def discover_abstraction_dataframe(df: pd.DataFrame, parameters: Optional[Dict[Any, Any]] = None) -> Tuple[
Any, Any, Any, Any, Any, Any, Any]:
"""
Discovers an abstraction from a dataframe that is useful for the Heuristics Miner ++ algorithm
Parameters
--------------
df
Dataframe
parameters
Parameters of the algorithm, including:
- Parameters.ACTIVITY_KEY
- Parameters.START_TIMESTAMP_KEY
- Parameters.TIMESTAMP_KEY
- Parameters.CASE_ID_KEY
Returns
--------------
start_activities
Start activities
end_activities
End activities
activities_occurrences
Activities along with their number of occurrences
dfg
Directly-follows graph
performance_dfg
(Performance) Directly-follows graph
sojourn_time
Sojourn time for each activity
concurrent_activities
Concurrent activities
"""
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes.DEFAULT_NAME_KEY)
start_timestamp_key = exec_utils.get_param_value(Parameters.START_TIMESTAMP_KEY, parameters,
None)
if start_timestamp_key is None:
start_timestamp_key = xes.DEFAULT_START_TIMESTAMP_KEY
parameters = copy(parameters)
parameters[Parameters.START_TIMESTAMP_KEY] = start_timestamp_key
timestamp_key = exec_utils.get_param_value(Parameters.TIMESTAMP_KEY, parameters, xes.DEFAULT_TIMESTAMP_KEY)
case_id_glue = exec_utils.get_param_value(Parameters.CASE_ID_KEY, parameters, constants.CASE_CONCEPT_NAME)
start_activities = pd_sa.get_start_activities(df, parameters=parameters)
end_activities = pd_ea.get_end_activities(df, parameters=parameters)
activities_occurrences = pd_attributes.get_attribute_values(df, activity_key, parameters=parameters)
efg_parameters = copy(parameters)
efg_parameters[pd_efg.Parameters.KEEP_FIRST_FOLLOWING] = True
dfg = pd_efg.apply(df, parameters=efg_parameters)
performance_dfg = df_statistics.get_dfg_graph(df, case_id_glue=case_id_glue,
activity_key=activity_key, timestamp_key=timestamp_key,
start_timestamp_key=start_timestamp_key, measure="performance")
sojourn_time = pd_soj_time.apply(df, parameters=parameters)
concurrent_activities = pd_conc_act.apply(df, parameters=parameters)
return (
start_activities, end_activities, activities_occurrences, dfg, performance_dfg, sojourn_time,
concurrent_activities)
def discover_eventually_follows_graph(log: Union[EventLog, pd.DataFrame]) -> Dict[Tuple[str, str], int]:
"""
Gets the eventually follows graph from a log object
Parameters
---------------
log
Log object
Returns
---------------
eventually_follows_graph
Dictionary of tuples of activities that eventually follows each other; along with the number of occurrences
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.statistics.eventually_follows.pandas import get
return get.apply(log)
else:
from pm4py.statistics.eventually_follows.log import get
return get.apply(log)
def discover_eventually_follows_graph(log: Union[EventLog, pd.DataFrame]) -> Dict[Tuple[str, str], int]:
"""
Gets the eventually follows graph from a log object
Parameters
---------------
log
Log object
Returns
---------------
eventually_follows_graph
Dictionary of tuples of activities that eventually follows each other; along with the number of occurrences
"""
if type(log) not in [pd.DataFrame, EventLog, EventStream]: raise Exception("the method can be applied only to a traditional event log!")
if check_is_pandas_dataframe(log):
check_pandas_dataframe_columns(log)
from pm4py.statistics.eventually_follows.pandas import get
return get.apply(log, parameters=get_properties(log))
else:
from pm4py.statistics.eventually_follows.log import get
return get.apply(log, parameters=get_properties(log))
def execute_script():
log_path = os.path.join("..", "tests", "input_data",
"interval_event_log.csv")
dataframe = pm4py.read_csv(log_path)
log_path = os.path.join("..", "tests", "input_data", "reviewing.xes")
log = pm4py.read_xes(log_path)
dataframe = pm4py.convert_to_dataframe(log)
parameters = {}
#parameters[constants.PARAMETER_CONSTANT_START_TIMESTAMP_KEY] = "start_timestamp"
parameters[constants.PARAMETER_CONSTANT_TIMESTAMP_KEY] = "time:timestamp"
parameters[constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = "concept:name"
parameters[constants.PARAMETER_CONSTANT_CASEID_KEY] = "case:concept:name"
parameters["strict"] = True
parameters["format"] = "svg"
start_activities = sa_get.get_start_activities(dataframe,
parameters=parameters)
end_activities = ea_get.get_end_activities(dataframe,
parameters=parameters)
att_count = att_get.get_attribute_values(dataframe,
"concept:name",
parameters=parameters)
parameters["start_activities"] = start_activities
parameters["end_activities"] = end_activities
soj_time = soj_time_get.apply(dataframe, parameters=parameters)
print("soj_time")
print(soj_time)
conc_act = conc_act_get.apply(dataframe, parameters=parameters)
print("conc_act")
print(conc_act)
efg = efg_get.apply(dataframe, parameters=parameters)
print("efg")
print(efg)
dfg_freq, dfg_perf = df_statistics.get_dfg_graph(
dataframe, measure="both", start_timestamp_key="start_timestamp")
dfg_gv_freq = dfg_vis_fact.apply(dfg_freq,
activities_count=att_count,
variant=dfg_vis_fact.Variants.FREQUENCY,
soj_time=soj_time,
parameters=parameters)
dfg_vis_fact.view(dfg_gv_freq)
dfg_gv_perf = dfg_vis_fact.apply(dfg_perf,
activities_count=att_count,
variant=dfg_vis_fact.Variants.PERFORMANCE,
soj_time=soj_time,
parameters=parameters)
dfg_vis_fact.view(dfg_gv_perf)
net, im, fm = dfg_conv.apply(dfg_freq)
gviz = pn_vis.apply(net, im, fm, parameters=parameters)
pn_vis.view(gviz)
