def apply(log, parameters=None, variant=DFG_NATIVE):
"""
Calculates DFG graph (frequency or performance) starting from a log
Parameters
----------
log
Log
parameters
Possible parameters passed to the algorithms:
aggregationMeasure -> performance aggregation measure (min, max, mean, median)
activity_key -> Attribute to use as activity
timestamp_key -> Attribute to use as timestamp
variant
Variant of the algorithm to use, possible values:
native, frequency, performance, frequency_greedy, performance_greedy
Returns
-------
dfg
DFG graph
"""
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_util.DEFAULT_TIMESTAMP_KEY
if pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_CASEID_KEY] = pmutil.constants.CASE_ATTRIBUTE_GLUE
if isinstance(log, pandas.core.frame.DataFrame):
log = csv_import_adapter.convert_timestamp_columns_in_df(
log,
timest_columns=[
parameters[pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY]
])
dfg_frequency, dfg_performance = df_statistics.get_dfg_graph(
log,
measure="both",
activity_key=parameters[
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY],
timestamp_key=parameters[
pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY],
case_id_glue=parameters[
pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY])
if 'native' in variant or 'frequency' in variant:
return dfg_frequency
else:
return dfg_performance
return VERSIONS[variant](log_conversion.apply(log, parameters,
log_conversion.TO_EVENT_LOG),
parameters=parameters)
def test_prefiltering_dataframe(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=',')
dataframe = attributes_filter.filter_df_keeping_spno_activities(dataframe, activity_key="concept:name")
dataframe = case_filter.filter_on_ncases(dataframe, case_id_glue="case:concept:name")
dataframe = csv_import_adapter.convert_timestamp_columns_in_df(dataframe)
dataframe = dataframe.sort_values('time:timestamp')
event_log = log_conv_fact.apply(dataframe, variant=log_conv_fact.TO_EVENT_STREAM)
log = log_conv_fact.apply(event_log)
del log
def convert_df_pm_format(
df,
sort=False,
sort_field="time:timestamp",
timest_format=None,
timest_columns=None,
):
df = convert_timestamp_columns_in_df(df,
timest_format=timest_format,
timest_columns=timest_columns)
if sort and sort_field:
df = df.sort_values(sort_field)
return df
def __init__(
self,
df,
timestamp_field="timestamp",
case_id_field="case_id",
activity_field="activity",
):
super(TraceComparison, self).__init__()
self.timestamp_field = timestamp_field
self.case_id_field = case_id_field
self.activity_field = activity_field
self.event_log = csv_import_adapter.convert_timestamp_columns_in_df(
df, timest_columns=[timestamp_field])
self.observe(self.on_trace_change, names="trace")
self.activities = self.event_log[self.activity_field].unique().tolist()
self.on_trace_change()
def __init__(
self,
df,
timestamp_field="timestamp",
case_id_field="case_id",
activity_field="activity",
):
super(TraceExplorer, self).__init__()
self.df = csv_import_adapter.convert_timestamp_columns_in_df(
df, timest_columns=[timestamp_field])
events = []
for index, row in self.df.iterrows():
events.append({
"ENTITY_ID": row[case_id_field],
"TS": row[timestamp_field],
"EVENT_NAME": row[activity_field],
})
self.value = events
def apply(net,
initial_marking=None,
final_marking=None,
log=None,
aggregated_statistics=None,
parameters=None,
variant="wo_decoration"):
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_util.DEFAULT_TIMESTAMP_KEY
if pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_CASEID_KEY] = log_util.CASE_ATTRIBUTE_GLUE
if log is not None:
if isinstance(log, pandas.core.frame.DataFrame):
log = csv_import_adapter.convert_timestamp_columns_in_df(
log,
timest_columns=[
parameters[
pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY]
])
log = log_conversion.apply(log, parameters,
log_conversion.TO_EVENT_LOG)
return VERSIONS[variant](net,
initial_marking,
final_marking,
log=log,
aggregated_statistics=aggregated_statistics,
parameters=parameters)
def __init__(
self,
df,
timestamp_field="timestamp",
case_id_field="case_id",
activity_field="activity",
):
super(ProcessMap, self).__init__()
self.timestamp_field = timestamp_field
self.case_id_field = case_id_field
self.activity_field = activity_field
self.df = csv_import_adapter.convert_timestamp_columns_in_df(
df, timest_columns=[timestamp_field])
self.cases = self.df.groupby(case_id_field)
self.activities = self.cases.agg({
activity_field: lambda x: "".join(x)
}).groupby(activity_field)
self.sorted_activities = self.activities.size().sort_values(
ascending=False)
self.observe(self.on_filter_change, names="filter")
self.on_filter_change()
def execute_script():
aa = time.time()
dataframe = csv_import_adapter.import_dataframe_from_path_wo_timeconversion(
inputLog, sep=',')
dataframe = csv_import_adapter.convert_caseid_column_to_str(
dataframe, case_id_glue=CASEID_GLUE)
dataframe = csv_import_adapter.convert_timestamp_columns_in_df(
dataframe, timest_format=TIMEST_FORMAT, timest_columns=TIMEST_COLUMNS)
dataframe = dataframe.sort_values([CASEID_GLUE, TIMEST_KEY])
dataframe_fa = attributes_filter.filter_df_keeping_spno_activities(
dataframe,
activity_key=ACTIVITY_KEY,
max_no_activities=MAX_NO_ACTIVITIES)
bb = time.time()
print("importing log time=", (bb - aa))
parameters_cde = {
constants.PARAMETER_CONSTANT_CASEID_KEY: CASEID_GLUE,
constants.PARAMETER_CONSTANT_TIMESTAMP_KEY: TIMEST_KEY,
"sort_by_column": "caseDuration",
"sort_ascending": False,
"max_ret_cases": 1000
}
cases_desc = case_statistics.get_cases_description(
dataframe, parameters=parameters_cde)
print(cases_desc)
bb2 = time.time()
print("calculating and printing cases_desc = ", (bb2 - bb))
calculate_process_schema_from_df(dataframe_fa, "NOFILTERS_FREQUENCY.svg",
"NOFILTERS_PERFORMANCE.svg")
GENERATED_IMAGES.append("NOFILTERS_FREQUENCY.svg")
GENERATED_IMAGES.append("NOFILTERS_PERFORMANCE.svg")
if DELETE_VARIABLES:
del dataframe_fa
cc = time.time()
print(
"saving initial Inductive Miner process schema along with frequency metrics=",
(cc - bb2))
dataframe_cp = case_filter.filter_on_case_performance(
dataframe,
case_id_glue=CASEID_GLUE,
timestamp_key=TIMEST_KEY,
min_case_performance=100000,
max_case_performance=10000000)
dataframe_cp_fa = attributes_filter.filter_df_keeping_spno_activities(
dataframe_cp,
activity_key=ACTIVITY_KEY,
max_no_activities=MAX_NO_ACTIVITIES)
dataframe_cp = None
if DELETE_VARIABLES:
del dataframe_cp
calculate_process_schema_from_df(dataframe_cp_fa,
"FILTER_CP_FREQUENCY.svg",
"FILTER_CP_PERFORMANCE.svg")
GENERATED_IMAGES.append("FILTER_CP_FREQUENCY.svg")
GENERATED_IMAGES.append("FILTER_CP_PERFORMANCE.svg")
if DELETE_VARIABLES:
del dataframe_cp_fa
dd = time.time()
print("filtering on case performance and generating process schema=",
(dd - cc))
if ENABLE_ATTRIBUTE_FILTER:
parameters_att = {
constants.PARAMETER_CONSTANT_CASEID_KEY: CASEID_GLUE,
constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY: ATTRIBUTE_TO_FILTER,
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: ATTRIBUTE_TO_FILTER,
"positive": True
}
dataframe_att = attributes_filter.apply(dataframe,
ATTRIBUTE_VALUES_TO_FILTER,
parameters=parameters_att)
# dataframe_att = attributes_filter.apply_auto_filter(dataframe, parameters=parameters_att)
print(
"all the activities in the log",
attributes_filter.get_attribute_values(dataframe_att,
ACTIVITY_KEY))
dataframe_att_fa = attributes_filter.filter_df_keeping_spno_activities(
dataframe_att,
activity_key=ACTIVITY_KEY,
max_no_activities=MAX_NO_ACTIVITIES)
if DELETE_VARIABLES:
del dataframe_att
calculate_process_schema_from_df(dataframe_att_fa,
"FILTER_ATT_FREQUENCY.svg",
"FILTER_ATT_PERFORMANCE.svg")
GENERATED_IMAGES.append("FILTER_ATT_FREQUENCY.svg")
GENERATED_IMAGES.append("FILTER_ATT_PERFORMANCE.svg")
if DELETE_VARIABLES:
del dataframe_att_fa
ee = time.time()
print("filtering on attribute values and generating process schema=",
(ee - dd))
ee = time.time()
parameters_sa = {
constants.PARAMETER_CONSTANT_CASEID_KEY: CASEID_GLUE,
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: ACTIVITY_KEY
}
parameters_ea = {
constants.PARAMETER_CONSTANT_CASEID_KEY: CASEID_GLUE,
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: ACTIVITY_KEY
}
start_act = start_activities_filter.get_start_activities(
dataframe, parameters=parameters_sa)
print("start activities in the log = ", start_act)
end_act = end_activities_filter.get_end_activities(
dataframe, parameters=parameters_ea)
print("end activities in the log = ", end_act)
ff = time.time()
print("finding start and end activities along with their count", (ff - ee))
if ENABLE_STARTACT_FILTER:
dataframe_sa = start_activities_filter.apply(dataframe,
STARTACT_TO_FILTER,
parameters=parameters_sa)
# dataframe_sa = start_activities_filter.apply_auto_filter(dataframe, parameters=parameters_sa)
start_act = start_activities_filter.get_start_activities(
dataframe_sa, parameters=parameters_sa)
print("start activities in the filtered log = ", start_act)
dataframe_sa_fa = attributes_filter.filter_df_keeping_spno_activities(
dataframe_sa,
activity_key=ACTIVITY_KEY,
max_no_activities=MAX_NO_ACTIVITIES)
if DELETE_VARIABLES:
del dataframe_sa
calculate_process_schema_from_df(dataframe_sa_fa,
"FILTER_SA_FREQUENCY.svg",
"FILTER_SA_PERFORMANCE.svg")
GENERATED_IMAGES.append("FILTER_SA_FREQUENCY.svg")
GENERATED_IMAGES.append("FILTER_SA_PERFORMANCE.svg")
if DELETE_VARIABLES:
del dataframe_sa_fa
gg = time.time()
if ENABLE_STARTACT_FILTER:
print("filtering start activities time=", (gg - ff))
if ENABLE_ENDACT_FILTER:
dataframe_ea = end_activities_filter.apply(dataframe,
ENDACT_TO_FILTER,
parameters=parameters_ea)
# dataframe_ea = end_activities_filter.apply_auto_filter(dataframe, parameters=parameters_ea)
end_act = end_activities_filter.get_end_activities(
dataframe_ea, parameters=parameters_ea)
print("end activities in the filtered log = ", end_act)
dataframe_ea_fa = attributes_filter.filter_df_keeping_spno_activities(
dataframe_ea,
activity_key=ACTIVITY_KEY,
max_no_activities=MAX_NO_ACTIVITIES)
if DELETE_VARIABLES:
del dataframe_ea
calculate_process_schema_from_df(dataframe_ea_fa,
"FILTER_EA_FREQUENCY.svg",
"FILTER_EA_PERFORMANCE.svg")
GENERATED_IMAGES.append("FILTER_EA_FREQUENCY.svg")
GENERATED_IMAGES.append("FILTER_EA_PERFORMANCE.svg")
if DELETE_VARIABLES:
del dataframe_ea_fa
hh = time.time()
if ENABLE_ENDACT_FILTER:
print("filtering end activities time=", (hh - gg))
if REMOVE_GENERATED_IMAGES:
for image in GENERATED_IMAGES:
os.remove(image)
def execute_script():
time1 = time.time()
dataframe = csv_import_adapter.import_dataframe_from_path_wo_timeconversion(
inputLog, sep=SEP, quotechar=QUOTECHAR)
time2 = time.time()
print("time2 - time1: " + str(time2 - time1))
parameters_filtering = {
constants.PARAMETER_CONSTANT_CASEID_KEY: CASEID_GLUE,
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: ACTIVITY_KEY
}
if enable_auto_filter:
dataframe = auto_filter.apply_auto_filter(
dataframe, parameters=parameters_filtering)
else:
dataframe = attributes_filter.apply_auto_filter(
dataframe, parameters=parameters_filtering)
time3 = time.time()
print("time3 - time2: " + str(time3 - time2))
if enable_filtering_on_cases:
dataframe = case_filter.filter_on_ncases(dataframe,
case_id_glue=CASEID_GLUE,
max_no_cases=max_no_cases)
time4 = time.time()
dataframe = csv_import_adapter.convert_caseid_column_to_str(
dataframe, case_id_glue=CASEID_GLUE)
dataframe = csv_import_adapter.convert_timestamp_columns_in_df(
dataframe, timest_columns=TIMEST_COLUMNS, timest_format=TIMEST_FORMAT)
time6 = time.time()
print("time6 - time4: " + str(time6 - time4))
# dataframe = dataframe.sort_values('time:timestamp')
time7 = time.time()
print("time7 - time6: " + str(time7 - time6))
# show the filtered dataframe on the screen
activities_count = attributes_filter.get_attribute_values(
dataframe, attribute_key=ACTIVITY_KEY)
[dfg_frequency, dfg_performance
] = df_statistics.get_dfg_graph(dataframe,
measure="both",
perf_aggregation_key="median",
case_id_glue=CASEID_GLUE,
activity_key=ACTIVITY_KEY,
timestamp_key=TIMEST_KEY)
if enable_filtering_df:
print("len dfg_frequency 0=", len(dfg_frequency))
dfg_frequency = dfg_filtering.apply(
dfg_frequency, {"noiseThreshold": filtering_df_noise})
print("len dfg_frequency 1=", len(dfg_frequency))
time8 = time.time()
print("time8 - time7: " + str(time8 - time7))
gviz = dfg_vis_factory.apply(dfg_frequency,
activities_count=activities_count,
parameters={"format": "svg"})
dfg_vis_factory.view(gviz)
net, initial_marking, final_marking = inductive_factory.apply_dfg(
dfg_frequency)
# net, initial_marking, final_marking = alpha_factory.apply_dfg(dfg_frequency)
spaths = get_shortest_paths(net)
time9 = time.time()
print("time9 - time8: " + str(time9 - time8))
aggregated_statistics = get_decorations_from_dfg_spaths_acticount(
net, dfg_performance, spaths, activities_count, variant="performance")
gviz = pn_vis_factory.apply(net,
initial_marking,
final_marking,
variant="performance",
aggregated_statistics=aggregated_statistics,
parameters={"format": "svg"})
time10 = time.time()
print("time10 - time9: " + str(time10 - time9))
print("time10 - time1: " + str(time10 - time1))
pn_vis_factory.view(gviz)