From 7eff903837d1000270d4911648215b59c6f4e51f Mon Sep 17 00:00:00 2001
From: nwickel <n.wickelmaier@iwm-tuebingen.de>
Date: Sun, 10 Mar 2024 17:50:09 +0100
Subject: [PATCH] Added script to check on process models for case clusters;
 not sure this makes sense

---
 code/12_pm-case-clusters.py | 45 +++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)
 create mode 100644 code/12_pm-case-clusters.py

diff --git a/code/12_pm-case-clusters.py b/code/12_pm-case-clusters.py
new file mode 100644
index 0000000..1634a9a
--- /dev/null
+++ b/code/12_pm-case-clusters.py
@@ -0,0 +1,45 @@
+# 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: 2024-03-06
+
+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_2019_case-clusters.csv", sep = ";")
+
+event_log = pm4py.format_dataframe(dat, case_id = "case", activity_key = "item",
+                                  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=.3)
+    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")