Source code for pm4py.statistics.passed_time.pandas.variants.pre

'''
    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 pm4py.util.xes_constants import DEFAULT_NAME_KEY, DEFAULT_TIMESTAMP_KEY
from pm4py.util.constants import CASE_CONCEPT_NAME
from pm4py.algo.discovery.dfg.adapters.pandas import df_statistics as pandas
from pm4py.util import exec_utils
from pm4py.util import constants
from enum import Enum
from typing import Optional, Dict, Any
import pandas as pd




class Parameters(Enum):
    ATTRIBUTE_KEY = constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY
    ACTIVITY_KEY = constants.PARAMETER_CONSTANT_ACTIVITY_KEY
    START_TIMESTAMP_KEY = constants.PARAMETER_CONSTANT_START_TIMESTAMP_KEY
    TIMESTAMP_KEY = constants.PARAMETER_CONSTANT_TIMESTAMP_KEY
    CASE_ID_KEY = constants.PARAMETER_CONSTANT_CASEID_KEY
    MAX_NO_POINTS_SAMPLE = "max_no_of_points_to_sample"
    KEEP_ONCE_PER_CASE = "keep_once_per_case"
    BUSINESS_HOURS = "business_hours"
    BUSINESS_HOUR_SLOTS = "business_hour_slots"
    WORKCALENDAR = "workcalendar"





def apply(
    df: pd.DataFrame,
    activity: str,
    parameters: Optional[Dict[Any, Any]] = None,
) -> Dict[str, Any]:
    """
    Gets the time passed from each preceding activity

    Parameters
    -------------
    df
        Dataframe
    activity
        Activity that we are considering
    parameters
        Possible parameters of the algorithm

    Returns
    -------------
    dictio
        Dictionary containing a 'pre' key with the
        list of aggregates times from each preceding activity to the given activity
    """
    if parameters is None:
        parameters = {}

    case_id_glue = exec_utils.get_param_value(
        Parameters.CASE_ID_KEY, parameters, CASE_CONCEPT_NAME
    )
    activity_key = exec_utils.get_param_value(
        Parameters.ACTIVITY_KEY, parameters, DEFAULT_NAME_KEY
    )
    timestamp_key = exec_utils.get_param_value(
        Parameters.TIMESTAMP_KEY, parameters, DEFAULT_TIMESTAMP_KEY
    )
    start_timestamp_key = exec_utils.get_param_value(
        Parameters.START_TIMESTAMP_KEY, parameters, None
    )

    business_hours = exec_utils.get_param_value(
        Parameters.BUSINESS_HOURS, parameters, False
    )
    business_hours_slots = exec_utils.get_param_value(
        Parameters.BUSINESS_HOUR_SLOTS,
        parameters,
        constants.DEFAULT_BUSINESS_HOUR_SLOTS,
    )

    workcalendar = exec_utils.get_param_value(
        Parameters.WORKCALENDAR,
        parameters,
        constants.DEFAULT_BUSINESS_HOURS_WORKCALENDAR,
    )

    [dfg_frequency, dfg_performance] = pandas.get_dfg_graph(
        df,
        measure="both",
        activity_key=activity_key,
        case_id_glue=case_id_glue,
        timestamp_key=timestamp_key,
        start_timestamp_key=start_timestamp_key,
        business_hours=business_hours,
        business_hours_slot=business_hours_slots,
        workcalendar=workcalendar,
    )

    pre = []
    sum_perf_pre = 0.0
    sum_acti_pre = 0.0

    for entry in dfg_performance.keys():
        if entry[1] == activity:
            pre.append(
                [
                    entry[0],
                    float(dfg_performance[entry]),
                    int(dfg_frequency[entry]),
                ]
            )
            sum_perf_pre = sum_perf_pre + float(
                dfg_performance[entry]
            ) * float(dfg_frequency[entry])
            sum_acti_pre = sum_acti_pre + float(dfg_frequency[entry])

    perf_acti_pre = 0.0
    if sum_acti_pre > 0:
        perf_acti_pre = sum_perf_pre / sum_acti_pre

    return {"pre": pre, "pre_avg_perf": perf_acti_pre}