def execute_script():
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
activities = pm4py.get_attribute_values(log, "concept:name")
dfg, sa, ea = pm4py.discover_dfg(log)
# filters the DFG to make a simpler one
perc = 0.5
dfg, sa, ea, activities = dfg_filtering.filter_dfg_on_activities_percentage(
dfg, sa, ea, activities, perc)
dfg, sa, ea, activities = dfg_filtering.filter_dfg_on_paths_percentage(
dfg, sa, ea, activities, perc)
# creates the simulated log
simulated_log = dfg_playout.apply(dfg, sa, ea)
print(simulated_log)
print(len(simulated_log))
print(sum(x.attributes["probability"] for x in simulated_log))
# shows the two DFGs to show that they are identical
pm4py.view_dfg(dfg, sa, ea, log=log, format="svg")
new_dfg, new_sa, new_ea = pm4py.discover_dfg(simulated_log)
pm4py.view_dfg(new_dfg, new_sa, new_ea, log=simulated_log, format="svg")
for trace in simulated_log:
print(list(x["concept:name"] for x in trace))
print(trace.attributes["probability"],
dfg_playout.get_trace_probability(trace, dfg, sa, ea))
break
dfg, sa, ea = pm4py.discover_dfg(log)
variants = pm4py.get_variants(log)
sum_prob_log_variants = 0.0
for var in variants:
sum_prob_log_variants += dfg_playout.get_trace_probability(
variants[var][0], dfg, sa, ea)
print(
"percentage of behavior allowed from DFG that is in the log (from 0.0 to 1.0): ",
sum_prob_log_variants)
def execute_script():
log = pm4py.read_xes("../tests/input_data/running-example.xes")
dfg, sa, ea = pm4py.discover_dfg(log)
tree = pm4py.discover_process_tree_inductive(log)
heu_net = pm4py.discover_heuristics_net(log)
net, im, fm = pm4py.discover_petri_net_alpha(log)
bpmn = pm4py.convert_to_bpmn(tree)
ts = ts_discovery.apply(log)
x_cases, y_cases = case_statistics.get_kde_caseduration(log)
gviz1 = dfg_visualizer.apply(dfg)
gviz2 = tree_visualizer.apply(tree)
gviz3 = hn_visualizer.apply(heu_net)
gviz4 = pn_visualizer.apply(net, im, fm)
gviz5 = bpmn_visualizer.apply(bpmn)
gviz6 = ts_visualizer.apply(ts)
gviz7 = graphs_visualizer.apply(x_cases, y_cases, variant=graphs_visualizer.Variants.CASES,
parameters={graphs_visualizer.Variants.CASES.value.Parameters.FORMAT: "svg"})
print("1", len(dfg_visualizer.serialize_dot(gviz1)))
print("1", len(dfg_visualizer.serialize(gviz1)))
print("2", len(tree_visualizer.serialize_dot(gviz2)))
print("2", len(tree_visualizer.serialize(gviz2)))
print("3", len(hn_visualizer.serialize(gviz3)))
print("4", len(pn_visualizer.serialize_dot(gviz4)))
print("4", len(pn_visualizer.serialize(gviz4)))
print("5", len(bpmn_visualizer.serialize_dot(gviz5)))
print("5", len(bpmn_visualizer.serialize(gviz5)))
print("6", len(ts_visualizer.serialize_dot(gviz6)))
print("6", len(ts_visualizer.serialize(gviz6)))
print("7", len(graphs_visualizer.serialize(gviz7)))
def test_filter_act_percentage(self):
from pm4py.algo.filtering.dfg import dfg_filtering
log = pm4py.read_xes("input_data/running-example.xes")
dfg, sa, ea = pm4py.discover_dfg(log)
act_count = pm4py.get_attribute_values(log, "concept:name")
dfg_filtering.filter_dfg_on_activities_percentage(
dfg, sa, ea, act_count, 0.1)
def test_dfg_align(self):
import pm4py
from pm4py.objects.dfg.filtering import dfg_filtering
from pm4py.objects.dfg.utils import dfg_alignment
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
dfg, sa, ea = pm4py.discover_dfg(log)
act_count = pm4py.get_attribute_values(log, "concept:name")
dfg, sa, ea, act_count = dfg_filtering.filter_dfg_on_activities_percentage(dfg, sa, ea, act_count, 0.5)
dfg, sa, ea, act_count = dfg_filtering.filter_dfg_on_paths_percentage(dfg, sa, ea, act_count, 0.5)
aligned_traces = dfg_alignment.apply(log, dfg, sa, ea)
def execute_script():
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
frequency_dfg, sa, ea = pm4py.discover_dfg(log)
performance_dfg, sa, ea = pm4py.discover_performance_dfg(log)
simulated_log = dfg_simulator.apply(
frequency_dfg,
sa,
ea,
variant=dfg_simulator.Variants.PERFORMANCE,
parameters={"performance_dfg": performance_dfg})
print(simulated_log)
def execute_script():
dataframe1 = pd.read_csv(
os.path.join("..", "tests", "input_data", "interleavings",
"receipt_even.csv"))
dataframe1 = pm4py.format_dataframe(dataframe1)
dataframe2 = pd.read_csv(
os.path.join("..", "tests", "input_data", "interleavings",
"receipt_odd.csv"))
dataframe2 = pm4py.format_dataframe(dataframe2)
case_relations = pd.read_csv(
os.path.join("..", "tests", "input_data", "interleavings",
"case_relations.csv"))
merged = case_relations_merging.apply(dataframe1, dataframe2,
case_relations)
dfg, sa, ea = pm4py.discover_dfg(merged)
pm4py.view_dfg(dfg, sa, ea, format="svg")
def execute_script():
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
print("number of cases", len(log))
print("number of events", sum(len(x) for x in log))
print("number of variants", len(pm4py.get_variants(log)))
ac = get.get_attribute_values(log, "concept:name")
dfg, sa, ea = pm4py.discover_dfg(log)
perc = 0.5
dfg, sa, ea, ac = dfg_filtering.filter_dfg_on_activities_percentage(
dfg, sa, ea, ac, perc)
dfg, sa, ea, ac = dfg_filtering.filter_dfg_on_paths_percentage(
dfg, sa, ea, ac, perc)
aa = time.time()
aligned_traces = dfg_alignment.apply(log, dfg, sa, ea)
bb = time.time()
net, im, fm = pm4py.convert_to_petri_net(dfg, sa, ea)
for trace in aligned_traces:
if trace["cost"] != trace["internal_cost"]:
print(trace)
pass
print(bb - aa)
print(sum(x["visited_states"] for x in aligned_traces))
print(
sum(x["cost"] // align_utils.STD_MODEL_LOG_MOVE_COST
for x in aligned_traces))
gviz = visualizer.apply(dfg,
activities_count=ac,
parameters={
"start_activities": sa,
"end_activities": ea,
"format": "svg"
})
visualizer.view(gviz)
cc = time.time()
aligned_traces2 = petri_alignments.apply(
log,
net,
im,
fm,
variant=petri_alignments.Variants.VERSION_DIJKSTRA_LESS_MEMORY)
dd = time.time()
print(dd - cc)
print(sum(x["visited_states"] for x in aligned_traces2))
print(
sum(x["cost"] // align_utils.STD_MODEL_LOG_MOVE_COST
for x in aligned_traces2))
def get_process_svg():
parameters = request.args.get("parameters")
parameters = __process_parameters(parameters)
log = __prepare_event_log(parameters)
ext_type = parameters[
"ext_type"] if "ext_type" in parameters else "document_flow_log"
log_type = __get_log_type_from_ext_type(ext_type)
if log_type == 0:
log.type = "succint"
from pm4pymdl.algo.mvp.gen_framework import algorithm as discovery
from pm4pymdl.visualization.mvp.gen_framework import visualizer as vis_factory
model = discovery.apply(log,
model_type_variant="model3",
node_freq_variant="type31",
edge_freq_variant="type11")
gviz = vis_factory.apply(model, parameters={"format": "svg"})
elif log_type == 1 or log_type == 2:
import pandas as pd
if type(log) is pd.DataFrame:
from pm4py.objects.dfg.retrieval.pandas import get_dfg_graph
dfg = get_dfg_graph(log)
from pm4py.statistics.start_activities.pandas import get as pd_sa_get
from pm4py.statistics.end_activities.pandas import get as pd_ea_get
sa = pd_sa_get.get_start_activities(log)
ea = pd_ea_get.get_end_activities(log)
else:
dfg, sa, ea = pm4py.discover_dfg(log)
act_count = pm4py.get_attribute_values(log, "concept:name")
dfg, sa, ea, act_count = dfg_filtering.filter_dfg_on_paths_percentage(
dfg, sa, ea, act_count, 0.2, keep_all_activities=True)
gviz = pm4py.visualization.dfg.visualizer.apply(
dfg,
activities_count=act_count,
parameters={
"format": "svg",
"start_activities": sa,
"end_activities": ea
})
ser = pm4py.visualization.dfg.visualizer.serialize(gviz).decode("utf-8")
return ser
def execute_script():
log = pm4py.read_xes("../tests/input_data/receipt.xes")
dfg, sa, ea = pm4py.discover_dfg(log)
act_count = pm4py.get_attribute_values(log, "concept:name")
# keep the specified amount of activities
dfg, sa, ea, act_count = pm4py.objects.dfg.filtering.dfg_filtering.filter_dfg_on_activities_percentage(
dfg, sa, ea, act_count, 0.3)
# keep the specified amount of paths
dfg, sa, ea, act_count = pm4py.objects.dfg.filtering.dfg_filtering.filter_dfg_on_paths_percentage(
dfg, sa, ea, act_count, 0.3)
# view the DFG
gviz = dfg_visualizer.apply(
dfg,
activities_count=act_count,
parameters={
dfg_visualizer.Variants.FREQUENCY.value.Parameters.START_ACTIVITIES:
sa,
dfg_visualizer.Variants.FREQUENCY.value.Parameters.END_ACTIVITIES:
ea,
dfg_visualizer.Variants.FREQUENCY.value.Parameters.FORMAT: "svg"
})
dfg_visualizer.view(gviz)
def test_dfg(self):
log = pm4py.read_xes("input_data/running-example.xes")
dfg, sa, ea = pm4py.discover_dfg(log)
def execute_script():
ENABLE_VISUALIZATION = True
# reads a XES into an event log
log1 = pm4py.read_xes("../tests/input_data/running-example.xes")
# reads a CSV into a dataframe
df = pd.read_csv("../tests/input_data/running-example.csv")
# formats the dataframe with the mandatory columns for process mining purposes
df = pm4py.format_dataframe(df,
case_id="case:concept:name",
activity_key="concept:name",
timestamp_key="time:timestamp")
# converts the dataframe to an event log
log2 = pm4py.convert_to_event_log(df)
# converts the log read from XES into a stream and dataframe respectively
stream1 = pm4py.convert_to_event_stream(log1)
df2 = pm4py.convert_to_dataframe(log1)
# writes the log1 to a XES file
pm4py.write_xes(log1, "ru1.xes")
dfg, dfg_sa, dfg_ea = pm4py.discover_dfg(log1)
petri_alpha, im_alpha, fm_alpha = pm4py.discover_petri_net_alpha(log1)
petri_inductive, im_inductive, fm_inductive = pm4py.discover_petri_net_inductive(
log1)
petri_heuristics, im_heuristics, fm_heuristics = pm4py.discover_petri_net_heuristics(
log1)
tree_inductive = pm4py.discover_tree_inductive(log1)
heu_net = pm4py.discover_heuristics_net(log1)
pm4py.write_dfg(dfg, dfg_sa, dfg_ea, "ru_dfg.dfg")
pm4py.write_petri_net(petri_alpha, im_alpha, fm_alpha, "ru_alpha.pnml")
pm4py.write_petri_net(petri_inductive, im_inductive, fm_inductive,
"ru_inductive.pnml")
pm4py.write_petri_net(petri_heuristics, im_heuristics, fm_heuristics,
"ru_heuristics.pnml")
pm4py.write_process_tree(tree_inductive, "ru_inductive.ptml")
dfg, dfg_sa, dfg_ea = pm4py.read_dfg("ru_dfg.dfg")
petri_alpha, im_alpha, fm_alpha = pm4py.read_petri_net("ru_alpha.pnml")
petri_inductive, im_inductive, fm_inductive = pm4py.read_petri_net(
"ru_inductive.pnml")
petri_heuristics, im_heuristics, fm_heuristics = pm4py.read_petri_net(
"ru_heuristics.pnml")
tree_inductive = pm4py.read_process_tree("ru_inductive.ptml")
pm4py.save_vis_petri_net(petri_alpha, im_alpha, fm_alpha, "ru_alpha.png")
pm4py.save_vis_petri_net(petri_inductive, im_inductive, fm_inductive,
"ru_inductive.png")
pm4py.save_vis_petri_net(petri_heuristics, im_heuristics, fm_heuristics,
"ru_heuristics.png")
pm4py.save_vis_process_tree(tree_inductive, "ru_inductive_tree.png")
pm4py.save_vis_heuristics_net(heu_net, "ru_heunet.png")
pm4py.save_vis_dfg(dfg, dfg_sa, dfg_ea, "ru_dfg.png")
if ENABLE_VISUALIZATION:
pm4py.view_petri_net(petri_alpha, im_alpha, fm_alpha, format="svg")
pm4py.view_petri_net(petri_inductive,
im_inductive,
fm_inductive,
format="svg")
pm4py.view_petri_net(petri_heuristics,
im_heuristics,
fm_heuristics,
format="svg")
pm4py.view_process_tree(tree_inductive, format="svg")
pm4py.view_heuristics_net(heu_net, format="svg")
pm4py.view_dfg(dfg, dfg_sa, dfg_ea, format="svg")
aligned_traces = pm4py.conformance_alignments(log1, petri_inductive,
im_inductive, fm_inductive)
replayed_traces = pm4py.conformance_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
fitness_tbr = pm4py.evaluate_fitness_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
print("fitness_tbr", fitness_tbr)
fitness_align = pm4py.evaluate_fitness_alignments(log1, petri_inductive,
im_inductive,
fm_inductive)
print("fitness_align", fitness_align)
precision_tbr = pm4py.evaluate_precision_tbr(log1, petri_inductive,
im_inductive, fm_inductive)
print("precision_tbr", precision_tbr)
precision_align = pm4py.evaluate_precision_alignments(
log1, petri_inductive, im_inductive, fm_inductive)
print("precision_align", precision_align)
print("log start activities = ", pm4py.get_start_activities(log2))
print("df start activities = ", pm4py.get_start_activities(df2))
print("log end activities = ", pm4py.get_end_activities(log2))
print("df end activities = ", pm4py.get_end_activities(df2))
print("log attributes = ", pm4py.get_attributes(log2))
print("df attributes = ", pm4py.get_attributes(df2))
print("log org:resource values = ",
pm4py.get_attribute_values(log2, "org:resource"))
print("df org:resource values = ",
pm4py.get_attribute_values(df2, "org:resource"))
print("start_activities len(filt_log) = ",
len(pm4py.filter_start_activities(log2, ["register request"])))
print("start_activities len(filt_df) = ",
len(pm4py.filter_start_activities(df2, ["register request"])))
print("end_activities len(filt_log) = ",
len(pm4py.filter_end_activities(log2, ["pay compensation"])))
print("end_activities len(filt_df) = ",
len(pm4py.filter_end_activities(df2, ["pay compensation"])))
print(
"attributes org:resource len(filt_log) (cases) cases = ",
len(
pm4py.filter_attribute_values(log2,
"org:resource", ["Ellen"],
level="case")))
print(
"attributes org:resource len(filt_log) (cases) events = ",
len(
pm4py.filter_attribute_values(log2,
"org:resource", ["Ellen"],
level="event")))
print(
"attributes org:resource len(filt_df) (events) cases = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="case")))
print(
"attributes org:resource len(filt_df) (events) events = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="event")))
print(
"attributes org:resource len(filt_df) (events) events notpositive = ",
len(
pm4py.filter_attribute_values(df2,
"org:resource", ["Ellen"],
level="event",
retain=False)))
print("variants log = ", pm4py.get_variants(log2))
print("variants df = ", pm4py.get_variants(df2))
print(
"variants filter log = ",
len(
pm4py.filter_variants(log2, [[
"register request", "examine thoroughly", "check ticket",
"decide", "reject request"
]])))
print(
"variants filter df = ",
len(
pm4py.filter_variants(df2, [[
"register request", "examine thoroughly", "check ticket",
"decide", "reject request"
]])))
print("variants filter percentage = ",
len(pm4py.filter_variants_percentage(log2, threshold=0.8)))
print(
"paths filter log len = ",
len(
pm4py.filter_directly_follows_relation(
log2, [("register request", "examine casually")])))
print(
"paths filter dataframe len = ",
len(
pm4py.filter_directly_follows_relation(
df2, [("register request", "examine casually")])))
print(
"timeframe filter log events len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="events")))
print(
"timeframe filter log traces_contained len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_contained")))
print(
"timeframe filter log traces_intersecting len = ",
len(
pm4py.filter_time_range(log2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_intersecting")))
print(
"timeframe filter df events len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="events")))
print(
"timeframe filter df traces_contained len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_contained")))
print(
"timeframe filter df traces_intersecting len = ",
len(
pm4py.filter_time_range(df2,
"2011-01-01 00:00:00",
"2011-02-01 00:00:00",
mode="traces_intersecting")))
# remove the temporary files
os.remove("ru1.xes")
os.remove("ru_dfg.dfg")
os.remove("ru_alpha.pnml")
os.remove("ru_inductive.pnml")
os.remove("ru_heuristics.pnml")
os.remove("ru_inductive.ptml")
os.remove("ru_alpha.png")
os.remove("ru_inductive.png")
os.remove("ru_heuristics.png")
os.remove("ru_inductive_tree.png")
os.remove("ru_heunet.png")
os.remove("ru_dfg.png")
def test_dfg_playout(self):
import pm4py
from pm4py.algo.simulation.playout.dfg import algorithm as dfg_playout
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
dfg, sa, ea = pm4py.discover_dfg(log)
dfg_playout.apply(dfg, sa, ea)
def test_filter_paths_percentage(self):
log = pm4py.read_xes("input_data/running-example.xes")
dfg, sa, ea = pm4py.discover_dfg(log)
act_count = pm4py.get_attribute_values(log, "concept:name")
pm4py.objects.dfg.filtering.dfg_filtering.filter_dfg_on_paths_percentage(
dfg, sa, ea, act_count, 0.3)
def test_dfg_playout(self):
import pm4py
from pm4py.objects.dfg.utils import dfg_playout
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
dfg, sa, ea = pm4py.discover_dfg(log)
dfg_playout.apply(dfg, sa, ea)
