def test_filtering_attr_events(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.csv")
dataframe = csv_import_adapter.import_dataframe_from_path_wo_timeconversion(input_log, sep=',')
df1 = attributes_filter.apply_events(dataframe, ["reject request"], parameters={"positive": True})
df2 = attributes_filter.apply_events(dataframe, ["reject request"], parameters={"positive": False})
del df1
del df2
def filter_event_attribute_values(
log: Union[EventLog, pd.DataFrame],
attribute_key: str,
values: Union[Set[str], List[str]],
level: str = "case",
retain: bool = True) -> Union[EventLog, pd.DataFrame]:
"""
Filter a log object on the values of some event attribute
Parameters
--------------
log
Log object
attribute_key
Attribute to filter
values
Admitted (or forbidden) values
level
Specifies how the filter should be applied ('case' filters the cases where at least one occurrence happens,
'event' filter the events eventually trimming the cases)
retain
Specified if the values should be kept or removed
Returns
--------------
filtered_log
Filtered log object
"""
if type(log) not in [pd.DataFrame, EventLog, EventStream]:
raise Exception(
"the method can be applied only to a traditional event log!")
parameters = get_properties(log)
parameters[constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = attribute_key
if check_is_pandas_dataframe(log):
check_pandas_dataframe_columns(log)
from pm4py.algo.filtering.pandas.attributes import attributes_filter
if level == "event":
parameters[attributes_filter.Parameters.POSITIVE] = retain
return attributes_filter.apply_events(log,
values,
parameters=parameters)
elif level == "case":
parameters[attributes_filter.Parameters.POSITIVE] = retain
return attributes_filter.apply(log, values, parameters=parameters)
else:
from pm4py.algo.filtering.log.attributes import attributes_filter
if level == "event":
parameters[attributes_filter.Parameters.POSITIVE] = retain
return attributes_filter.apply_events(log,
values,
parameters=parameters)
elif level == "case":
parameters[attributes_filter.Parameters.POSITIVE] = retain
return attributes_filter.apply(log, values, parameters=parameters)
def test_filtering_attr_events(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.csv")
dataframe = pd.read_csv(input_log)
dataframe = dataframe_utils.convert_timestamp_columns_in_df(dataframe)
df1 = attributes_filter.apply_events(dataframe, ["reject request"],
parameters={attributes_filter.Parameters.POSITIVE: True})
df2 = attributes_filter.apply_events(dataframe, ["reject request"],
parameters={attributes_filter.Parameters.POSITIVE: False})
del df1
del df2
def apply(dataframe, filter, parameters=None):
"""
Apply a filter to the current log (attributes filter)
Parameters
------------
dataframe
Pandas dataframe
filter
Filter to apply
parameters
Parameters of the algorithm
Returns
------------
dataframe
Pandas dataframe
"""
if parameters is None:
parameters = {}
parameters[constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = filter[1][0]
return attributes_filter.apply_events(dataframe,
filter[1][1],
parameters=parameters)
def filter_event_attribute_values(log: Union[EventLog, pd.DataFrame], attribute_key: str, values: List[str],
level: str = "case", retain: bool = True) -> Union[EventLog, pd.DataFrame]:
"""
Filter a log object on the values of some event attribute
Parameters
--------------
log
Log object
attribute_key
Attribute to filter
values
Admitted (or forbidden) values
level
Specifies how the filter should be applied ('case' filters the cases where at least one occurrence happens,
'event' filter the events eventually trimming the cases)
retain
Specified if the values should be kept or removed
Returns
--------------
filtered_log
Filtered log object
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.algo.filtering.pandas.attributes import attributes_filter
if level == "event":
return attributes_filter.apply_events(log, values,
parameters={constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute_key,
attributes_filter.Parameters.POSITIVE: retain})
elif level == "case":
return attributes_filter.apply(log, values, parameters={
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute_key,
attributes_filter.Parameters.POSITIVE: retain})
else:
from pm4py.algo.filtering.log.attributes import attributes_filter
if level == "event":
return attributes_filter.apply_events(log, values,
parameters={constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute_key,
attributes_filter.Parameters.POSITIVE: retain})
elif level == "case":
return attributes_filter.apply(log, values, parameters={
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute_key,
attributes_filter.Parameters.POSITIVE: retain})
def filter_attribute_values(log, attribute, values, how="cases", positive=True):
"""
Filter a log_skeleton object on the values of some attribute
Parameters
--------------
log
Log object
attribute
Attribute to filter
values
Admitted (or forbidden) values
how
Specifies how the filter should be applied (cases filters the cases where at least one occurrence happens,
events filter the events eventually trimming the cases)
positive
Specified if the values should be kept or removed
Returns
--------------
filtered_log
Filtered log_skeleton object
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.algo.filtering.pandas.attributes import attributes_filter
if how == "events":
return attributes_filter.apply_events(log, values,
parameters={constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute,
attributes_filter.Parameters.POSITIVE: positive})
elif how == "cases":
return attributes_filter.apply(log, values, parameters={
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute, attributes_filter.Parameters.POSITIVE: positive})
else:
from pm4py.algo.filtering.log.attributes import attributes_filter
if how == "events":
return attributes_filter.apply_events(log, values,
parameters={constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute,
attributes_filter.Parameters.POSITIVE: positive})
else:
return attributes_filter.apply(log, values, parameters={
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: attribute, attributes_filter.Parameters.POSITIVE: positive})
def filter_log_by_resource_names(log, names: list):
"""Filters the eventlog by events having certain resources
Arguments:
log {DataFrame} -- The log to use for analysis
names {list} -- The resource names to filter by
Returns:
DataFrame -- The filtered log
"""
return attributes_filter.apply_events(log, names, parameters={constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: "org:resource", "positive": True})