- Filtering: -
- Used Columns: -
"""
from eval.evaluation import run_experiment
from grm import preprocessing
from pm4py.algo.filtering.log.attributes import attributes_filter
log_file = "bpi2017.csv"
name_of_case_id = "Case ID"
name_of_activity = "Activity"
name_of_timestamp = "Complete Timestamp"
name_of_label = "Accepted"
hyper_params = {'num_epochs': 1000}
k = 10
log = preprocessing.import_data("../data", log_file, separator=";", quote='', case_id=name_of_case_id,
activity=name_of_activity,
time_stamp=name_of_timestamp, target=name_of_label)
activities = attributes_filter.get_attribute_values(log, "concept:name")
# filter out activities representing work items
w_activities = [i for i in activities.keys() if i.startswith('W_')]
log_filtered = attributes_filter.apply_events(log, w_activities, parameters={
attributes_filter.PARAMETER_CONSTANT_ATTRIBUTE_KEY: "concept:name", "positive": True})
run_experiment(log, hyper_params=hyper_params, k=k, ml_flow_run_name_prefix=log_file)
from grm import preprocessing
import eval.baselines.evaluation as evaluation
import os
predictor = "XG"
log_file = "clickstream_anon.csv"
name_of_case_id = "CASE_KEY"
name_of_activity = "ACTIVITY"
name_of_timestamp = "EVENTTIMESTAMP"
name_of_label = "EXCEPTION"
log = preprocessing.import_data(os.path.normpath("../../../data"),
log_file,
separator=",",
quote='"',
case_id=name_of_case_id,
activity=name_of_activity,
time_stamp=name_of_timestamp,
target=name_of_label)
evaluation.run_cross_validation(log,
predictor,
name_of_activity,
k=10,
ml_flow_run_name_prefix=log_file)
from grm import GRM, preprocessing
from pm4py.objects.log.util import sampling
# import data
data_raw = preprocessing.import_data("data",
"BPI2020_PermitLog.csv",
separator=";",
quote='',
case_id="Case ID",
activity="Activity",
time_stamp="Complete Timestamp",
target="(case) Overspent")
# Create new GRM model object
hyper_params = {'num_epochs': 1}
grm_model = GRM.GRM(data_raw, params=hyper_params)
# Train GGNN model
grm_model.train()
# Evaluation of the GGNN model
evaluation_metrics = grm_model.testing_log()
print(evaluation_metrics)
# Visualization as DFG (with sample of evaluation data)
multi_instance_log = sampling.sample(data_raw, n=100)
grm_model.visualize_dfg(save_file=False,
log=multi_instance_log,
file_name="multi")
