2024-01-25 17:21:18 +01:00
|
|
|
import pm4py
|
|
|
|
import pandas as pd
|
|
|
|
import numpy as np
|
|
|
|
|
|
|
|
from python_helpers import eval_pm, pn_infos
|
|
|
|
|
|
|
|
###### Load data and create event logs ######
|
|
|
|
|
|
|
|
dat = pd.read_csv("results/haum/event_logfiles_2024-01-18_09-58-52.csv", sep = ";")
|
|
|
|
dat = dat[dat["date.start"] < "2020-03-13"]
|
|
|
|
# --> only pre corona (before artworks were updated)
|
2024-01-30 11:48:48 +01:00
|
|
|
dat = dat[dat["path"] != 106098]
|
|
|
|
# exclude broken trace
|
2024-01-25 17:21:18 +01:00
|
|
|
|
|
|
|
log_path = pm4py.format_dataframe(dat, case_id = "path", activity_key = "event",
|
|
|
|
timestamp_key = "date.start")
|
|
|
|
|
|
|
|
###### Infos for items ######
|
|
|
|
|
2024-01-30 11:48:48 +01:00
|
|
|
eval = pd.DataFrame(columns = ["fitness", "precision", "generalizability",
|
|
|
|
"simplicity", "sound", "narcs", "ntrans",
|
|
|
|
"nplaces", "nvariants", "mostfreq"])
|
2024-01-25 17:21:18 +01:00
|
|
|
for item in log_path.item.unique().tolist():
|
2024-01-30 11:48:48 +01:00
|
|
|
eval = pd.concat([eval, pn_infos(log_path, "item", item)])
|
|
|
|
eval = eval.sort_index()
|
2024-01-25 17:21:18 +01:00
|
|
|
|
|
|
|
# Export
|
2024-01-30 11:48:48 +01:00
|
|
|
eval.to_csv("results/haum/pn_infos_items.csv", sep = ";")
|