%reset

import pm4py
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

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"]
dat = dat[dat["path"] != 106098]       # exclude broken trace
# --> only pre corona (before artworks were updated)

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


###### Infos for items ######

mdi = pd.DataFrame(columns = ["fitness", "precision", "generalizability",
                              "simplicity", "sound", "narcs", "ntrans",
                              "nplaces", "nvariants", "mostfreq"])
for item in log_path.item.unique().tolist():
    mdi = pd.concat([mdi, pn_infos(log_path, "item", item)])
mdi = mdi.sort_index()

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

# datitem = dat.groupby("item")[["duration", "distance",
#                                "scaleSize", "rotationDegree"]].mean()
# 
# def length_path(data):
#     x = data.path
#     return len(x.unique())
# def length_case(data):
#     x = data.case
#     return len(x.unique())
# def length_topic(data):
#     x = data.topic.dropna()
#     return len(x.unique())
# 
# datitem["npaths"] = dat.groupby(["item"]).apply(length_path)
# datitem["ncases"] = dat.groupby(["item"]).apply(length_case)
# datitem["ntopics"] = dat.groupby(["item"]).apply(length_topic)
# 
# datitem.index = datitem.index.astype(str).str.rjust(3, "0")
# datitem = datitem.sort_index()
# datitem.index = mdi.index
# 
# datitem = pd.concat([mdi, datitem], yaxis = 1)