Source code for pm4py.statistics.eventually_follows.pandas.get

'''
    PM4Py – A Process Mining Library for Python
Copyright (C) 2024 Process Intelligence Solutions UG (haftungsbeschränkt)

This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as
published by the Free Software Foundation, either version 3 of the
License, or any later version.

This program 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 Affero General Public License for more details.

You should have received a copy of the GNU Affero General Public License
along with this program.  If not, see this software project's root or
visit <https://www.gnu.org/licenses/>.

Website: https://processintelligence.solutions
Contact: info@processintelligence.solutions
'''
from enum import Enum

from pm4py.algo.discovery.dfg.adapters.pandas.df_statistics import get_partial_order_dataframe
from pm4py.util import exec_utils, constants, xes_constants
from typing import Optional, Dict, Any, Union, Tuple
import pandas as pd




[docs]
class Parameters(Enum):
    ACTIVITY_KEY = constants.PARAMETER_CONSTANT_ACTIVITY_KEY
    CASE_ID_KEY = constants.PARAMETER_CONSTANT_CASEID_KEY
    TIMESTAMP_KEY = constants.PARAMETER_CONSTANT_TIMESTAMP_KEY
    START_TIMESTAMP_KEY = constants.PARAMETER_CONSTANT_START_TIMESTAMP_KEY
    KEEP_FIRST_FOLLOWING = "keep_first_following"






[docs]
def apply(dataframe: pd.DataFrame, parameters: Optional[Dict[Union[str, Parameters], Any]] = None) -> Dict[Tuple[str, str], int]:
    if parameters is None:
        parameters = {}

    if parameters is None:
        parameters = {}

    activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes_constants.DEFAULT_NAME_KEY)
    case_id_glue = exec_utils.get_param_value(Parameters.CASE_ID_KEY, parameters, constants.CASE_CONCEPT_NAME)
    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, None)
    keep_first_following = exec_utils.get_param_value(Parameters.KEEP_FIRST_FOLLOWING, parameters, False)

    partial_order_dataframe = get_partial_order_dataframe(dataframe, start_timestamp_key=start_timestamp_key,
                                                          timestamp_key=timestamp_key, case_id_glue=case_id_glue,
                                                          activity_key=activity_key,
                                                          keep_first_following=keep_first_following)

    ret_dict = partial_order_dataframe.groupby([activity_key, activity_key + '_2']).size().to_dict()

    # assure to avoid problems with np.float64, by using the Python float type
    for el in ret_dict:
        ret_dict[el] = int(ret_dict[el])

    return ret_dict