This file is part of PM4Py (More Info: https://pm4py.fit.fraunhofer.de).
PM4Py is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
PM4Py is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with PM4Py. If not, see <https://www.gnu.org/licenses/>.
from pm4py.objects.log.obj import EventLog
from typing import Tuple
[docs]def split(log: EventLog, train_percentage: float = 0.8) -> Tuple[EventLog, EventLog]:
Split an event log in a training log and a test log (for machine learning purposes)
Fraction of traces to be included in the training log (from 0.0 to 1.0)
Training event log
Test event log
idxs = [i for i in range(len(log))]
stop_idx = math.floor(len(idxs) * train_percentage) + 1
idxs_train = idxs[:stop_idx]
idxs_test = idxs[stop_idx:]
train_log = EventLog(list(), attributes=log.attributes, extensions=log.extensions, classifiers=log.classifiers,
test_log = EventLog(list(), attributes=log.attributes, extensions=log.extensions, classifiers=log.classifiers,
for idx in idxs_train:
for idx in idxs_test:
return train_log, test_log