From b50f52dc6c4b0ce39e9d97e1b4db01db1f4a40d6 Mon Sep 17 00:00:00 2001
From: nwickel <n.wickelmaier@iwm-tuebingen.de>
Date: Tue, 19 Mar 2024 18:15:16 +0100
Subject: [PATCH] Next try for extracting process maps for case clusters

---
 code/05_check-traces.R       |  2 +-
 code/07_item-clustering.R    |  4 +-
 code/13_dfgs-case-clusters.R | 96 ++++++++++++++++++++++++++++++++++++
 3 files changed, 99 insertions(+), 3 deletions(-)
 create mode 100644 code/13_dfgs-case-clusters.R

diff --git a/code/05_check-traces.R b/code/05_check-traces.R
index 2e37f7e..2e6fb33 100644
--- a/code/05_check-traces.R
+++ b/code/05_check-traces.R
@@ -84,7 +84,7 @@ dfg <- processmapR::process_map(alog,
   render     = FALSE)
 
 processmapR::export_map(dfg,
-  file_name = paste0("results/processmaps/dfg_complete_R.pdf"),
+  file_name = paste0("results/processmaps/dfg_complete_WFnet_R.pdf"),
   file_type = "pdf")
 
 rm(tmp)
diff --git a/code/07_item-clustering.R b/code/07_item-clustering.R
index ddbea13..bd0e37a 100644
--- a/code/07_item-clustering.R
+++ b/code/07_item-clustering.R
@@ -172,9 +172,9 @@ for (clst in sort(unique(res$cluster))) {
     render     = FALSE)
 
   processmapR::export_map(dfg,
-    file_name = paste0("results/processmaps/dfg_cluster", clst, "_R.pdf"),
+    file_name = paste0("results/processmaps/dfg_items_cluster", clst, "_R.pdf"),
     file_type = "pdf",
-    title     = paste("DFG Cluster", clst))
+    title     = paste("Cluster", clst))
 }
 
 #--------------- (3) Visualization with pictures ---------------
diff --git a/code/13_dfgs-case-clusters.R b/code/13_dfgs-case-clusters.R
new file mode 100644
index 0000000..038edb5
--- /dev/null
+++ b/code/13_dfgs-case-clusters.R
@@ -0,0 +1,96 @@
+# 13_dfgs-case-clusters.R
+#
+# content: 
+#
+# input:  results/haum/tmp_user-navigation.RData
+# output: 
+#
+# last mod: 2024-03-19
+
+# setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
+
+load("results/haum/tmp_user-navigation.RData")
+
+#dat <- read.table("results/haum/eventlogs_2019_case-clusters.csv", header = TRUE, sep = ";")
+
+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()
+
+
+
+
+## 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$cluster == i, ],
+                             case_id     = "case",
+                             activity_id = "item",
+                             resource_id = "path",
+                             timestamps  = c("start", "complete"))
+  
+  dfg <- processmapR::process_map(edeaR::filter_infrequent_flows(alog, min_n = ns[i]),
+    type_nodes = processmapR::frequency("relative", color_scale = "Greys"),
+    sec_nodes  = processmapR::frequency("absolute"),
+    type_edges = processmapR::frequency("relative", color_edges = mycols[i]),
+    sec_edges  = processmapR::frequency("absolute"),
+    rankdir    = "LR",
+    render     = FALSE)
+
+  processmapR::export_map(dfg,
+    file_name = paste0("results/processmaps/dfg_cases_cluster", i, "_R.pdf"),
+    file_type = "pdf",
+    title     = cl_names[i])
+}
+
+
+# cluster 1: 50
+# cluster 2: 30 o. 20
+# cluster 3: 20 - 30
+# cluster 4: 5
+# cluster 5: 20
+
+get_percent_variants <- function(log, cluster, min_n) {
+
+  alog <- bupaR::activitylog(log[log$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])
+}
+