'''
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.util.constants import CASE_CONCEPT_NAME
from pm4py.util.xes_constants import DEFAULT_NAME_KEY
from pm4py.util.constants import GROUPED_DATAFRAME
from pm4py.util import exec_utils
from pm4py.util import constants
from enum import Enum
from typing import Optional, Dict, Any, Union, Tuple, List, Set
import pandas as pd
[docs]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"
[docs]def get_end_activities(df: pd.DataFrame, parameters: Optional[Dict[Union[str, Parameters], Any]] = None) -> Dict[str, int]:
"""
Get end activities count
Parameters
-----------
df
Pandas dataframe
parameters
Parameters of the algorithm, including:
Parameters.CASE_ID_KEY -> Case ID column in the dataframe
Parameters.ACTIVITY_KEY -> Column that represents the activity
Returns
-----------
endact_dict
Dictionary of end activities along with their count
"""
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)
grouped_df = parameters[GROUPED_DATAFRAME] if GROUPED_DATAFRAME in parameters else None
if grouped_df is None:
grouped_df = df.groupby(case_id_glue, sort=False)
endact_dict = dict(grouped_df[activity_key].last().value_counts())
return endact_dict