def execute_script():
log_input_directory = "xesinput"
all_logs_names = os.listdir(log_input_directory)
all_logs_names = [log for log in all_logs_names if ".xe" in log]
for logName in all_logs_names:
# logPath = os.path.join("..", "tests", "inputData", logName)
log_path = log_input_directory + "\\" + logName
log = xes_importer.apply(log_path)
print("\n\n")
print("log loaded")
print("Number of traces - ", len(log))
event_log = log_conversion.apply(
log, variant=log_conversion.TO_EVENT_STREAM)
print("Number of events - ", len(event_log))
print("Classifiers ", log.classifiers)
exp_log_name = "xescert_exportlogs" + "\\" + "exp_" + logName
print("exporting log", exp_log_name)
xes_exporter.apply(log, exp_log_name)
print("exported log", exp_log_name)
log, classifier_attr_key = insert_classifier.search_act_class_attr(log)
classifiers = list(log.classifiers.keys())
if classifier_attr_key is None and classifiers:
try:
print(classifiers)
log, classifier_attr_key = insert_classifier.insert_activity_classifier_attribute(
log, classifiers[0])
print(classifier_attr_key)
except:
print("exception in handling classifier")
if classifier_attr_key is None:
classifier_attr_key = "concept:name"
if len(event_log) > 0 and classifier_attr_key in event_log[0]:
parameters = {
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: classifier_attr_key
}
dfg = dfg_algorithm.apply(log, parameters=parameters)
gviz = dfg_vis.apply(dfg,
log=log,
variant="frequency",
parameters=parameters)
# dfg_vis.view(gviz)
dfg_vis.save(gviz,
"xescert_images\\" + logName.replace("xes", "png"))
print("Reimporting log file just exported - ", exp_log_name)
log = xes_importer.apply(exp_log_name)
print("log loaded", exp_log_name)
print("Number of traces - ", len(log))
event_log = log_conversion.apply(
log, variant=log_conversion.TO_EVENT_STREAM)
print("Number of events - ", len(event_log))
print("Classifiers ", log.classifiers)
def main_ts():
# specify path of training and test sets
train_path = '../data/BPIChallenge2011_training_0-80.xes'
test_path = '../data/BPIChallenge2011_testing_80-100.xes'
#import training log
train_log = xes_importer.apply(train_path)
activity_names_1 = get_activity_names(train_log)
#import test log
test_log = xes_importer.apply(test_path)
activity_names_2 = get_activity_names(test_log)
#create list of unique activities in all the dataset
activity_names = activity_names_1 + activity_names_2
activity_names = sorted(set(activity_names),
key=lambda x: activity_names.index(x))
#create list of unique timestamps in all the dataset
all_ts = get_ts_list(train_log) + get_ts_list(test_log)
all_ts = sorted(set(all_ts), key=lambda x: all_ts.index(x))
print('Number of features: %d' % len(activity_names))
print('Feature list: ', activity_names)
print("\n")
#obtain timestamp encoding for each case in the training log
enc_si_ts_train = []
for case_index, case in enumerate(train_log):
encoded_row = [case.attributes["concept:name"]]
enc_si_ts = encode_trace_simple_index_with_timestamp(
case, activity_names, all_ts)
encoded_row.extend(np.reshape(enc_si_ts, -1))
encoded_row.append(case.attributes["label"])
enc_si_ts_train.append(encoded_row)
#obtain timestamp encoding for each case in the test log
enc_si_ts_test = []
for case_index, case in enumerate(test_log):
encoded_row = [case.attributes["concept:name"]]
enc_si_ts = encode_trace_simple_index_with_timestamp(
case, activity_names, all_ts)
encoded_row.extend(np.reshape(enc_si_ts, -1))
encoded_row.append(case.attributes["label"])
enc_si_ts_test.append(encoded_row)
print("First case with timestamp informations: \n", enc_si_ts_train[0])
#create training dataframe with timestamp encoding
df_train = pd.DataFrame(data=enc_si_ts_train, columns=compute_columns())
print(df_train.head())
df_train.to_csv('train_si_ts.csv')
#create test dataframe with timestamp encoding
df_test = pd.DataFrame(data=enc_si_ts_test, columns=compute_columns())
print(df_test.head())
df_test.to_csv('test_si_ts.csv')
return df_train, df_test
def test_importing_xes(self):
from pm4py.objects.log.importer.xes import importer as xes_importer
log = xes_importer.apply(os.path.join("input_data",
"running-example.xes"),
variant=xes_importer.Variants.ITERPARSE)
log = xes_importer.apply(os.path.join("input_data",
"running-example.xes"),
variant=xes_importer.Variants.LINE_BY_LINE)
def main_si():
#----------->specify path of training and test sets
train_path = '../data/BPIChallenge2011_training_0-80.xes'
test_path = '../data/BPIChallenge2011_testing_80-100.xes'
#import training log
train_log = xes_importer.apply(train_path)
activity_names_1 = get_activity_names(train_log)
#import test log
test_log = xes_importer.apply(test_path)
activity_names_2 = get_activity_names(test_log)
#create list of unique activities in all the dataset
activity_names = activity_names_1 + activity_names_2
activity_names = sorted(set(activity_names),
key=lambda x: activity_names.index(x))
#obtain simple index encoding for each case in training log
train_encoded_log = []
for case_index, case in enumerate(train_log):
encoded_row = [case.attributes["concept:name"]]
encoded_row.extend(encode_trace_simple_index(case, activity_names))
encoded_row.append(case.attributes["label"])
train_encoded_log.append(encoded_row)
#obtain simple index encoding for each case in test log
test_encoded_log = []
for case_index, case in enumerate(test_log):
encoded_row = [case.attributes["concept:name"]]
encoded_row.extend(encode_trace_simple_index(case, activity_names))
encoded_row.append(case.attributes["label"])
test_encoded_log.append(encoded_row)
print('Number of features: %d' % len(activity_names))
print('Feature list: ', activity_names)
print("\n")
#check if all the cases have only 20 events
print(train_encoded_log[:4])
print(len(train_encoded_log))
for i in range(len(train_encoded_log)):
print(len(train_encoded_log[i]))
#create the dataframe for training set
train_df = pd.DataFrame(data=train_encoded_log, columns=compute_columns())
print(train_df.head())
train_df.to_csv("train_si.csv")
#create the dataframe for test set
test_df = pd.DataFrame(data=test_encoded_log, columns=compute_columns())
print(test_df.head())
test_df.to_csv("test_si.csv")
return train_df, test_df
def test_importExportXEStoXES(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"
log = xes_importer.apply(
os.path.join(INPUT_DATA_DIR, "running-example.xes"))
xes_exporter.apply(
log, os.path.join(OUTPUT_DATA_DIR, "running-example-exported.xes"))
log_imported_after_export = xes_importer.apply(
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.xes"))
self.assertEqual(len(log), len(log_imported_after_export))
os.remove(os.path.join(OUTPUT_DATA_DIR,
"running-example-exported.xes"))
def load_data():
"""Load and return example data.
Returns:
log (List[List[str]]): example log.
"""
# file path
absPath = os.path.abspath(__file__)
fileDir = os.path.dirname(absPath)
code = os.path.dirname(fileDir)
data = os.path.join(code, "data")
# load the first 2000 traces of the example log
variant = xes_importer.Variants.ITERPARSE
parameters = {variant.value.Parameters.MAX_TRACES: 2000}
log = xes_importer.apply(
os.path.join(data, "BPI_Challenge_2012.xes"),
variant=variant,
parameters=parameters,
)
# get log as format List[List[str]]
return [[event["concept:name"] for event in trace] for trace in log]
def test_log_skeleton(self):
log = xes_importer.apply(
os.path.join("input_data", "running-example.xes"))
from pm4py.algo.discovery.log_skeleton import algorithm as lsk_discovery
model = lsk_discovery.apply(log)
from pm4py.algo.conformance.log_skeleton import algorithm as lsk_conformance
conf = lsk_conformance.apply(log, model)
def import_log(self, complete_filename, filename):
# import the chosen event log and calculate some statistics
self.current_log = LogInfo(complete_filename, filename)
if '.xes' in complete_filename:
# Assume that it is a XES file
variant = xes_importer.Variants.ITERPARSE
parameters = {variant.value.Parameters.TIMESTAMP_SORT: True}
self.current_log.log = xes_importer.apply(complete_filename,
variant=variant,
parameters=parameters)
self.current_log.first_traces = log_converter.apply(
EventLog(self.current_log.log[0:self.MAX_TRACES]),
variant=log_converter.Variants.TO_DATA_FRAME)
self.current_log.median_case_duration = case_statistics.get_median_caseduration(
self.current_log.log,
parameters={
case_statistics.Parameters.TIMESTAMP_KEY: "time:timestamp"
})
self.current_log.median_case_duration_in_hours = self.current_log.median_case_duration / 60 / 60
self.current_log.total_of_cases = len(self.current_log.log)
self.current_log.total_of_events = len(self.current_log.log)
print(
f'Log [{filename}] - total of cases [{self.current_log.total_of_cases}] - median case duration '
f'[{self.current_log.median_case_duration / 60 / 60}hrs]')
def compute_alignment(xes_file, pnml_file):
"""
Compute alignments for event log with given model.
Save alignments results and all metrics during computation in a csv file.
Parameters
----------
xes_file : .xes file
The xes file of the event log
pnml_file : .pnml file
The petri net model
"""
event_log = xes_importer.apply(xes_file)
model_net, model_im, model_fm = petri_importer.apply(pnml_file)
# get log name and model name
log_name = Path(log_path).stem
model_name = Path(model_path).stem
# define the column name in result file
field_names = [
'case_id', 'total', 'heuristic', 'queue', 'states', 'arcs', 'sum',
'num_insert', 'num_removal', 'num_update', 'simple_lp', 'complex_lp',
'restart', 'split_num', 'trace_length', 'alignment_length', 'cost',
'alignment'
]
df = pd.DataFrame(columns=field_names)
trace_variant_lst = {}
# iterate every case in log
for case_index in tqdm(range(len(event_log))):
events_lst = []
for event in event_log[case_index]:
events_lst.append(event['concept:name'])
trace_str = ''.join(events_lst)
# if the sequence of events is met for the first time
if trace_str not in trace_variant_lst:
# construct synchronous product net
sync_product = SynchronousProduct(event_log[case_index], model_net,
model_im, model_fm)
initial_marking, final_marking, cost_function, incidence_matrix, trace_sync, trace_log \
= sync_product.construct_sync_product(event_log[case_index], model_net, model_im, model_fm)
# compute alignment with split-pint-based algorithm + caching strategy + reopen method
start_time = timeit.default_timer()
ali_with_split_astar = AlignmentWithCacheReopenAstar(
initial_marking, final_marking, cost_function,
incidence_matrix, trace_sync, trace_log)
alignment_result = ali_with_split_astar.search()
# get the total computation time
alignment_result['total'] = timeit.default_timer() - start_time
alignment_result['case_id'] = event_log[case_index].attributes[
'concept:name']
trace_variant_lst[trace_str] = alignment_result
else:
alignment_result = trace_variant_lst[trace_str]
alignment_result['case_id'] = event_log[case_index].attributes[
'concept:name']
df = df.append(alignment_result, ignore_index=True)
# The name of result csv file is of the form: 'log_name + model_name + algorithm type.csv'
df.to_csv('../results/log=' + log_name + '&model=' + model_name +
'&algorithm=cache_reopen_astar' + '.csv',
index=False)
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 read_xes(filename, p=1, n_DPI=False):
'''
read event log in xes format
input filename, percentage
output log object, variants_count
filename = filename in xes format
p = percentage of traces % to exploit from the log
'''
log = xes_importer.apply(filename)
if p < 1:
log = variants_filter.filter_log_variants_percentage(log, percentage=p)
# variants = variants_filter.get_variants(log)
variants = case_statistics.get_variant_statistics(log)
# #
VARIANT = []
for v in variants:
VARIANT.append(v['variant'])
#
# VARIANT = list(variants.keys())
if n_DPI:
VARIANT = VARIANT[:n_DPI]
log = variants_filter.apply(log, VARIANT)
print('=' * 100, '\n=READ THE XES FILE\n'
'length of log', len(log), '\nlength of event',
sum(len(trace) for trace in log),
'\nnumber of variants : {}'.format(len(VARIANT)))
return log, VARIANT
def read_xes(path: str) -> obj.EventStream:
"""
Reads the .xes file, extracts the events and preprocesses data for CDESF.
Parameters
--------------------------------------
path: str
File path and name
Returns
--------------------------------------
An event stream
"""
variant = xes_importer.Variants.ITERPARSE
parameters = {variant.value.Parameters.TIMESTAMP_SORT: True}
log_xes = xes_importer.apply(path, variant=variant, parameters=parameters)
event_stream = log_converter.apply(
log_xes,
variant=log_converter.Variants.TO_EVENT_STREAM,
parameters={
constants.PARAMETER_CONSTANT_CASEID_KEY: "case:concept:name",
constants.PARAMETER_CONSTANT_ACTIVITY_KEY: "concept:name",
constants.PARAMETER_CONSTANT_TIMESTAMP_KEY: "time:timestamp",
},
)
return event_stream
def execute_script():
log = xes_importer.apply(
os.path.join("..", "tests", "input_data", "running-example.xes"))
print(len(log))
log2 = func.filter_(lambda x: len(x) > 5, log)
print(type(log2))
print(len(log2))
def execute_script():
log = importer.apply(os.path.join("..", "tests", "input_data", "running-example.xes"))
tree = inductive_miner.apply_tree(log)
gviz1 = pt_vis_factory.apply(tree, parameters={"format": "svg"})
# pt_vis_factory.view(gviz1)
gviz2 = pt_visualizer.apply(tree, parameters={pt_visualizer.Variants.WO_DECORATION.value.Parameters.FORMAT: "svg"})
pt_visualizer.view(gviz2)
def evaluate_logwithmodel(logpath):
"""
Calculate and return evaluation measurements like fitness, precision, simplicity and generalization, given the path
of event log.
Parameters:
logpath (str): Path of event log
Returns:
fitness (float): Fitness value measured using pm4py
precision (float): Precision value measured using pm4py
simplicity (float): Simplicity value measured using pm4py
generalization (float): Generalization value measured using pm4py
"""
xes_log = importer.apply(logpath)
net, initial_marking, final_marking = inductive_miner.apply(xes_log)
fitness = replay_fitness_evaluator.apply(
xes_log,
net,
initial_marking,
final_marking,
variant=replay_fitness_evaluator.Variants.TOKEN_BASED)
prec = precision_evaluator.apply(
xes_log,
net,
initial_marking,
final_marking,
variant=precision_evaluator.Variants.ETCONFORMANCE_TOKEN)
simp = simplicity_evaluator.apply(net)
gen = generalization_evaluator.apply(xes_log, net, initial_marking,
final_marking)
return round(fitness['log_fitness'],
3), round(prec, 3), round(simp, 3), round(gen, 3)
def test_playout_tree_basic(self):
log = xes_importer.apply(
os.path.join("input_data", "running-example.xes"))
from pm4py.algo.discovery.inductive import algorithm as inductive_miner
tree = inductive_miner.apply_tree(log)
from pm4py.simulation.tree_playout import algorithm as tree_playout
new_log = tree_playout.apply(tree)
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 test_importingPetriLogAlignment(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"
imported_petri1, marking1, fmarking1 = petri_importer.apply(
os.path.join(INPUT_DATA_DIR, "running-example.pnml"))
log = xes_importer.apply(
os.path.join(INPUT_DATA_DIR, "running-example.xes"))
final_marking = petri.petrinet.Marking()
for p in imported_petri1.places:
if not p.out_arcs:
final_marking[p] = 1
for trace in log:
cf_result = align_alg.apply(
trace,
imported_petri1,
marking1,
final_marking,
variant=align_alg.VERSION_DIJKSTRA_NO_HEURISTICS)['alignment']
is_fit = True
for couple in cf_result:
if not (couple[0] == couple[1]
or couple[0] == ">>" and couple[1] is None):
is_fit = False
if not is_fit:
raise Exception("should be fit")
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_48(self):
import os
from pm4py.objects.log.importer.xes import importer as xes_importer
from pm4py.algo.discovery.alpha import algorithm as alpha_miner
log = xes_importer.apply(os.path.join("input_data", "running-example.xes"))
parameters = {alpha_miner.Variants.ALPHA_VERSION_CLASSIC.value.Parameters.ACTIVITY_KEY: "concept:name"}
net, initial_marking, final_marking = alpha_miner.apply(log, parameters=parameters)
def execute_script():
log = importer.apply(os.path.join("..", "tests", "input_data", "running-example.xes"))
net, im, fm = inductive_miner.apply(log)
aligned_traces = alignments.apply(log, net, im, fm)
gviz = visualizer.apply(log, aligned_traces,
parameters={visualizer.Variants.CLASSIC.value.Parameters.FORMAT: "svg"})
visualizer.view(gviz)
def test_58(self):
import os
from pm4py.objects.log.importer.xes import importer as xes_importer
from pm4py.algo.discovery.inductive import algorithm as inductive_miner
log = xes_importer.apply(os.path.join("input_data", "running-example.xes"))
net, initial_marking, final_marking = inductive_miner.apply(log)
from pm4py.algo.conformance.alignments import algorithm as alignments
model_cost_function = dict()
sync_cost_function = dict()
for t in net.transitions:
# if the label is not None, we have a visible transition
if t.label is not None:
# associate cost 1000 to each move-on-model associated to visible transitions
model_cost_function[t] = 1000
# associate cost 0 to each move-on-log
sync_cost_function[t] = 0
else:
# associate cost 1 to each move-on-model associated to hidden transitions
model_cost_function[t] = 1
parameters = {}
parameters[
alignments.Variants.VERSION_STATE_EQUATION_A_STAR.value.Parameters.PARAM_MODEL_COST_FUNCTION] = model_cost_function
parameters[
alignments.Variants.VERSION_STATE_EQUATION_A_STAR.value.Parameters.PARAM_SYNC_COST_FUNCTION] = sync_cost_function
alignments = alignments.apply_log(log, net, initial_marking, final_marking, parameters=parameters)
def test_playout(self):
log = xes_importer.apply(
os.path.join("input_data", "running-example.xes"))
from pm4py.algo.discovery.alpha import algorithm as alpha_miner
net, im, fm = alpha_miner.apply(log)
from pm4py.simulation.playout import simulator
log2 = simulator.apply(net, im, fm)
def test_61(self):
import os
from pm4py.objects.log.importer.xes import importer as xes_importer
log = xes_importer.apply(os.path.join("input_data", "roadtraffic50traces.xes"))
from pm4py.objects.log.util import get_log_representation
str_trace_attributes = []
str_event_attributes = ["concept:name"]
num_trace_attributes = []
num_event_attributes = ["amount"]
data, feature_names = get_log_representation.get_representation(log, str_trace_attributes, str_event_attributes,
num_trace_attributes, num_event_attributes)
data, feature_names = get_log_representation.get_default_representation(log)
from pm4py.objects.log.util import get_class_representation
target, classes = get_class_representation.get_class_representation_by_trace_duration(log, 2 * 8640000)
from sklearn import tree
clf = tree.DecisionTreeClassifier()
clf.fit(data, target)
from pm4py.visualization.decisiontree import visualizer as dectree_visualizer
gviz = dectree_visualizer.apply(clf, feature_names, classes)
def test_alignment(self):
log = xes_importer.apply(
os.path.join("input_data", "running-example.xes"))
from pm4py.algo.discovery.alpha import algorithm as alpha_miner
net, im, fm = alpha_miner.apply(log)
from pm4py.algo.conformance.alignments import algorithm as alignments
aligned_traces = alignments.apply(
log,
net,
im,
fm,
variant=alignments.Variants.VERSION_STATE_EQUATION_A_STAR)
aligned_traces = alignments.apply(
log,
net,
im,
fm,
variant=alignments.Variants.VERSION_DIJKSTRA_NO_HEURISTICS)
from pm4py.evaluation.replay_fitness import evaluator as rp_fitness_evaluator
fitness = rp_fitness_evaluator.apply(
log,
net,
im,
fm,
variant=rp_fitness_evaluator.Variants.ALIGNMENT_BASED)
evaluation = rp_fitness_evaluator.evaluate(
aligned_traces,
variant=rp_fitness_evaluator.Variants.ALIGNMENT_BASED)
from pm4py.evaluation.precision import evaluator as precision_evaluator
precision = precision_evaluator.apply(
log,
net,
im,
fm,
variant=rp_fitness_evaluator.Variants.ALIGNMENT_BASED)
def execute_script():
log = xes_importer.apply(
os.path.join("..", "tests", "input_data", "running-example.xes"))
frequency_dfg = dfg_miner.apply(log, variant=dfg_miner.Variants.FREQUENCY)
net, im, fm = dfg_conv.apply(frequency_dfg)
# perform the Montecarlo simulation with the arrival rate inferred by the log (the simulation lasts 5 secs)
parameters = {}
parameters[montecarlo_simulation.Variants.PETRI_SEMAPH_FIFO.value.
Parameters.TOKEN_REPLAY_VARIANT] = Variants.BACKWARDS
parameters[montecarlo_simulation.Variants.PETRI_SEMAPH_FIFO.value.
Parameters.PARAM_ENABLE_DIAGNOSTICS] = False
parameters[montecarlo_simulation.Variants.PETRI_SEMAPH_FIFO.value.
Parameters.PARAM_MAX_THREAD_EXECUTION_TIME] = 5
log, res = montecarlo_simulation.apply(log,
net,
im,
fm,
parameters=parameters)
print(
"\n(Montecarlo - Petri net) case arrival ratio inferred from the log")
print(res["median_cases_ex_time"])
print(res["total_cases_time"])
# perform the Montecarlo simulation with the arrival rate specified (the simulation lasts 5 secs)
parameters[montecarlo_simulation.Variants.PETRI_SEMAPH_FIFO.value.
Parameters.PARAM_CASE_ARRIVAL_RATIO] = 60
log, res = montecarlo_simulation.apply(log,
net,
im,
fm,
parameters=parameters)
print(
"\n(Montecarlo - Petri net) case arrival ratio specified by the user")
print(res["median_cases_ex_time"])
print(res["total_cases_time"])
def test_tokenreplay(self):
log = xes_importer.apply(
os.path.join("input_data", "running-example.xes"))
from pm4py.algo.discovery.alpha import algorithm as alpha_miner
net, im, fm = alpha_miner.apply(log)
from pm4py.algo.conformance.tokenreplay import algorithm as token_replay
replayed_traces = token_replay.apply(
log, net, im, fm, variant=token_replay.Variants.TOKEN_REPLAY)
replayed_traces = token_replay.apply(
log, net, im, fm, variant=token_replay.Variants.BACKWARDS)
from pm4py.evaluation.replay_fitness import evaluator as rp_fitness_evaluator
fitness = rp_fitness_evaluator.apply(
log,
net,
im,
fm,
variant=rp_fitness_evaluator.Variants.TOKEN_BASED)
evaluation = rp_fitness_evaluator.evaluate(
replayed_traces, variant=rp_fitness_evaluator.Variants.TOKEN_BASED)
from pm4py.evaluation.precision import evaluator as precision_evaluator
precision = precision_evaluator.apply(
log,
net,
im,
fm,
variant=precision_evaluator.Variants.ETCONFORMANCE_TOKEN)
from pm4py.evaluation.generalization import evaluator as generalization_evaluation
generalization = generalization_evaluation.apply(
log,
net,
im,
fm,
variant=generalization_evaluation.Variants.GENERALIZATION_TOKEN)
def execute_script():
# import the log
log_path = os.path.join("..", "tests", "input_data", "receipt.xes")
log = xes_importer.apply(log_path)
# apply Inductive Miner
net, initial_marking, final_marking = inductive_miner.apply(log)
# get visualization
variant = pn_vis.Variants.PERFORMANCE
parameters_viz = {
pn_vis.Variants.PERFORMANCE.value.Parameters.AGGREGATION_MEASURE:
"mean",
pn_vis.Variants.PERFORMANCE.value.Parameters.FORMAT: "svg"
}
gviz = pn_vis.apply(net,
initial_marking,
final_marking,
log=log,
variant=variant,
parameters=parameters_viz)
pn_vis.view(gviz)
# do another visualization with frequency
variant = pn_vis.Variants.FREQUENCY
parameters_viz = {pn_vis.Variants.FREQUENCY.value.Parameters.FORMAT: "svg"}
gviz = pn_vis.apply(net,
initial_marking,
final_marking,
log=log,
variant=variant,
parameters=parameters_viz)
pn_vis.view(gviz)
def test_alignment(self):
log = xes_importer.apply(os.path.join("input_data", "running-example.xes"))
from pm4py.algo.discovery.alpha import algorithm as alpha_miner
net, im, fm = alpha_miner.apply(log)
from pm4py.algo.conformance.alignments import algorithm as alignments
aligned_traces = alignments.apply(log, net, im, fm, variant=alignments.Variants.VERSION_STATE_EQUATION_A_STAR)
aligned_traces = alignments.apply(log, net, im, fm, variant=alignments.Variants.VERSION_DIJKSTRA_NO_HEURISTICS)
def test_performance_spectrum(self):
log = xes_importer.apply(os.path.join("input_data", "running-example.xes"))
from pm4py.algo.discovery.performance_spectrum import algorithm as pspectrum
ps = pspectrum.apply(log, ["register request", "decide"])
df = pd.read_csv(os.path.join("input_data", "running-example.csv"))
df = dataframe_utils.convert_timestamp_columns_in_df(df)
ps = pspectrum.apply(df, ["register request", "decide"])