sep = ";")
@@ -121,7 +110,7 @@ eval_clean = pd.DataFrame(columns = ["fitness", "precision", "generalizability",
                                      "simplicity", "sound", "narcs", "ntrans",
                                      "nplaces", "nvariants", "mostfreq"])
 
-for miner in ["conformative", "alpha", "heuristics", "inductive", "ilp"]:
+for miner in ["normative", "alpha", "heuristics", "inductive", "ilp"]:
     eval_clean = pd.concat([eval_clean, pn_infos_miner(event_log_clean, miner)])
 
 eval_clean.to_csv("results/eval_all-miners_clean.csv", sep = ";")
@@ -129,28 +118,27 @@ eval_clean.to_csv("results/eval_all-miners_clean.csv", sep = ";")
 ## Directly-follows graph
 dfg, start_activities, end_activities = pm4py.discover_dfg(event_log_clean)
 pm4py.view_dfg(dfg, start_activities, end_activities)
-pm4py.save_vis_dfg(dfg, start_activities, end_activities, "results/processmaps/dfg_complete_python.png")
 
 ## Export petri nets
-pm4py.vis.save_vis_petri_net(basenet, initial_marking, final_marking, "results/processmaps/petrinet_conformative.png")
+pm4py.vis.save_vis_petri_net(basenet, initial_marking, final_marking,
+        "../../thesis/figures/petrinet_normative.png")
 h_net, h_im, h_fm = pm4py.discover_petri_net_heuristics(event_log_clean)
-pm4py.vis.save_vis_petri_net(h_net, h_im, h_fm, "results/processmaps/petrinet_heuristics_clean.png")
+pm4py.vis.save_vis_petri_net(h_net, h_im, h_fm, "../../thesis/figures/petrinet_heuristics_clean.png")
 a_net, a_im, a_fm = pm4py.discover_petri_net_alpha(event_log_clean)
-pm4py.vis.save_vis_petri_net(a_net, a_im, a_fm, "results/processmaps/petrinet_alpha_clean.png")
+pm4py.vis.save_vis_petri_net(a_net, a_im, a_fm, "../../thesis/figures/petrinet_alpha_clean.png")
 i_net, i_im, i_fm = pm4py.discover_petri_net_inductive(event_log_clean)
-pm4py.vis.save_vis_petri_net(i_net, i_im, i_fm, "results/processmaps/petrinet_inductive_clean.png")
+pm4py.vis.save_vis_petri_net(i_net, i_im, i_fm, "../../thesis/figures/petrinet_inductive_clean.png")
 ilp_net, ilp_im, ilp_fm = pm4py.discover_petri_net_ilp(event_log_clean)
-pm4py.vis.save_vis_petri_net(ilp_net, ilp_im, ilp_fm, "results/processmaps/petrinet_ilp_clean.png")
+pm4py.vis.save_vis_petri_net(ilp_net, ilp_im, ilp_fm, "../../thesis/figures/petrinet_ilp_clean.png")
 
 # convert to BPMN
 base_bpmn = pm4py.convert.convert_to_bpmn(basenet, initial_marking, final_marking)
-pm4py.vis.save_vis_bpmn(base_bpmn, "results/processmaps/bpmn_conformative.png")
+pm4py.vis.save_vis_bpmn(base_bpmn, "../../thesis/figures/bpmn_normative.png")
 i_bpmn = pm4py.convert.convert_to_bpmn(i_net, i_im, i_fm)
-pm4py.vis.save_vis_bpmn(i_bpmn, "results/processmaps/bpmn_inductive_clean.png")
+pm4py.vis.save_vis_bpmn(i_bpmn, "../../thesis/figures/bpmn_inductive_clean.png")
 ilp_bpmn = pm4py.convert.convert_to_bpmn(ilp_net, ilp_im, ilp_fm)
-pm4py.vis.save_vis_bpmn(ilp_bpmn, "results/processmaps/bpmn_ilp_clean.png")
+pm4py.vis.save_vis_bpmn(ilp_bpmn, "../../thesis/figures/bpmn_ilp_clean.png")
 a_bpmn = pm4py.convert.convert_to_bpmn(a_net, a_im, a_fm)
-pm4py.vis.save_vis_bpmn(a_bpmn, "results/processmaps/bpmn_alpha_clean.png")
+pm4py.vis.save_vis_bpmn(a_bpmn, "../../thesis/figures/bpmn_alpha_clean.png")
 h_bpmn = pm4py.convert.convert_to_bpmn(h_net, h_im, h_fm)
-pm4py.vis.save_vis_bpmn(h_bpmn, "results/processmaps/bpmn_heuristics_clean.png")
+pm4py.vis.save_vis_bpmn(h_bpmn, "../../thesis/figures/bpmn_heuristics_clean.png")
-

code/05_check-traces.R

@@ -5,22 +5,23 @@
 #          (3) DFG for complete data
 #          (4) Export data frame for analyses
 #
-# input:  results/haum/event_logfiles_2024-02-21_16-07-33.csv
+# input:  results/event_logfiles_2024-02-21_16-07-33.csv
-#         results/haum/raw_logfiles_2024-02-21_16-07-33.csv
+#         results/raw_logfiles_2024-02-21_16-07-33.csv
-# output: results/haum/eventlogs_pre-corona_cleaned.RData
+# output: results/eventlogs_pre-corona_cleaned.RData
-#         results/haum/eventlogs_pre-corona_cleaned.csv
+#         results/eventlogs_pre-corona_cleaned.csv
+#         ../../thesis/figures/dfg_complete_WFnet_R.pdf
 #
-# last mod: 2024-03-06
+# last mod: 2024-03-23
 
 # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
 
 #--------------- (1) Look at broken trace ---------------
 
-datraw <- read.table("results/haum/raw_logfiles_2024-02-21_16-07-33.csv",
+datraw <- read.table("results/raw_logfiles_2024-02-21_16-07-33.csv",
-                   header = TRUE, sep = ";")
+                     header = TRUE, sep = ";")
 
 
-datlogs <- read.table("results/haum/event_logfiles_2024-02-21_16-07-33.csv",
+datlogs <- read.table("results/event_logfiles_2024-02-21_16-07-33.csv",
                       colClasses = c("character", "character", "POSIXct",
                                      "POSIXct", "character", "integer",
                                      "numeric", "character", "character",
@@ -84,7 +85,7 @@ dfg <- processmapR::process_map(alog,
   render     = FALSE)
 
 processmapR::export_map(dfg,
-  file_name = paste0("results/processmaps/dfg_complete_R.pdf"),
+  file_name = paste0("../../thesis/figures/dfg_complete_WFnet_R.pdf"),
   file_type = "pdf")
 
 rm(tmp)
@@ -109,10 +110,10 @@ dat <- datlogs[as.Date(datlogs$date.start) < "2020-03-13", ]
 # Remove corrupt trace
 dat <- dat[dat$path != 106098, ]
 
-save(dat, file = "results/haum/eventlogs_pre-corona_cleaned.RData")
+save(dat, file = "results/eventlogs_pre-corona_cleaned.RData")
 
 write.table(dat,
-            file = "results/haum/eventlogs_pre-corona_cleaned.csv",
+            file = "results/eventlogs_pre-corona_cleaned.csv",
             sep = ";",
             quote = FALSE,
             row.names = FALSE)

code/06_infos-items.py

@@ -3,10 +3,10 @@
 # content: (1) Load data and create event log
 #          (2) Infos for items
 #
-# input:  results/haum/eventlogs_pre-corona_cleaned.csv
+# input:  results/eventlogs_pre-corona_cleaned.csv
-# output: results/haum/pn_infos_items.csv
+# output: results/pn_infos_items.csv
 #
-# last mod: 2024-03-06
+# last mod: 2024-03-22
 
 import pm4py
 import pandas as pd
@@ -16,7 +16,7 @@ from python_helpers import eval_pm, pn_infos
 
 #--------------- (1) Load data and create event logs ---------------
 
-dat = pd.read_csv("results/haum/eventlogs_pre-corona_cleaned", sep = ";")
+dat = pd.read_csv("results/eventlogs_pre-corona_cleaned", sep = ";")
 
 log_path = pm4py.format_dataframe(dat, case_id = "path", activity_key = "event",
                                   timestamp_key = "date.start")
@@ -33,5 +33,5 @@ for item in log_path.item.unique().tolist():
 eval = eval.sort_index()
 
 # Export
-eval.to_csv("results/haum/pn_infos_items.csv", sep = ";")
+eval.to_csv("results/pn_infos_items.csv", sep = ";")
 

code/07_item-clustering.R

@@ -7,15 +7,12 @@
 #          (2) Clustering
 #          (3) Visualization with pictures
 #
-# input:  results/haum/eventlogs_pre-corona_cleaned.RData
+# input:  results/eventlogs_pre-corona_cleaned.RData
-#         results/haum/pn_infos_items.csv
+#         results/pn_infos_items.csv
-# output: results/haum/eventlogs_pre-corona_item-clusters.csv
+# output: results/eventlogs_pre-corona_item-clusters.csv
-#         results/figures/dendrogram_items.pdf
+#         ../../thesis/figures/data/clustering_items.RData"
-#         results/figures/clustering_items.pdf
-#         results/figures/clustering_artworks.pdf
-#         results/figures/clustering_artworks.png
 #
-# last mod: 2024-03-08
+# last mod: 2024-03-22
 
 # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
 
@@ -25,11 +22,11 @@ source("R_helpers.R")
 
 #--------------- (1.1) Read log event data ---------------
 
-load("results/haum/eventlogs_pre-corona_cleaned.RData")
+load("results/eventlogs_pre-corona_cleaned.RData")
 
 #--------------- (1.2) Read infos for PM for items ---------------
 
-datitem <- read.table("results/haum/pn_infos_items.csv", header = TRUE,
+datitem <- read.table("results/pn_infos_items.csv", header = TRUE,
                       sep = ";", row.names = 1)
 
 #--------------- (1.3) Extract additional infos for clustering ---------------
@@ -96,9 +93,6 @@ mycols <- c("#434F4F", "#78004B", "#FF6900", "#3CB4DC", "#91C86E", "Black")
 
 cluster <- cutree(hc, k = k)
 
-pdf("results/figures/dendrogram_items.pdf", width = 6.5, height = 5.5, pointsize = 10)
-# TODO: Move code for plots to /thesis/
-
 factoextra::fviz_dend(hc, k = k,
                       cex = 0.5,
                       k_colors = mycols,
@@ -109,10 +103,6 @@ factoextra::fviz_dend(hc, k = k,
                       #ggtheme = ggplot2::theme_bw()
 )
 
-dev.off()
-
-pdf("results/figures/clustering_items.pdf", width = 6.5, height = 5.5, pointsize = 10)
-
 factoextra::fviz_cluster(list(data = df, cluster = cluster),
                          palette = mycols,
                          ellipse.type = "convex",
@@ -121,8 +111,6 @@ factoextra::fviz_cluster(list(data = df, cluster = cluster),
                          main = "",
                          ggtheme = ggplot2::theme_bw())
 
-dev.off()
-
 aggregate(cbind(precision, generalizability, nvariants, duration, distance,
                 scaleSize , rotationDegree, npaths, ncases, nmoves,
                 nflipCard, nopenTopic, nopenPopup) ~ cluster, datitem,
@@ -138,18 +126,6 @@ item <- sprintf("%03d", as.numeric(gsub("item_([0-9]{3})", "\\1",
 res <- merge(dat, data.frame(item, cluster), by = "item", all.x = TRUE)
 res <- res[order(res$fileId.start, res$date.start, res$timeMs.start), ]
 
-# 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/haum/eventlogs_pre-corona_item-clusters.csv",
-            sep = ";",
-            quote = FALSE,
-            row.names = FALSE)
 
 # DFGs for clusters
 res$start <- res$date.start
@@ -163,63 +139,30 @@ for (clst in sort(unique(res$cluster))) {
     resource_id = "item",
     timestamps  = c("start", "complete"))
 
-  dfg <- processmapR::process_map(alog,
+  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",
+    rankdir    = "LR")
-    render     = FALSE)
-
-  processmapR::export_map(dfg,
-    file_name = paste0("results/processmaps/dfg_cluster", clst, "_R.pdf"),
-    file_type = "pdf",
-    title     = paste("DFG Cluster", clst))
 }
 
-#--------------- (3) Visualization with pictures ---------------
 
-coor_2d <- cmdscale(dist_mat, k = 2)
+# 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)
 
-items <- sprintf("%03d", as.numeric(rownames(datitem)))
+write.table(res,
+            file = "results/eventlogs_pre-corona_item-clusters.csv",
+            sep = ";",
+            quote = FALSE,
+            row.names = FALSE)
 
-pdf("results/figures/clustering_artworks.pdf", height = 8, width = 8, pointsize = 16)
+# Save data for plots and tables
-#png("results/figures/clustering_artworks.png", units = "in", height = 8, width = 8, pointsize = 16, res = 300)
 
-par(mai = c(.6,.6,.1,.1), mgp = c(2.4, 1, 0))
+save(hc, k, res, dist_mat, datitem, df,
-
+     file = "../../thesis/figures/data/clustering_items.RData")
-plot(coor_2d, type = "n", ylim = c(-3.7, 2.6), xlim = c(-5, 10.5),
-     xlab = "", ylab = "")
-
-for (item in items) {
-
-  if (item == "125") {
-
-    pic <- jpeg::readJPEG(paste0("../data/haum/ContentEyevisit/eyevisit_cards_light/",
-                          item, "/", item, ".jpg"))
-  } else {
-    pic <- png::readPNG(paste0("../data/haum/ContentEyevisit/eyevisit_cards_light/",
-                        item, "/", item, ".png"))
-  }
-
-  img <- as.raster(pic[,,1:3])
-
-  x <- coor_2d[items == item, 1]
-  y <- coor_2d[items == item, 2]
-
-  points(x, y,
-         col = mycols[cluster[items == item]],
-         cex = 6,
-         pch = 15)
-
-  rasterImage(img,
-              xleft = x - .45,
-              xright = x + .45,
-              ybottom = y - .2,
-              ytop = y + .2)
-
-}
-legend("topright", paste("Cluster", 1:k), col = mycols, pch = 15, bty = "n")
-
-dev.off()
 

code/08_case-characteristics.R

@@ -5,10 +5,11 @@
 #          (3) Select features for navigation behavior
 #          (4) Export data frames
 #
-# 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: results/dataframes_case_2019.RData
+#         results/centrality_cases.RData
 #
-# last mod: 2024-03-08
+# last mod: 2024-03-22
 
 # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
 
@@ -16,7 +17,7 @@ source("R_helpers.R")
 
 #--------------- (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
 dat <- dat[as.Date(dat$date.start) > "2018-12-31" &
@@ -135,8 +136,8 @@ dattree <- data.frame(case = datcase$case,
 )
 
 # centrality <- pbapply::pbsapply(dattree$case, get_centrality, data = dat)
-# save(centrality, file = "results/haum/tmp_centrality.RData")
+# save(centrality, file = "results/centrality_cases.RData")
-load("results/haum/tmp_centrality.RData")
+load("results/centrality_cases.RData")
 
 dattree$BetweenCentrality <- centrality
 
@@ -171,17 +172,5 @@ dattree$AvDurItemNorm <- normalize(dattree$AvDurItem)
 
 #--------------- (4) Export data frames ---------------
 
-save(dat, datcase, dattree, file = "results/haum/dataframes_case_2019.RData")
+save(dat, datcase, dattree, file = "results/dataframes_case_2019.RData")
-
-write.table(datcase,
-            file = "results/haum/datcase.csv",
-            sep = ";",
-            quote = FALSE,
-            row.names = FALSE)
-
-write.table(datcase,
-            file = "results/haum/dattree.csv",
-            sep = ";",
-            quote = FALSE,
-            row.names = FALSE)
 

code/08_infos-clusters.py

@@ -1,45 +0,0 @@
-# 08_infos-clusters.py
-#
-# content: (1) Load data and create event log
-#          (2) Infos for clusters
-#          (3) Process maps for clusters
-#
-# input:  results/haum/eventlogs_pre-corona_item-clusters.csv
-# output: results/haum/pn_infos_clusters.csv
-#
-# last mod: 2024-03-06
-
-import pm4py
-import pandas as pd
-
-from python_helpers import eval_pm, pn_infos
-
-#--------------- (1) Load data and create event logs ---------------
-
-dat = pd.read_csv("results/haum/eventlogs_pre-corona_item-clusters.csv", sep = ";")
-
-log_path = pm4py.format_dataframe(dat, case_id = "path", activity_key = "event",
-                                  timestamp_key = "date.start")
-
-#--------------- (2) Infos for clusters ---------------
-
-# Merge clusters into data frame
-eval = pd.DataFrame(columns = ["fitness", "precision", "generalizability",
-                               "simplicity", "sound", "narcs", "ntrans",
-                               "nplaces", "nvariants", "mostfreq"])
-for cluster in log_path.grp.unique().tolist():
-    eval = pd.concat([eval, pn_infos(log_path, "grp", cluster)])
-eval = eval.sort_index()
-
-eval.to_csv("results/haum/pn_infos_clusters.csv", sep = ";")
-
-#--------------- (3) Process maps for clusters ---------------
-
-for cluster in log_path.grp.unique().tolist():
-    subdata = log_path[log_path.grp == cluster]
-    subnet, subim, subfm = pm4py.discover_petri_net_inductive(subdata, noise_threshold=0.5)
-    pm4py.save_vis_petri_net(subnet, subim, subfm,
-       "results/processmaps/petrinet_cluster" + str(cluster).zfill(3) + ".png")
-    bpmn = pm4py.convert.convert_to_bpmn(subnet, subim, subfm)
-    pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/bpmn_cluster_" +
-            str(cluster).zfill(3) + ".png")

code/09_user-navigation.R

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

code/10_validation.R

@@ -6,10 +6,10 @@
 #          (4) Clustering
 #          (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")
 
@@ -17,7 +17,7 @@ source("R_helpers.R")
 
 #--------------- (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
 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)
-# 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
 

code/11_investigate-variants.R

@@ -3,10 +3,11 @@
 # content: (1) Read data
 #          (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")
 
@@ -14,7 +15,7 @@ library(bupaverse)
 
 #--------------- (1) Read data ---------------
 
-load("results/haum/eventlogs_pre-corona_cleaned.RData")
+load("results/eventlogs_pre-corona_cleaned.RData")
 
 #--------------- (2) Investigate variants ---------------
 
@@ -27,7 +28,7 @@ alog <- activitylog(dat,
                     resource_id = "path",
                     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)
 # --> sequences of artworks are just too rare
 dev.off()
@@ -54,7 +55,7 @@ y <- as.numeric(tab)
 p1 <- lm(log(y) ~ log(x))
 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)
 par(mai = c(.6,.6,.1,.1), mgp = c(2.4, 1, 0))
 

code/12_dfgs-case-clusters.R

@@ -0,0 +1,93 @@
+# 13_dfgs-case-clusters.R
+#
+# content: (1) Read data
+#          (2) Export DFGs for clusters
+#
+# input:  results/user-navigation.RData
+# 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: 2024-03-22
+
+# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
+
+#--------------- (1) Read data ---------------
+
+load("results/user-navigation.RData")
+
+dat <- res
+
+dat$start <- as.POSIXct(dat$date.start)
+dat$complete <- as.POSIXct(dat$date.stop)
+
+alog <- bupaR::activitylog(dat[dat$cluster == cluster, ],
+                            case_id     = "case",
+                            activity_id = "item",
+                            resource_id = "path",
+                            timestamps  = c("start", "complete"))
+
+processmapR::trace_explorer(alog, n_traces = 25)
+
+tr <- bupaR::traces(alog)
+tab <- table(tr$absolute_frequency)
+
+tab[1] / nrow(tr)
+
+alog |> edeaR::filter_infrequent_flows(min_n = 20) |> processmapR::process_map()
+
+#--------------- (2) Export DFGs for clusters ---------------
+
+mycols <- c("#3CB4DC", "#FF6900", "#78004B", "#91C86E", "#434F4F")
+cl_names <- c("Scanning", "Exploring", "Flitting", "Searching", "Info")
+
+ns <- c(30, 20, 10, 5, 30)
+
+for (i in 1:5) {
+
+  alog <- bupaR::activitylog(dat[dat$cluster == i, ],
+                             case_id     = "case",
+                             activity_id = "item",
+                             resource_id = "path",
+                             timestamps  = c("start", "complete"))
+  
+  dfg <- processmapR::process_map(edeaR::filter_infrequent_flows(alog, min_n = ns[i]),
+    type_nodes = processmapR::frequency("relative", color_scale = "Greys"),
+    sec_nodes  = processmapR::frequency("absolute"),
+    type_edges = processmapR::frequency("relative", color_edges = mycols[i]),
+    sec_edges  = processmapR::frequency("absolute"),
+    rankdir    = "LR",
+    render     = FALSE)
+
+  processmapR::export_map(dfg,
+    file_name = paste0("../../thesis/figures/dfg_cases_cluster", i, "_R.pdf"),
+    file_type = "pdf",
+    title     = cl_names[i])
+}
+
+# cluster 1: 50
+# cluster 2: 30 o. 20
+# cluster 3: 20 - 30
+# cluster 4: 5
+# cluster 5: 20
+
+get_percent_variants <- function(log, cluster, min_n) {
+
+  alog <- bupaR::activitylog(log[log$cluster == cluster, ],
+                             case_id     = "case",
+                             activity_id = "item",
+                             resource_id = "path",
+                             timestamps  = c("start", "complete"))
+
+  nrow(edeaR::filter_infrequent_flows(alog, min_n = min_n)) /
+    nrow(alog)
+}
+
+perc <- numeric(5)
+
+for (i in 1:5) {
+  perc[i] <- get_percent_variants(log = dat, cluster = i, min_n = ns[i])
+}
+

code/13_pm-case-clusters.py

@@ -1,46 +0,0 @@
-# 12_pm-case-clusters.py
-#
-# content: (1) Load data and create event log
-#          (2) Infos for clusters
-#          (3) Process maps for clusters
-#
-# input:  results/haum/eventlogs_pre-corona_item-clusters.csv
-# output: results/haum/pn_infos_clusters.csv
-#
-# last mod: 2024-03-10
-
-import pm4py
-import pandas as pd
-
-from python_helpers import eval_pm, pn_infos
-
-#--------------- (1) Load data and create event logs ---------------
-
-dat = pd.read_csv("results/haum/eventlogs_2019_case-clusters_new.csv", sep = ";")
-
-event_log = pm4py.format_dataframe(dat, case_id = "case", activity_key = "event_new",
-                                  timestamp_key = "date.start")
-
-#--------------- (2) Infos for clusters ---------------
-
-# Merge clusters into data frame
-eval = pd.DataFrame(columns = ["fitness", "precision", "generalizability",
-                               "simplicity", "sound", "narcs", "ntrans",
-                               "nplaces", "nvariants", "mostfreq"])
-for cluster in event_log.cluster.unique().tolist():
-    eval = pd.concat([eval, pn_infos(event_log, "cluster", cluster)])
-eval = eval.sort_index()
-
-eval.to_csv("results/haum/pn_infos_clusters.csv", sep = ";")
-
-#--------------- (3) Process maps for clusters ---------------
-
-for cluster in event_log.cluster.unique().tolist():
-    subdata = event_log[event_log.cluster == cluster]
-    subnet, subim, subfm = pm4py.discover_petri_net_inductive(subdata, noise_threshold = .7)
-    pm4py.save_vis_petri_net(subnet, subim, subfm,
-       "results/processmaps/petrinet_cluster" + str(cluster) + "_cases.png")
-    bpmn = pm4py.convert.convert_to_bpmn(subnet, subim, subfm)
-    pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/bpmn_cluster" +
-            str(cluster) + "_cases.png")
-

code/python_helpers.py

@@ -36,8 +36,8 @@ def pn_infos_miner(log, miner):
         net, im, fm = pm4py.discover_petri_net_ilp(log)
     elif miner == "inductive":
         net, im, fm = pm4py.discover_petri_net_inductive(log)
-    elif miner == "conformative":
+    elif miner == "normative":
-        net, im, fm = pm4py.read_pnml("results/haum/conformative_petrinet_con.pnml")
+        net, im, fm = pm4py.read_pnml("results/normative_petrinet.pnml")
 
     eval = eval_append(log, net, im, fm)
     eval.index = [miner]