def test_case_statistics(self):
from pm4py.statistics.traces.pandas import case_statistics
df = self.get_dataframe()
case_statistics.get_cases_description(df)
case_statistics.get_variants_df(df)
case_statistics.get_variant_statistics(df)
#case_statistics.get_variant_statistics_with_case_duration(df)
case_statistics.get_events(df, "N77802")
case_statistics.get_variants_df_with_case_duration(df)
case_statistics.get_variants_df_and_list(df)
case_statistics.get_kde_caseduration(df)
def get_events(self, caseid, parameters=None):
"""
Gets the events of a case
Parameters
-------------
caseid
Case ID
parameters
Parameters of the algorithm
Returns
------------
list_events
Events belonging to the case
"""
if parameters is None:
parameters = {}
parameters[
constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = self.activity_key
parameters[
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = self.activity_key
if not self.grouped_dataframe is None:
parameters[constants.GROUPED_DATAFRAME] = self.grouped_dataframe
return case_statistics.get_events(self.dataframe,
caseid,
parameters=parameters)
def get_events(path, log_name, managed_logs, parameters=None):
if parameters is None:
parameters = {}
no_samples = parameters[
PARAMETER_NO_SAMPLES] if PARAMETER_NO_SAMPLES in parameters else DEFAULT_MAX_NO_SAMPLES
use_transition = parameters[
PARAMETER_USE_TRANSITION] if PARAMETER_USE_TRANSITION in parameters else DEFAULT_USE_TRANSITION
activity_key = DEFAULT_NAME_KEY if not use_transition else "@@classifier"
filters = parameters[FILTERS] if FILTERS in parameters else []
parameters[pm4py_constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = activity_key
parameters[pm4py_constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = activity_key
case_id = parameters["case_id"]
folder = os.path.join(path, log_name)
parquet_list = parquet_importer.get_list_parquet(folder)
ret = []
count = 0
for index, pq in enumerate(parquet_list):
pq_basename = Path(pq).name
if pq_basename in managed_logs:
count = count + 1
df = get_filtered_parquet(pq,
None,
filters,
use_transition=use_transition,
parameters=parameters)
try:
events = case_statistics.get_events(df, case_id)
if len(events) > 0:
df = parquet_importer.apply(pq)
ret = case_statistics.get_events(df, case_id)
break
except:
pass
if count >= no_samples:
break
return ret