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 = {}
most_common_variant = parameters[PARAM_MOST_COMMON_VARIANT] if PARAM_MOST_COMMON_VARIANT in parameters else None
if most_common_variant is None:
most_common_variant = []
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
grouped_df = parameters[GROUPED_DATAFRAME] if GROUPED_DATAFRAME in parameters else None
return_dict = parameters[
RETURN_EA_COUNT_DICT_AUTOFILTER] if RETURN_EA_COUNT_DICT_AUTOFILTER in parameters else False
decreasing_factor = parameters[
"decreasingFactor"] if "decreasingFactor" in parameters else filtering_constants.DECREASING_FACTOR
if len(df) > 0:
end_activities = get_end_activities(df, parameters=parameters)
ealist = end_activities_common.get_sorted_end_activities_list(end_activities)
eathreshold = end_activities_common.get_end_activities_threshold(ealist, decreasing_factor)
return filter_df_on_end_activities_nocc(df, eathreshold, ea_count0=end_activities, case_id_glue=case_id_glue,
activity_key=activity_key, grouped_df=grouped_df, return_dict=return_dict,
most_common_variant=most_common_variant)
if return_dict:
return df, {}
return df
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)
return_dict = exec_utils.get_param_value(Parameters.RETURN_EA_COUNT, parameters, False)
decreasing_factor = exec_utils.get_param_value(Parameters.DECREASING_FACTOR, parameters,
filtering_constants.DECREASING_FACTOR)
most_common_variant = parameters[PARAM_MOST_COMMON_VARIANT] if PARAM_MOST_COMMON_VARIANT in parameters else None
if most_common_variant is None:
most_common_variant = []
if len(df) > 0:
end_activities = get_end_activities(df, parameters=parameters)
ealist = end_activities_common.get_sorted_end_activities_list(end_activities)
eathreshold = end_activities_common.get_end_activities_threshold(ealist, decreasing_factor)
return filter_df_on_end_activities_nocc(df, eathreshold, ea_count0=end_activities, case_id_glue=case_id_glue,
activity_key=activity_key, grouped_df=grouped_df,
return_dict=return_dict,
most_common_variant=most_common_variant)
if return_dict:
return df, {}
return 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:
decreasingFactor -> Decreasing factor (stops the algorithm when the next activity by occurrence is below
this factor in comparison to previous)
attribute_key -> Attribute key (must be specified if different from concept:name)
Returns
---------
filtered_log
Filtered log
"""
if parameters is None:
parameters = {}
attribute_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
if len(log) > 0:
parameters_variants = {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)
end_activities = get_end_activities(log,
parameters=parameters_variants)
ealist = end_activities_common.get_sorted_end_activities_list(
end_activities)
eathreshold = end_activities_common.get_end_activities_threshold(
ealist, decreasing_factor)
filtered_log = filter_log_by_end_activities(end_activities, variants,
vc, eathreshold,
attribute_key)
return filtered_log
return log
def apply_auto_filter(df, parameters=None):
"""Applies auto filter on end activities
"""
if parameters is None:
parameters = {}
most_common_variant = parameters[
PARAM_MOST_COMMON_VARIANT] if PARAM_MOST_COMMON_VARIANT in parameters else None
if most_common_variant is None:
most_common_variant = []
timestamp_key = parameters[
PARAMETER_CONSTANT_TIMESTAMP_KEY] if PARAMETER_CONSTANT_TIMESTAMP_KEY in parameters else DEFAULT_TIMESTAMP_KEY
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
grouped_df = parameters[
GROUPED_DATAFRAME] if GROUPED_DATAFRAME in parameters else None
return_dict = parameters[
RETURN_EA_COUNT_DICT_AUTOFILTER] if RETURN_EA_COUNT_DICT_AUTOFILTER in parameters else False
decreasing_factor = parameters[
"decreasingFactor"] if "decreasingFactor" in parameters else DECREASING_FACTOR
if df.count() > 0:
end_activities = get_end_activities(df, parameters=parameters)
ealist = end_activities_common.get_sorted_end_activities_list(
end_activities)
eathreshold = end_activities_common.get_end_activities_threshold(
ealist, decreasing_factor)
return filter_df_on_end_activities_nocc(
df,
eathreshold,
ea_count0=end_activities,
timestamp_key=timestamp_key,
case_id_glue=case_id_glue,
activity_key=activity_key,
grouped_df=grouped_df,
return_dict=return_dict,
most_common_variant=most_common_variant)
if return_dict:
return df, {}
return df
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
end_activities = get_end_activities(df, parameters=parameters)
ealist = end_activities_common.get_sorted_end_activities_list(
end_activities)
eathreshold = end_activities_common.get_end_activities_threshold(
ealist, decreasing_factor)
return filter_df_on_end_activities_nocc(df,
eathreshold,
ea_count=end_activities,
case_id_glue=case_id_glue,
activity_key=activity_key)