mtt_haum/code/06_infos-items.py

# 06_infos-items.py
#
# content: (1) Load data and create event log
#          (2) Infos for items
#
# input:  results/eventlogs_pre-corona_cleaned.csv
# output: results/pn_infos_items.csv
#
# last mod: 2024-03-22

import pm4py
import pandas as pd
import numpy as np

from python_helpers import eval_pm, pn_infos

#--------------- (1) Load data and create event logs ---------------

dat = pd.read_csv("results/eventlogs_pre-corona_cleaned", sep = ";")

log_path = pm4py.format_dataframe(dat, case_id = "path", activity_key = "event",
                                  timestamp_key = "date.start")

#--------------- (2) Infos for items ---------------

eval = pd.DataFrame(columns = ["fitness", "precision", "generalizability",
                               "simplicity", "sound", "narcs", "ntrans",
                               "nplaces", "nvariants", "mostfreq"])

for item in log_path.item.unique().tolist():
    eval = pd.concat([eval, pn_infos(log_path, "item", item)])

eval = eval.sort_index()

# Export
eval.to_csv("results/pn_infos_items.csv", sep = ";")