From 42cb777d36299e93988bc2bcbba01483d7da1cb4 Mon Sep 17 00:00:00 2001
From: nwickel <n.wickelmaier@iwm-tuebingen.de>
Date: Wed, 27 Mar 2024 10:07:36 +0100
Subject: [PATCH] Updated DFGs for case clusters; exported data for tables

---
 code/12_dfgs-case-clusters.R | 36 ++++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

diff --git a/code/12_dfgs-case-clusters.R b/code/12_dfgs-case-clusters.R
index 232b2c6..a5b2083 100644
--- a/code/12_dfgs-case-clusters.R
+++ b/code/12_dfgs-case-clusters.R
@@ -23,7 +23,7 @@ dat <- res
 dat$start <- as.POSIXct(dat$date.start)
 dat$complete <- as.POSIXct(dat$date.stop)
 
-alog <- bupaR::activitylog(dat[dat$cluster == cluster, ],
+alog <- bupaR::activitylog(dat[dat$cluster == 4, ],
                             case_id     = "case",
                             activity_id = "item",
                             resource_id = "path",
@@ -36,7 +36,7 @@ tab <- table(tr$absolute_frequency)
 
 tab[1] / nrow(tr)
 
-alog |> edeaR::filter_infrequent_flows(min_n = 20) |> processmapR::process_map()
+alog |> edeaR::filter_infrequent_flows(min_n = 5) |> processmapR::process_map()
 
 #--------------- (2) Export DFGs for clusters ---------------
 
@@ -44,6 +44,7 @@ mycols <- c("#3CB4DC", "#FF6900", "#78004B", "#91C86E", "#434F4F")
 cl_names <- c("Scanning", "Exploring", "Flitting", "Searching", "Info")
 
 ns <- c(30, 20, 10, 5, 30)
+#ns <- c(20, 20, 20, 5, 20)
 
 for (i in 1:5) {
 
@@ -52,7 +53,7 @@ for (i in 1:5) {
                              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"),
@@ -67,27 +68,30 @@ for (i in 1:5) {
     title     = cl_names[i])
 }
 
-# cluster 1: 50
-# cluster 2: 30 o. 20
-# cluster 3: 20 - 30
-# cluster 4: 5
-# cluster 5: 20
+# What data is used and how many traces are unique
 
-get_percent_variants <- function(log, cluster, min_n) {
+perc_filter <- numeric(5)
+perc_unqiue <- numeric(5)
 
-  alog <- bupaR::activitylog(log[log$cluster == cluster, ],
+for (i in 1:5) {
+
+  alog <- bupaR::activitylog(dat[dat$cluster == i, ],
                              case_id     = "case",
                              activity_id = "item",
                              resource_id = "path",
                              timestamps  = c("start", "complete"))
 
-  nrow(edeaR::filter_infrequent_flows(alog, min_n = min_n)) /
+  perc_filter[i] <- nrow(edeaR::filter_infrequent_flows(alog, min_n = ns[i])) /
     nrow(alog)
+
+  cs <- bupaR::cases(alog)
+  infreq_tr <- names(which(table(cs$trace) == 1))
+  infreq_cs <- cs$case[cs$trace %in% infreq_tr]
+
+  perc_unqiue[i] <- nrow(alog[alog$case %in% infreq_cs, ]) / nrow(alog)
+
 }
 
-perc <- numeric(5)
-
-for (i in 1:5) {
-  perc[i] <- get_percent_variants(log = dat, cluster = i, min_n = ns[i])
-}
+save(ns, perc_filter, perc_unqiue,
+     file = "../../thesis/figures/data/dfgs_case-cluster.RData")