def test_dfg(self):
log = pm4py.read_xes("input_data/running-example.xes")
dfg, sa, ea = pm4py.discover_dfg(log)
def test_precision_alignments(self):
log = pm4py.read_xes("input_data/running-example.xes")
net, im, fm = pm4py.discover_petri_net_inductive(log)
precision_ali = pm4py.precision_alignments(log, net, im, fm)
def test_convert_to_net_from_heu(self):
log = pm4py.read_xes("input_data/running-example.xes")
heu_net = pm4py.discover_heuristics_net(log)
net, im, fm = pm4py.convert_to_petri_net(heu_net)
self.assertTrue(isinstance(net, PetriNet))
def test_heuristics_miner_heu_net(self):
log = pm4py.read_xes("input_data/running-example.xes")
heu_net = pm4py.discover_heuristics_net(log)
def test_alignments(self):
log = pm4py.read_xes("input_data/running-example.xes")
net, im, fm = pm4py.discover_petri_net_inductive(log)
aligned_traces = pm4py.conformance_diagnostics_alignments(
log, net, im, fm)
def test_case_arrival(self):
import pm4py
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
avg = pm4py.get_case_arrival_average(log)
self.assertIsNotNone(avg)
def test_inductive_miner_noise(self):
log = pm4py.read_xes("input_data/running-example.xes")
net, im, fm = pm4py.discover_petri_net_inductive(log,
noise_threshold=0.5)
def execute_script():
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
rework = rework_get.apply(log)
print(rework)
def test_tree_align_receipt(self):
import pm4py
log = pm4py.read_xes("input_data/receipt.xes")
tree = pm4py.discover_process_tree_inductive(log, noise_threshold=0.2)
al = pm4py.conformance_diagnostics_alignments(log, tree)
Χρήση παραδοσιακών αλγορίθμων process mining.
"""
import pm4py
from pm4py.algo.filtering.log.timestamp import timestamp_filter
from pm4py.algo.discovery.alpha import algorithm as alpha_miner
from pm4py.algo.discovery.heuristics import algorithm as heuristics_miner
from pm4py.algo.discovery.inductive import algorithm as inductive_miner
from pm4py.visualization.petrinet import visualizer, parameters
from pm4py.algo.conformance.alignments import algorithm as alignment
from pm4py.objects.petri.align_utils import pretty_print_alignments
from contextlib import redirect_stdout
from pm4py.evaluation.simplicity import evaluator as simplicity_factory
from pm4py.evaluation.precision import evaluator as precision_evaluator
from pm4py.evaluation.replay_fitness import evaluator as fitness_evaluator
log = pm4py.read_xes(
r'C:\Users\user\Desktop\ΔΙΠΛΩΜΑΤΙΚΗ\12696884\BPI Challenge 2017.xes\BPI Challenge 2017.xes'
)
log_2 = log[:1000]
#log = log[:1000] Για να βρώ το Precision παιρνω 1000 traces γιατί αλλιώς κάνει πάνω από 2 ώρες για να το βρεί.
"""
ALPHA-MINER
"""
alpha_petri, initial_marking, final_marking = alpha_miner.apply(log)
gviz = visualizer.apply(alpha_petri, initial_marking, final_marking)
visualizer.view(gviz)
alpha_petri_2, initial_marking, final_marking = alpha_miner.apply(
log_2) # Για το precision
"""
HEURISTIC-MINER
def test_align(self):
log = pm4py.read_xes("input_data/running-example.xes")
net, im, fm = pm4py.discover_petri_net_inductive(log,
noise_threshold=0.2)
aligned_traces = alignments.apply(log, net, im, fm)
diagn_df = alignments.get_diagnostics_dataframe(log, aligned_traces)
def test_minimum_self_distance(self):
import pm4py
from pm4py.algo.discovery.minimum_self_distance import algorithm as minimum_self_distance
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
msd = minimum_self_distance.apply(log)
def test_log_to_trie(self):
import pm4py
from pm4py.algo.transformation.log_to_trie import algorithm as log_to_trie
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
trie = log_to_trie.apply(log)
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_marking_equation_net(self):
import pm4py
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
net, im, fm = pm4py.discover_petri_net_inductive(log)
pm4py.solve_marking_equation(net, im, fm)
def test_tree_align_reviewing(self):
import pm4py
log = pm4py.read_xes("compressed_input_data/04_reviewing.xes.gz")
tree = pm4py.discover_process_tree_inductive(log, noise_threshold=0.2)
al = pm4py.conformance_diagnostics_alignments(log, tree)
def test_discovery_inductive_bpmn(self):
import pm4py
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
bpmn_graph = pm4py.discover_bpmn_inductive(log)
self.assertIsNotNone(bpmn_graph)
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_efg(self):
log = pm4py.read_xes("input_data/running-example.xes")
pm4py.discover_eventually_follows_graph(log)
def execute_script():
log = pm4py.read_xes(os.path.join("..", "tests", "input_data", "interval_event_log.xes"))
print(cycle_time_get.apply(log, parameters={cycle_time_get.Parameters.START_TIMESTAMP_KEY: "start_timestamp",
cycle_time_get.Parameters.TIMESTAMP_KEY: "time:timestamp"}))
def test_inductive_miner_tree(self):
log = pm4py.read_xes("input_data/running-example.xes")
tree = pm4py.discover_process_tree_inductive(log)
tree = pm4py.discover_process_tree_inductive(log, noise_threshold=0.2)
def read_xes(path):
log = pm4py.read_xes(path)
from pm4py.objects.conversion.log import converter as log_converter
return log_converter.apply(log,
variant=log_converter.Variants.TO_DATA_FRAME)
def test_dfg(self):
log = pm4py.read_xes("input_data/running-example.xes")
dfg, sa, ea = pm4py.discover_directly_follows_graph(log)
def test_new_statistics_log(self):
log = pm4py.read_xes("input_data/running-example.xes")
pm4py.get_trace_attribute_values(log, "creator")
pm4py.discover_eventually_follows_graph(log)
pm4py.get_case_arrival_average(log)
def test_tbr(self):
log = pm4py.read_xes("input_data/running-example.xes")
net, im, fm = pm4py.discover_petri_net_inductive(log)
replayed_traces = pm4py.conformance_diagnostics_token_based_replay(
log, net, im, fm)
def test_serialization_log(self):
log = pm4py.read_xes("input_data/running-example.xes")
ser = pm4py.serialize(log)
log2 = pm4py.deserialize(ser)
def test_precision_tbr(self):
log = pm4py.read_xes("input_data/running-example.xes")
net, im, fm = pm4py.discover_petri_net_inductive(log)
precision_tbr = pm4py.precision_token_based_replay(log, net, im, fm)
def test_minimum_self_distance_2(self):
import pm4py
log = pm4py.read_xes(os.path.join("input_data", "running-example.xes"))
msd = pm4py.get_minimum_self_distance_witnesses(log)
def test_alpha_miner(self):
log = pm4py.read_xes("input_data/running-example.xes")
net, im, fm = pm4py.discover_petri_net_alpha(log)
def importLog(path, name):
log = pm.read_xes(os.path.join(path, name + ".xes"))
return log
