def apply_auto_filter(df, parameters=None):
"""
Apply auto filter on end activities
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
Parameters.DECREASING_FACTOR -> Decreasing factor that should be passed to the algorithm
Returns
-----------
df
Filtered dataframe
"""
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 = exec_utils.get_param_value(Parameters.GROUP_DATAFRAME, parameters, None)
decreasing_factor = exec_utils.get_param_value(Parameters.DECREASING_FACTOR, parameters,
filtering_constants.DECREASING_FACTOR)
start_activities = get_start_activities(df, parameters=parameters)
salist = start_activities_common.get_sorted_start_activities_list(start_activities)
sathreshold = start_activities_common.get_start_activities_threshold(salist, decreasing_factor)
return filter_df_on_start_activities_nocc(df, sathreshold, sa_count0=start_activities, case_id_glue=case_id_glue,
activity_key=activity_key, grouped_df=grouped_df)
def apply_auto_filter(log, variants=None, parameters=None):
"""
Apply an end attributes filter detecting automatically a percentage
Parameters
----------
log
Log
variants
(If specified) Dictionary with variant as the key and the list of traces as the value
parameters
Parameters of the algorithm, including:
Parameters.DECREASING_FACTOR -> Decreasing factor (stops the algorithm when the next activity by occurrence is below
this factor in comparison to previous)
Parameters.ATTRIBUTE_KEY -> Attribute key (must be specified if different from concept:name)
Returns
---------
filtered_log
Filtered log
"""
if parameters is None:
parameters = {}
attribute_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters, DEFAULT_NAME_KEY)
decreasing_factor = exec_utils.get_param_value(
Parameters.DECREASING_FACTOR, parameters, DECREASING_FACTOR)
parameters_variants = {
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: attribute_key
}
if variants is None:
variants = variants_filter.get_variants(log,
parameters=parameters_variants)
vc = variants_filter.get_variants_sorted_by_count(variants)
start_activities = get_start_activities(log,
parameters=parameters_variants)
salist = start_activities_common.get_sorted_start_activities_list(
start_activities)
sathreshold = start_activities_common.get_start_activities_threshold(
salist, decreasing_factor)
filtered_log = filter_log_by_start_activities(start_activities, variants,
vc, sathreshold,
attribute_key)
return filtered_log
def apply_auto_filter(df, parameters=None):
"""
Apply auto filter on end activities
Parameters
-----------
df
Pandas dataframe
parameters
Parameters of the algorithm, including:
case_id_glue -> Case ID column in the dataframe
activity_key -> Column that represents the activity
decreasingFactor -> Decreasing factor that should be passed to the algorithm
Returns
-----------
df
Filtered dataframe
"""
if parameters is None:
parameters = {}
case_id_glue = parameters[
PARAMETER_CONSTANT_CASEID_KEY] if PARAMETER_CONSTANT_CASEID_KEY in parameters else CASE_CONCEPT_NAME
activity_key = parameters[
PARAMETER_CONSTANT_ACTIVITY_KEY] if PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else DEFAULT_NAME_KEY
decreasing_factor = parameters[
"decreasingFactor"] if "decreasingFactor" in parameters else filtering_constants.DECREASING_FACTOR
grouped_df = parameters[GROUPED_DATAFRAME] if GROUPED_DATAFRAME in parameters else None
start_activities = get_start_activities(df, parameters=parameters)
salist = start_activities_common.get_sorted_start_activities_list(start_activities)
sathreshold = start_activities_common.get_start_activities_threshold(salist, decreasing_factor)
return filter_df_on_start_activities_nocc(df, sathreshold, sa_count0=start_activities, case_id_glue=case_id_glue,
activity_key=activity_key, grouped_df=grouped_df)