def apply(log, parameters=None):
"""
Apply the IMDF algorithm to a log obtaining a Petri net along with an initial and final marking
Parameters
-----------
log
Log
parameters
Parameters of the algorithm, including:
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY -> attribute of the log to use as activity name
(default concept:name)
Returns
-----------
net
Petri net
initial_marking
Initial marking
final_marking
Final marking
"""
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_util.DEFAULT_TIMESTAMP_KEY
if pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_CASEID_KEY] = pmutil.constants.CASE_ATTRIBUTE_GLUE
if isinstance(log, pandas.core.frame.DataFrame):
dfg = df_statistics.get_dfg_graph(
log,
case_id_glue=parameters[
pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY],
activity_key=parameters[
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY],
timestamp_key=parameters[
pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY])
start_activities = pd_start_act_stats.get_start_activities(
log, parameters=parameters)
end_activities = pd_end_act_stats.get_end_activities(
log, parameters=parameters)
activities = pd_attributes_stats.get_attribute_values(
log,
parameters[pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY],
parameters=parameters)
return apply_dfg(dfg,
activities=activities,
start_activities=start_activities,
end_activities=end_activities,
parameters=parameters)
log = log_conversion.apply(log, parameters, log_conversion.TO_EVENT_LOG)
tree = apply_tree(log, parameters=parameters)
net, initial_marking, final_marking = tree_to_petri.apply(tree)
return net, initial_marking, final_marking
def test_get_attributes(self):
from pm4py.statistics.attributes.pandas import get
df = self.get_dataframe()
get.get_attribute_values(df, "concept:name")
get.get_kde_date_attribute(df, "time:timestamp")
get.get_kde_numeric_attribute(df, "amount")
def discover_abstraction_dataframe(
df: pd.DataFrame,
parameters: Optional[Dict[Any, Any]] = None
) -> Tuple[Any, Any, Any, Any, Any, Any, Any]:
"""
Discovers an abstraction from a dataframe that is useful for the Heuristics Miner ++ algorithm
Parameters
--------------
df
Dataframe
parameters
Parameters of the algorithm, including:
- Parameters.ACTIVITY_KEY
- Parameters.START_TIMESTAMP_KEY
- Parameters.TIMESTAMP_KEY
- Parameters.CASE_ID_KEY
Returns
--------------
start_activities
Start activities
end_activities
End activities
activities_occurrences
Activities along with their number of occurrences
dfg
Directly-follows graph
performance_dfg
(Performance) Directly-follows graph
sojourn_time
Sojourn time for each activity
concurrent_activities
Concurrent activities
"""
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters, xes.DEFAULT_NAME_KEY)
start_timestamp_key = exec_utils.get_param_value(
Parameters.START_TIMESTAMP_KEY, parameters, None)
if start_timestamp_key is None:
start_timestamp_key = xes.DEFAULT_START_TIMESTAMP_KEY
parameters = copy(parameters)
parameters[Parameters.START_TIMESTAMP_KEY] = start_timestamp_key
timestamp_key = exec_utils.get_param_value(Parameters.TIMESTAMP_KEY,
parameters,
xes.DEFAULT_TIMESTAMP_KEY)
case_id_glue = exec_utils.get_param_value(Parameters.CASE_ID_KEY,
parameters,
constants.CASE_CONCEPT_NAME)
start_activities = pd_sa.get_start_activities(df, parameters=parameters)
end_activities = pd_ea.get_end_activities(df, parameters=parameters)
activities_occurrences = pd_attributes.get_attribute_values(
df, activity_key, parameters=parameters)
efg_parameters = copy(parameters)
efg_parameters[pd_efg.Parameters.KEEP_FIRST_FOLLOWING] = True
dfg = pd_efg.apply(df, parameters=efg_parameters)
performance_dfg = df_statistics.get_dfg_graph(
df,
case_id_glue=case_id_glue,
activity_key=activity_key,
timestamp_key=timestamp_key,
start_timestamp_key=start_timestamp_key,
measure="performance")
sojourn_time = pd_soj_time.apply(df, parameters=parameters)
concurrent_activities = pd_conc_act.apply(df, parameters=parameters)
return (start_activities, end_activities, activities_occurrences, dfg,
performance_dfg, sojourn_time, concurrent_activities)