def filter_variants(log, variants, retain=True):
"""
Filter a log on a specified set of variants
Parameters
---------------
log
Event log
variants
collection of variants to filter; A variant should be specified as a list of activity names, e.g., ['a','b','c']
retain
boolean; if True all traces conforming to the specified variants are retained; if False, all those traces are removed
Returns
--------------
filtered_log
Filtered log object
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.algo.filtering.pandas.variants import variants_filter
return variants_filter.apply(
log, [",".join(v) for v in variants],
parameters={variants_filter.Parameters.POSITIVE: retain})
else:
from pm4py.algo.filtering.log.variants import variants_filter
return variants_filter.apply(
log, [",".join(v) for v in variants],
parameters={variants_filter.Parameters.POSITIVE: retain})
def test_filtering_variants(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=',')
variants = case_statistics.get_variant_statistics(dataframe)
chosen_variants = [variants[0]["variant"]]
dataframe = variants_filter.apply(dataframe, chosen_variants)
del dataframe
def test_filtering_variants(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)
variants = case_statistics.get_variant_statistics(dataframe)
chosen_variants = [variants[0]["variant"]]
dataframe = variants_filter.apply(dataframe, chosen_variants)
del dataframe
def get_case_statistics(self, parameters=None):
"""
Gets the statistics on cases
Parameters
-------------
parameters
Possible parameters of the algorithm
Returns
-------------
list_cases
List of cases
"""
if parameters is None:
parameters = {}
parameters[
constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = self.activity_key
parameters[
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = self.activity_key
if self.reduced_grouped_dataframe is not None:
parameters[
constants.GROUPED_DATAFRAME] = self.reduced_grouped_dataframe
# parameters["max_ret_cases"] = ws_constants.MAX_NO_CASES_TO_RETURN
parameters["sort_by_column"] = parameters[
"sort_by_column"] if "sort_by_column" in parameters else "caseDuration"
parameters["sort_ascending"] = parameters[
"sort_ascending"] if "sort_ascending" in parameters else False
if "variant" in parameters:
var_to_filter = parameters["variant"]
# TODO: TECHNICAL DEBT
# quick turnaround for bug
var_to_filter = var_to_filter.replace(" start", "+start")
var_to_filter = var_to_filter.replace(" START", "+START")
var_to_filter = var_to_filter.replace(" complete", "+complete")
var_to_filter = var_to_filter.replace(" COMPLETE", "+COMPLETE")
filtered_dataframe = variants_filter.apply(
self.get_reduced_dataframe(), [var_to_filter],
parameters=parameters)
return [
casestats.include_key_in_value_list(
case_statistics.get_cases_description(
filtered_dataframe, parameters=parameters))
] + [self.get_log_summary_dictio()]
else:
return [
casestats.include_key_in_value_list(
case_statistics.get_cases_description(
self.get_reduced_dataframe(), parameters=parameters))
] + [self.get_log_summary_dictio()]
def filter_variants(log, admitted_variants):
"""
Filter a log_skeleton on a specified set of variants
Parameters
---------------
log
Event log_skeleton
admitted_variants
List of variants to filter
Returns
--------------
filtered_log
Filtered log_skeleton object
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.algo.filtering.pandas.variants import variants_filter
return variants_filter.apply(log, admitted_variants)
else:
from pm4py.algo.filtering.log.variants import variants_filter
return variants_filter.apply(log, admitted_variants)
def filter_variants(log: Union[EventLog, pd.DataFrame],
variants: Union[Set[str], List[str]],
retain: bool = True) -> Union[EventLog, pd.DataFrame]:
"""
Filter a log on a specified set of variants
Parameters
---------------
log
Event log
variants
collection of variants to filter; A variant should be specified as a list of activity names, e.g., ['a','b','c']
retain
boolean; if True all traces conforming to the specified variants are retained; if False, all those traces are 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!")
from pm4py.util import variants_util
parameters = get_properties(log)
if variants_util.VARIANT_SPECIFICATION == variants_util.VariantsSpecifications.STRING:
variants = [constants.DEFAULT_VARIANT_SEP.join(v) for v in variants]
if check_is_pandas_dataframe(log):
check_pandas_dataframe_columns(log)
from pm4py.algo.filtering.pandas.variants import variants_filter
parameters[variants_filter.Parameters.POSITIVE] = retain
return variants_filter.apply(log, variants, parameters=parameters)
else:
from pm4py.algo.filtering.log.variants import variants_filter
parameters[variants_filter.Parameters.POSITIVE] = retain
return variants_filter.apply(log, variants, parameters=parameters)
def apply(dataframe, filter, parameters=None):
"""
Apply a filter to the current log (variants filter)
Parameters
------------
dataframe
Pandas dataframe
filter
Filter to apply
parameters
Parameters of the algorithm
Returns
------------
dataframe
Pandas dataframe
"""
if parameters is None:
parameters = {}
return variants_filter.apply(dataframe, filter[1], parameters=parameters)
def apply(df, parameters=None):
"""
Returns a Pandas dataframe from which a sound workflow net could be extracted taking into account
a discovery algorithm returning models only with visible transitions
Parameters
------------
df
Pandas dataframe
parameters
Possible parameters of the algorithm, including:
max_no_variants -> Maximum number of variants to consider to return a Petri net
Returns
------------
filtered_df
Filtered dataframe
"""
if parameters is None:
parameters = {}
if PARAMETER_CONSTANT_CASEID_KEY not in parameters:
parameters[PARAMETER_CONSTANT_CASEID_KEY] = CASE_CONCEPT_NAME
if PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[PARAMETER_CONSTANT_ACTIVITY_KEY] = DEFAULT_NAME_KEY
if PARAMETER_CONSTANT_TIMESTAMP_KEY not in parameters:
parameters[PARAMETER_CONSTANT_TIMESTAMP_KEY] = DEFAULT_TIMESTAMP_KEY
if PARAMETER_CONSTANT_ATTRIBUTE_KEY not in parameters:
parameters[PARAMETER_CONSTANT_ATTRIBUTE_KEY] = parameters[
PARAMETER_CONSTANT_ACTIVITY_KEY]
caseid_glue = parameters[PARAMETER_CONSTANT_CASEID_KEY]
activity_key = parameters[PARAMETER_CONSTANT_ACTIVITY_KEY]
timest_key = parameters[PARAMETER_CONSTANT_TIMESTAMP_KEY]
max_no_variants = parameters[
"max_no_variants"] if "max_no_variants" in parameters else 20
variants_df = case_statistics.get_variants_df(df, parameters=parameters)
parameters["variants_df"] = variants_df
variant_stats = case_statistics.get_variant_statistics(
df, parameters=parameters)
all_variants_list = []
for var in variant_stats:
all_variants_list.append([var["variant"], var[caseid_glue]])
all_variants_list = sorted(all_variants_list,
key=lambda x: (x[1], x[0]),
reverse=True)
considered_variants = []
considered_traces = []
i = 0
while i < min(len(all_variants_list), max_no_variants):
variant = all_variants_list[i][0]
considered_variants.append(variant)
filtered_df = variants_filter.apply(df,
considered_variants,
parameters=parameters)
dfg_frequency = dfg_util.get_dfg_graph(filtered_df,
measure="frequency",
perf_aggregation_key="median",
case_id_glue=caseid_glue,
activity_key=activity_key,
timestamp_key=timest_key)
net, initial_marking, final_marking = alpha_miner.apply_dfg(
dfg_frequency, parameters=parameters)
is_sound = check_soundness.check_petri_wfnet_and_soundness(net)
if not is_sound:
del considered_variants[-1]
else:
traces_of_this_variant = variants_filter.apply(
df, [variant], parameters=parameters).groupby(caseid_glue)
traces_of_this_variant_keys = list(
traces_of_this_variant.groups.keys())
trace_of_this_variant = traces_of_this_variant.get_group(
traces_of_this_variant_keys[0])
this_trace = transform.transform_event_log_to_trace_log(
pandas_df_imp.convert_dataframe_to_event_log(
trace_of_this_variant),
case_glue=caseid_glue)[0]
if not activity_key == DEFAULT_NAME_KEY:
for j in range(len(this_trace)):
this_trace[j][DEFAULT_NAME_KEY] = this_trace[j][
activity_key]
considered_traces.append(this_trace)
filtered_log = TraceLog(considered_traces)
try:
alignments = alignment_factory.apply(filtered_log, net,
initial_marking,
final_marking)
del alignments
fitness = replay_fitness_factory.apply(filtered_log,
net,
initial_marking,
final_marking,
parameters=parameters)
if fitness["log_fitness"] < 0.99999:
del considered_variants[-1]
del considered_traces[-1]
except TypeError:
del considered_variants[-1]
del considered_traces[-1]
i = i + 1
return variants_filter.apply(df,
considered_variants,
parameters=parameters)
