def test_concurrent_activities_xes(self):
log = xes_importer.apply(
os.path.join("input_data", "interval_event_log.xes"))
from pm4py.statistics.concurrent_activities.log import get
conc_act = get.apply(
log,
parameters={get.Parameters.START_TIMESTAMP_KEY: "start_timestamp"})
def test_efg_xes(self):
log = xes_importer.apply(
os.path.join("input_data", "interval_event_log.xes"))
from pm4py.statistics.eventually_follows.log import get
efg = get.apply(
log,
parameters={get.Parameters.START_TIMESTAMP_KEY: "start_timestamp"})
def test_sojourn_time_xes(self):
log = xes_importer.apply(
os.path.join("input_data", "interval_event_log.xes"))
from pm4py.statistics.sojourn_time.log import get
soj_time = get.apply(
log,
parameters={get.Parameters.START_TIMESTAMP_KEY: "start_timestamp"})
def apply(dfg, log=None, parameters=None, activities_count=None, soj_time=None):
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes.DEFAULT_NAME_KEY)
image_format = exec_utils.get_param_value(Parameters.FORMAT, parameters, "png")
max_no_of_edges_in_diagram = exec_utils.get_param_value(Parameters.MAX_NO_EDGES_IN_DIAGRAM, parameters, 75)
start_activities = exec_utils.get_param_value(Parameters.START_ACTIVITIES, parameters, [])
end_activities = exec_utils.get_param_value(Parameters.END_ACTIVITIES, parameters, [])
activities = dfg_utils.get_activities_from_dfg(dfg)
if activities_count is None:
if log is not None:
activities_count = attr_get.get_attribute_values(log, activity_key, parameters=parameters)
else:
activities_count = {key: 1 for key in activities}
if soj_time is None:
if log is not None:
soj_time = soj_time_get.apply(log, parameters=parameters)
else:
soj_time = {key: 0 for key in activities}
return graphviz_visualization(activities_count, dfg, image_format=image_format, measure="frequency",
max_no_of_edges_in_diagram=max_no_of_edges_in_diagram,
start_activities=start_activities, end_activities=end_activities, soj_time=soj_time)
def execute_script():
log_path = os.path.join("..", "tests", "input_data", "interval_event_log.xes")
#log_path = os.path.join("..", "tests", "input_data", "reviewing.xes")
log = xes_importer.apply(log_path)
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["strict"] = False
parameters["format"] = "svg"
start_activities = sa_get.get_start_activities(log, parameters=parameters)
end_activities = ea_get.get_end_activities(log, parameters=parameters)
parameters["start_activities"] = start_activities
parameters["end_activities"] = end_activities
soj_time = soj_time_get.apply(log, parameters=parameters)
print("soj_time")
print(soj_time)
conc_act = conc_act_get.apply(log, parameters=parameters)
print("conc_act")
print(conc_act)
efg = efg_get.apply(log, parameters=parameters)
print("efg")
print(efg)
dfg_freq = dfg_algorithm.apply(log, parameters=parameters, variant=dfg_algorithm.Variants.FREQUENCY)
dfg_perf = dfg_algorithm.apply(log, parameters=parameters, variant=dfg_algorithm.Variants.PERFORMANCE)
dfg_gv_freq = dfg_vis_fact.apply(dfg_freq, log=log, variant=dfg_vis_fact.Variants.FREQUENCY,
parameters=parameters)
dfg_vis_fact.view(dfg_gv_freq)
dfg_gv_perf = dfg_vis_fact.apply(dfg_perf, log=log, variant=dfg_vis_fact.Variants.PERFORMANCE,
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)
def test_efg_pandas(self):
import pm4py
import pandas as pd
dataframe = pd.read_csv(os.path.join("input_data", "interval_event_log.csv"))
from pm4py.objects.log.util import dataframe_utils
dataframe = dataframe_utils.convert_timestamp_columns_in_df(dataframe)
from pm4py.statistics.eventually_follows.pandas import get
efg = get.apply(dataframe, parameters={get.Parameters.START_TIMESTAMP_KEY: "start_timestamp"})
def discover_abstraction_log(
log: EventLog,
parameters: Optional[Dict[Any, Any]] = None
) -> Tuple[Any, Any, Any, Any, Any, Any, Any]:
"""
Discovers an abstraction from a log that is useful for the Heuristics Miner ++ algorithm
Parameters
--------------
log
Event log
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_activities = log_sa.get_start_activities(log, parameters=parameters)
end_activities = log_ea.get_end_activities(log, parameters=parameters)
activities_occurrences = log_attributes.get_attribute_values(
log, activity_key, parameters=parameters)
efg_parameters = copy(parameters)
efg_parameters[efg_get.Parameters.KEEP_FIRST_FOLLOWING] = True
dfg = efg_get.apply(log, parameters=efg_parameters)
performance_dfg = dfg_alg.apply(log,
variant=dfg_alg.Variants.PERFORMANCE,
parameters=parameters)
sojourn_time = soj_get.apply(log, parameters=parameters)
concurrent_activities = conc_act_get.apply(log, parameters=parameters)
return (start_activities, end_activities, activities_occurrences, dfg,
performance_dfg, sojourn_time, concurrent_activities)
def apply(dfg: Dict[Tuple[str, str], int],
log: EventLog = None,
parameters: Optional[Dict[Any, Any]] = None,
activities_count: Dict[str, int] = None,
soj_time: Dict[str, float] = None) -> Digraph:
"""
Visualize a frequency directly-follows graph
Parameters
-----------------
dfg
Frequency Directly-follows graph
log
(if provided) Event log for the calculation of statistics
activities_count
(if provided) Dictionary associating to each activity the number of occurrences in the log.
soj_time
(if provided) Dictionary associating to each activity the average sojourn time
parameters
Variant-specific parameters
Returns
-----------------
gviz
Graphviz digraph
"""
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters, xes.DEFAULT_NAME_KEY)
image_format = exec_utils.get_param_value(Parameters.FORMAT, parameters,
"png")
max_no_of_edges_in_diagram = exec_utils.get_param_value(
Parameters.MAX_NO_EDGES_IN_DIAGRAM, parameters, 100000)
start_activities = exec_utils.get_param_value(Parameters.START_ACTIVITIES,
parameters, {})
end_activities = exec_utils.get_param_value(Parameters.END_ACTIVITIES,
parameters, {})
font_size = exec_utils.get_param_value(Parameters.FONT_SIZE, parameters,
12)
font_size = str(font_size)
activities = dfg_utils.get_activities_from_dfg(dfg)
bgcolor = exec_utils.get_param_value(Parameters.BGCOLOR, parameters,
"transparent")
stat_locale = exec_utils.get_param_value(Parameters.STAT_LOCALE,
parameters, None)
if stat_locale is None:
stat_locale = {}
if activities_count is None:
if log is not None:
activities_count = attr_get.get_attribute_values(
log, activity_key, parameters=parameters)
else:
# the frequency of an activity in the log is at least the number of occurrences of
# incoming arcs in the DFG.
# if the frequency of the start activities nodes is also provided, use also that.
activities_count = Counter({key: 0 for key in activities})
for el in dfg:
activities_count[el[1]] += dfg[el]
if isinstance(start_activities, dict):
for act in start_activities:
activities_count[act] += start_activities[act]
if soj_time is None:
if log is not None:
soj_time = soj_time_get.apply(log, parameters=parameters)
else:
soj_time = {key: 0 for key in activities}
return graphviz_visualization(
activities_count,
dfg,
image_format=image_format,
measure="frequency",
max_no_of_edges_in_diagram=max_no_of_edges_in_diagram,
start_activities=start_activities,
end_activities=end_activities,
soj_time=soj_time,
font_size=font_size,
bgcolor=bgcolor,
stat_locale=stat_locale)
