def test_37(self):
from pm4py.algo.filtering.pandas.attributes import attributes_filter
df = self.load_running_example_df()
filtered_df = attributes_filter.apply_auto_filter(df, parameters={
attributes_filter.Parameters.CASE_ID_KEY: "case:concept:name",
attributes_filter.Parameters.ATTRIBUTE_KEY: "concept:name",
attributes_filter.Parameters.DECREASING_FACTOR: 0.6})
def apply_auto_filter(log, parameters=None):
"""
Apply some filters in battery to the log_skeleton in order to get a simplified log_skeleton
Parameters
----------
log
Log
parameters
Eventual parameters applied to the algorithms:
Parameters.DECREASING_FACTOR -> Decreasing factor (provided to all algorithms)
Parameters.ACTIVITY_KEY -> Activity key (must be specified if different from concept:name)
Returns
---------
filtered_log
Filtered log_skeleton
"""
# the following filters are applied:
# - activity filter (keep only attributes with a reasonable number of occurrences) (if enabled)
# - variant filter (keep only variants with a reasonable number of occurrences) (if enabled)
# - start attributes filter (keep only variants that starts with a plausible start activity) (if enabled)
# - end attributes filter (keep only variants that starts with a plausible end activity) (if enabled)
if parameters is None:
parameters = {}
enable_activities_filter = exec_utils.get_param_value(Parameters.ENABLE_ACTIVITES_FILTER, parameters, True)
enable_variants_filter = exec_utils.get_param_value(Parameters.ENABLE_VARIANTS_FILTER, parameters, False)
enable_start_activities_filter = exec_utils.get_param_value(Parameters.ENABLE_START_ACTIVITIES_FILTER, parameters,
False)
enable_end_activities_filter = exec_utils.get_param_value(Parameters.ENABLE_END_ACTIVITIES_FILTER, parameters, True)
attribute_key = exec_utils.get_param_value(Parameters.ATTRIBUTE_KEY, parameters, xes.DEFAULT_NAME_KEY)
parameters[Parameters.ATTRIBUTE_KEY] = attribute_key
parameters[Parameters.ACTIVITY_KEY] = attribute_key
variants = variants_module.get_variants(log, parameters=parameters)
filtered_log = log
if enable_activities_filter:
filtered_log = attributes_filter.apply_auto_filter(log, variants=variants, parameters=parameters)
variants = variants_module.get_variants(filtered_log, parameters=parameters)
if enable_variants_filter:
filtered_log = variants_module.apply_auto_filter(filtered_log, variants=variants, parameters=parameters)
variants = variants_module.get_variants(filtered_log, parameters=parameters)
if enable_start_activities_filter:
filtered_log = start_activities_filter.apply_auto_filter(filtered_log, variants=variants,
parameters=parameters)
if enable_end_activities_filter:
filtered_log = end_activities_filter.apply_auto_filter(filtered_log, variants=variants,
parameters=parameters)
return filtered_log
def test_logfiltering_filtering1(self):
# to avoid static method warnings in tests,
# that by construction of the unittest package have to be expressed in such way
self.dummy_variable = "dummy_value"
input_log = os.path.join(INPUT_DATA_DIR, "running-example.xes")
log = xes_importer.import_log(input_log)
log = attributes_filter.apply_auto_filter(log)
log = variants_module.apply_auto_filter(log)
log = start_activities_filter.apply_auto_filter(log)
log = end_activities_filter.apply_auto_filter(log)
log = paths_filter.apply_auto_filter(log)
del log
def apply_auto_filter(log, parameters=None):
"""
Apply some filters in battery to the log in order to get a simplified log
Parameters
----------
log
Log
parameters
Eventual parameters applied to the algorithms:
decreasingFactor -> Decreasing factor (provided to all algorithms)
activity_key -> Activity key (must be specified if different from concept:name)
Returns
---------
filtered_log
Filtered log
"""
# the following filters are applied:
# - activity filter (keep only attributes with a reasonable number of occurrences) (if enabled)
# - variant filter (keep only variants with a reasonable number of occurrences) (if enabled)
# - start attributes filter (keep only variants that starts with a plausible start activity) (if enabled)
# - end attributes filter (keep only variants that starts with a plausible end activity) (if enabled)
if parameters is None:
parameters = {}
attribute_key = parameters[
PARAMETER_CONSTANT_ACTIVITY_KEY] if PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
decreasing_factor = parameters[
"decreasingFactor"] if "decreasingFactor" in parameters else filtering_constants.DECREASING_FACTOR
parameters_child = {
"decreasingFactor": decreasing_factor,
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: attribute_key,
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute_key
}
enable_activities_filter = parameters[
"enable_activities_filter"] if "enable_activities_filter" in parameters else True
enable_variants_filter = parameters[
"enable_variants_filter"] if "enable_variants_filter" in parameters else False
enable_start_activities_filter = parameters[
"enable_start_activities_filter"] if "enable_start_activities_filter" in parameters else False
enable_end_activities_filter = parameters[
"enable_end_activities_filter"] if "enable_end_activities_filter" in parameters else True
variants = variants_module.get_variants(log, parameters=parameters_child)
filtered_log = log
if enable_activities_filter:
filtered_log = attributes_filter.apply_auto_filter(
log, variants=variants, parameters=parameters_child)
variants = variants_module.get_variants(filtered_log,
parameters=parameters_child)
if enable_variants_filter:
filtered_log = variants_module.apply_auto_filter(
filtered_log, variants=variants, parameters=parameters_child)
variants = variants_module.get_variants(filtered_log,
parameters=parameters_child)
if enable_start_activities_filter:
filtered_log = start_activities_filter.apply_auto_filter(
filtered_log, variants=variants, parameters=parameters_child)
if enable_end_activities_filter:
filtered_log = end_activities_filter.apply_auto_filter(
filtered_log, variants=variants, parameters=parameters_child)
return filtered_log
def test_36(self):
from pm4py.algo.filtering.log.attributes import attributes_filter
log = self.load_running_example_xes()
filtered_log = attributes_filter.apply_auto_filter(log, parameters={
attributes_filter.Parameters.ATTRIBUTE_KEY: "concept:name",
attributes_filter.Parameters.DECREASING_FACTOR: 0.6})
from pm4py.algo.filtering.log.end_activities import end_activities_filter
log_end = end_activities_filter.get_end_activities(log)
log_af_ea = end_activities_filter.apply_auto_filter(
log, parameters={"decreasingFactor": 0.6})
print(end_activities_filter.get_end_activities(log_af_ea))
## Other Events
from pm4py.algo.filtering.log.attributes import attributes_filter
from pm4py.util import constants
log = attributes_filter.apply_auto_filter(
log,
parameters={
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: "concept:name",
"decreasingFactor": 0.6
})
activities = attributes_filter.get_attribute_values(log, "concept:name")
auto_filtered_activities = attributes_filter.get_attribute_values(
log, "concept:name")
# Entire variants
from pm4py.algo.filtering.log.variants import variants_filter
variants = variants_filter.get_variants(log)
log = variants_filter.apply_auto_filter(log)
