# 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: 2024-04-04

import pm4py
import pandas as pd

from python_helpers import eval_pm, eval_append

#--------------- (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 = [0.0, 0.1, 0.2, 0.3, 0.4]

for nt in thresholds:

    net, im, fm = pm4py.discover_petri_net_inductive(event_log, noise_threshold = nt)

    eval = eval_append(event_log, net, im, fm)

    # Export process maps
    pm4py.save_vis_petri_net(net, im, fm, "results/processmaps/petrinet_complete_cases" + str(int(nt*10)).zfill(2) + ".png")
    bpmn = pm4py.convert.convert_to_bpmn(net, im, fm)
    pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/bpmn_complete_cases" + str(int(nt*10)).zfill(2) + ".png")

    # 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 = eval_append(log_clst, net_clst, im_clst, fm_clst)
        eval = pd.concat([eval, eval_clst])
        # Export process maps
        pm4py.save_vis_petri_net(net_clst, im_clst, fm_clst, "results/processmaps/petrinet_cluster" + str(cluster) + "_cases" + str(int(nt*10)).zfill(2) + ".png")
        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 = ";")