def test_importExportCSVtoCSV(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"
event_log = csv_importer.import_log(
os.path.join(INPUT_DATA_DIR, "running-example.csv"))
event_log = sorting.sort_timestamp(event_log)
event_log = sampling.sample(event_log)
event_log = index_attribute.insert_event_index_as_event_attribute(
event_log)
trace_log = log_transform.transform_event_log_to_trace_log(event_log)
trace_log = sorting.sort_timestamp(trace_log)
trace_log = sampling.sample(trace_log)
trace_log = index_attribute.insert_trace_index_as_event_attribute(
trace_log)
event_log_transformed = log_transform.transform_trace_log_to_event_log(
trace_log)
csv_exporter.export_log(
event_log_transformed,
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
event_log_imported_after_export = csv_importer.import_log(
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
trace_log_imported_after_export = log_transform.transform_event_log_to_trace_log(
event_log_imported_after_export)
self.assertEqual(len(trace_log), len(trace_log_imported_after_export))
os.remove(os.path.join(OUTPUT_DATA_DIR,
"running-example-exported.csv"))
def test_csv1documentation(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"
import os
from pm4py.objects.log.importer.csv import factory as csv_importer
event_log = csv_importer.import_log(
os.path.join("input_data", "running-example.csv"))
event_log_length = len(event_log)
del event_log_length
from pm4py.objects.log import transform
trace_log = transform.transform_event_log_to_trace_log(
event_log, case_glue="case:concept:name")
del trace_log
from pm4py.objects.log.importer.csv.versions import pandas_df_imp
from pm4py.objects.log import transform
dataframe = pandas_df_imp.import_dataframe_from_path(
os.path.join("input_data", "running-example.csv"))
event_log = pandas_df_imp.convert_dataframe_to_event_log(dataframe)
trace_log = transform.transform_event_log_to_trace_log(
event_log, case_glue="case:concept:name")
from pm4py.objects.log.exporter.csv import factory as csv_exporter
csv_exporter.export_log(event_log, "outputFile1.csv")
os.remove("outputFile1.csv")
from pm4py.objects.log.exporter.csv import factory as csv_exporter
csv_exporter.export_log(trace_log, "outputFile2.csv")
os.remove("outputFile2.csv")
def test_importExportXEStoCSV(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"
trace_log = xes_importer.import_log(
os.path.join(INPUT_DATA_DIR, "running-example.xes"))
event_log = log_transform.transform_trace_log_to_event_log(trace_log)
csv_exporter.export_log(
event_log,
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
event_log_newimport = csv_importer.import_log(
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
trace_log_imported_after_export = log_transform.transform_event_log_to_trace_log(
event_log_newimport)
self.assertEqual(len(trace_log), len(trace_log_imported_after_export))
os.remove(os.path.join(OUTPUT_DATA_DIR,
"running-example-exported.csv"))
def get_input_file(self):
event_log_address = input("Event Log:")
log_format = event_log_address.split('.')[-1]
if str(log_format) == 'csv':
event_log = pd.read_csv(event_log_address)
elif str(log_format) == 'xes':
xes_log = xes_importer.import_log(event_log_address)
event_log = transform.transform_trace_log_to_event_log(xes_log)
csv_exporter.export_log(event_log, "event_log.csv")
event_log = pd.read_csv("event_log.csv")
event_log_attributes = event_log.columns
return event_log
# Create DataFrame including
def create_matrix_resource(self, event_log):
event_log['Complete Timestamp'] = pd.to_datetime(event_log['Complete Timestamp'])
event_log['Start Timestamp'] = pd.to_datetime(event_log['Start Timestamp'])
event_duration = abs(event_log['Complete Timestamp'] - event_log['Start Timestamp'])
event_log['Event Duration'] = event_duration
# create adjancy matrix of activities
resource_matrix = pd.DataFrame(
np.zeros(shape=(event_log['Resource'].nunique(), event_log['Resource'].nunique())),
columns=event_log['Resource'].unique(), index=event_log['Resource'].unique())
temp_log = event_log.sort_values(['Start Timestamp'], ascending=True).groupby('Case ID')
trace = {}
for case, casegroup in temp_log:
trace.update({case: casegroup['Resource'].values})
for key, val in trace.items():
i = 0
while i < (len(val) - 1):
resource_matrix[val[i + 1]][val[i]] += 1
i += 1
return resource_matrix
# Create Matrix of Activities (Adjancy Matrix for Directly Follows Graph)
# In: event log, Out: Adjancy Matrix of Activities
def create_matrix(self, event_log):
event_log['Complete Timestamp'] = pd.to_datetime(event_log['Complete Timestamp'])
event_log['Start Timestamp'] = pd.to_datetime(event_log['Start Timestamp'])
event_duration = abs(event_log['Complete Timestamp'] - event_log['Start Timestamp'])
event_log['Event Duration'] = event_duration
# create activity duration dictionary
act_dur_dict = {}
temp_act_log = event_log.groupby(['Activity'])
for kact, vact in temp_act_log:
act_dur_dict[kact] = vact['Event Duration'].mean()
# create adjancy matrix of activities
matrix = pd.DataFrame(np.zeros(shape=(event_log['Activity'].nunique(), event_log['Activity'].nunique())),
columns=event_log['Activity'].unique(), index=event_log['Activity'].unique())
temp_log = event_log.sort_values(['Start Timestamp'], ascending=True).groupby('Case ID')
trace = {}
for case, casegroup in temp_log:
trace.update({case: casegroup['Activity'].values})
for key, val in trace.items():
i = 0
while i < (len(val) - 1):
matrix[val[i + 1]][val[i]] += 1
i += 1
return matrix,act_dur_dict