def apply_auto_filter(log, variants=None, parameters=None):
"""
Apply an 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_skeleton
"""
if parameters is None:
parameters = {}
attribute_key = exec_utils.get_param_value(Parameters.ATTRIBUTE_KEY,
parameters, DEFAULT_NAME_KEY)
decreasing_factor = exec_utils.get_param_value(
Parameters.DECREASING_FACTOR, parameters,
filtering_constants.DECREASING_FACTOR)
parameters_variants = {
PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute_key,
PARAMETER_CONSTANT_ACTIVITY_KEY: attribute_key
}
if len(log) > 0:
if variants is None:
variants = variants_filter.get_variants(
log, parameters=parameters_variants)
vc = variants_filter.get_variants_sorted_by_count(variants)
attributes_values = get_attribute_values(
log, attribute_key, parameters=parameters_variants)
alist = attributes_common.get_sorted_attributes_list(attributes_values)
thresh = attributes_common.get_attributes_threshold(
alist, decreasing_factor)
filtered_log = filter_log_by_attributes_threshold(
log, attributes_values, variants, vc, thresh, attribute_key)
return filtered_log
return log
def apply_auto_filter(df, parameters=None):
"""
Apply auto filter on activity values
Parameters
------------
df
Dataframe
parameters
Possible parameters of the algorithm, including:
activity_key -> Column containing 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 = []
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 DECREASING_FACTOR
if len(df) > 0:
activities = get_attribute_values(df, activity_key)
alist = attributes_common.get_sorted_attributes_list(activities)
thresh = attributes_common.get_attributes_threshold(
alist, decreasing_factor)
return filter_df_keeping_activ_exc_thresh(
df,
thresh,
activity_key=activity_key,
act_count0=activities,
most_common_variant=most_common_variant)
return df