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

Added python script for PM for case clusters (again)

Browse Source
This commit is contained in:
Nora Wickelmaier 2024-04-02 21:29:37 +02:00
parent 609e103018
commit dc489b4aa9
2 changed files with 59 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
code/13_pm-case-clusters.py Normal file
View File

@ -0,0 +1,52 @@
# 13_pm-case-clusters.py
#
# content: (1) Load data and create event log
# (2) Evaluation for clusters
#
# input: results/eventlogs_2019_case-clusters.csv
# output: results/eval_case_clusters.csv
#
# last mod: 2024-04-02
import pm4py
import pandas as pd
from python_helpers import eval_pm
#--------------- (1) Load data and create event logs ---------------
dat = pd.read_csv("results/eventlogs_2019_case-clusters.csv", sep = ";")
event_log = pm4py.format_dataframe(dat,
case_id = "case",
activity_key = "item",
timestamp_key = "date.start")
#--------------- (2) Evaluation for clusters ---------------
thresholds = [0.1, 0.2, 0.3, 0.4, 0.5]
for nt in thresholds:
net, im, fm = pm4py.discover_petri_net_inductive(event_log, noise_threshold = nt)
eval = pd.DataFrame(eval_pm(event_log, net, im, fm)).T
eval.columns = ["fitness", "generalization", "simplicity"]
#eval.columns = ["fitness", "precision", "generalization", "simplicity"]
# Merge clusters into data frame
for cluster in [1, 2, 3, 4, 5]:
log_clst = pm4py.filter_event_attribute_values(event_log, "cluster", [cluster])
net_clst, im_clst, fm_clst = pm4py.discover_petri_net_inductive(log_clst, noise_threshold = nt)
eval_clst = pd.DataFrame(eval_pm(log_clst, net_clst, im_clst, fm_clst)).T
eval_clst.columns = ["fitness", "generalization", "simplicity"]
#eval_clst.columns = ["fitness", "precision", "generalization", "simplicity"]
eval = pd.concat([eval, eval_clst])
# Export process maps
bpmn = pm4py.convert.convert_to_bpmn(net_clst, im_clst, fm_clst)
pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/bpmn_cluster" + str(cluster) +
"_cases" + str(int(nt*10)).zfill(2) + ".png")
eval.index = ["Complete", "Cluster 1", "Cluster 2", "Cluster 3", "Cluster 4", "Cluster 5"]
eval.to_csv("results/eval_case_clusters_" + str(int(nt*10)).zfill(2) + ".csv", sep = ";")

9
code/python_helpers.py
View File

@ -5,12 +5,17 @@ import pandas as pd
def eval_pm(data, net, initial_marking, final_marking):
"""Caculate fitness, precision, generalizability, and simplicity for petri net"""
print("Fitness is calculated")
fitness = pm4py.fitness_token_based_replay(data, net, initial_marking, final_marking)
precisison = pm4py.precision_token_based_replay(data, net, initial_marking, final_marking)
#print("Precision is calculated")
#precisison = pm4py.precision_token_based_replay(data, net, initial_marking, final_marking)
print("Generalizability is calculated")
generalizability = pm4py.algo.evaluation.generalization.algorithm.apply(data, net,
initial_marking, final_marking)
print("Simplicity is calculated")
simplicity = pm4py.algo.evaluation.simplicity.algorithm.apply(net)
return [fitness['average_trace_fitness'], precisison, generalizability, simplicity]
#return [fitness['average_trace_fitness'], precisison, generalizability, simplicity]
return [fitness['average_trace_fitness'], generalizability, simplicity]
def pn_infos(log, colname, filter):