def filter_paths(log, allowed_paths, positive=True):
"""
Filter a log_skeleton on a specified list of paths
Parameters
---------------
log
Log object
allowed_paths
Allowed/forbidden paths
positive
Parameter that says whether the paths
should be kept/removed
Returns
----------------
filtered_log
Filtered log_skeleton object
"""
if check_is_dataframe(log):
from pm4py.algo.filtering.pandas.paths import paths_filter
return paths_filter.apply(log, allowed_paths, parameters={paths_filter.Parameters.POSITIVE: positive})
else:
from pm4py.algo.filtering.log.paths import paths_filter
return paths_filter.apply(log, allowed_paths, parameters={paths_filter.Parameters.POSITIVE: positive})
def filter_directly_follows_relation(log: Union[EventLog, pd.DataFrame], relations: List[str], retain: bool = True) -> \
Union[EventLog, pd.DataFrame]:
"""
Retain traces that contain any of the specified 'directly follows' relations.
For example, if relations == [('a','b'),('a','c')] and log [<a,b,c>,<a,c,b>,<a,d,b>]
the resulting log will contain traces describing [<a,b,c>,<a,c,b>].
Parameters
---------------
log
Log object
relations
List of activity name pairs, which are allowed/forbidden paths
retain
Parameter that says whether the paths
should be kept/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)
if check_is_pandas_dataframe(log):
from pm4py.algo.filtering.pandas.paths import paths_filter
parameters[paths_filter.Parameters.POSITIVE] = retain
return paths_filter.apply(log, relations, parameters=parameters)
else:
from pm4py.algo.filtering.log.paths import paths_filter
parameters[paths_filter.Parameters.POSITIVE] = retain
return paths_filter.apply(log, relations, parameters=parameters)
def filter_directly_follows_relation(log, relations, retain=True):
"""
Retain traces that contain any of the specified 'directly follows' relations.
For example, if relations == [('a','b'),('a','c')] and log [<a,b,c>,<a,c,b>,<a,d,b>]
the resulting log will contain traces describing [<a,b,c>,<a,c,b>].
Parameters
---------------
log
Log object
relations
List of activity name pairs, which are allowed/forbidden paths
retain
Parameter that says whether the paths
should be kept/removed
Returns
----------------
filtered_log
Filtered log object
"""
if check_is_dataframe(log):
from pm4py.algo.filtering.pandas.paths import paths_filter
return paths_filter.apply(
log,
relations,
parameters={paths_filter.Parameters.POSITIVE: retain})
else:
from pm4py.algo.filtering.log.paths import paths_filter
return paths_filter.apply(
log,
relations,
parameters={paths_filter.Parameters.POSITIVE: retain})
def test_filtering_paths(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(input_log, sep=',')
df3 = paths_filter.apply(dataframe, [("examine casually", "check ticket")], {"positive": False})
del df3
df3 = paths_filter.apply(dataframe, [("examine casually", "check ticket")], {"positive": True})
del df3
def test_filtering_paths(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)
df3 = paths_filter.apply(dataframe, [("examine casually", "check ticket")],
{paths_filter.Parameters.POSITIVE: False})
del df3
df3 = paths_filter.apply(dataframe, [("examine casually", "check ticket")],
{paths_filter.Parameters.POSITIVE: True})
del df3
def apply(dataframe, filter, parameters=None):
"""
:param dataframe:
:param filter:
:param parameters:
:return:
"""
if parameters is None:
parameters = {}
parameters[constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = filter[1][0]
parameters["positive"] = True
paths_to_filter = []
for p in filter[1][1]:
paths_to_filter.append(p.split("@@"))
return paths_filter.apply(dataframe,
paths_to_filter,
parameters=parameters)