'''
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 enum import Enum
from typing import Dict, Optional, Any, List, Union
import pandas as pd
from pm4py.statistics.overlap.utils import compute
from pm4py.util import exec_utils, constants, xes_constants
[docs]class Parameters(Enum):
TIMESTAMP_KEY = constants.PARAMETER_CONSTANT_TIMESTAMP_KEY
START_TIMESTAMP_KEY = constants.PARAMETER_CONSTANT_START_TIMESTAMP_KEY
CASE_ID_KEY = constants.PARAMETER_CONSTANT_CASEID_KEY
[docs]def apply(df: pd.DataFrame, parameters: Optional[Dict[Union[str, Parameters], Any]] = None) -> List[int]:
"""
Computes the case overlap statistic from a Pandas dataframe
Parameters
-----------------
df
Dataframe
parameters
Parameters of the algorithm, including:
- Parameters.TIMESTAMP_KEY => attribute representing the completion timestamp
- Parameters.START_TIMESTAMP_KEY => attribute representing the start timestamp
Returns
----------------
case_overlap
List associating to each case the number of open cases during the life of a case
"""
if parameters is None:
parameters = {}
timestamp_key = exec_utils.get_param_value(Parameters.TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
start_timestamp_key = exec_utils.get_param_value(Parameters.START_TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
case_id_key = exec_utils.get_param_value(Parameters.CASE_ID_KEY, parameters, constants.CASE_CONCEPT_NAME)
columns = list({timestamp_key, start_timestamp_key, case_id_key})
stream = df[columns].to_dict('records')
points = []
cases = []
cases_points = {}
for event in stream:
case_id = event[case_id_key]
if case_id not in cases:
cases.append(case_id)
cases_points[case_id] = []
cases_points[case_id].append((event[start_timestamp_key].timestamp(), event[timestamp_key].timestamp()))
for case in cases:
case_points = cases_points[case]
points.append((min(x[0] for x in case_points), max(x[1] for x in case_points)))
return compute.apply(points, parameters=parameters)