def test_importExportCSVtoCSV(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"
event_log = csv_importer.import_event_stream(
os.path.join(INPUT_DATA_DIR, "running-example.csv"))
event_log = sorting.sort_timestamp(event_log)
event_log = sampling.sample(event_log)
event_log = index_attribute.insert_event_index_as_event_attribute(
event_log)
log = log_conv_fact.apply(event_log)
log = sorting.sort_timestamp(log)
log = sampling.sample(log)
log = index_attribute.insert_trace_index_as_event_attribute(log)
event_log_transformed = log_conv_fact.apply(
log, variant=log_conv_fact.TO_EVENT_STREAM)
csv_exporter.export(
event_log_transformed,
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
event_log_imported_after_export = csv_importer.import_event_stream(
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
log_imported_after_export = log_conv_fact.apply(
event_log_imported_after_export)
self.assertEqual(len(log), len(log_imported_after_export))
os.remove(os.path.join(OUTPUT_DATA_DIR,
"running-example-exported.csv"))
def test_csv1documentation(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"
import os
from pm4py.objects.log.importer.csv import factory as csv_importer
event_log = csv_importer.import_event_stream(
os.path.join("input_data", "running-example.csv"))
event_log_length = len(event_log)
del event_log_length
from pm4py.objects.log import transform
log = transform.transform_event_stream_to_event_log(
event_log, case_glue="case:concept:name")
del log
from pm4py.objects.log.importer.csv.versions import pandas_df_imp
dataframe = pandas_df_imp.import_dataframe_from_path(
os.path.join("input_data", "running-example.csv"))
event_log = log_conv_fact.apply(dataframe,
variant=log_conv_fact.TO_EVENT_STREAM)
log = log_conv_fact.apply(event_log)
from pm4py.objects.log.exporter.csv import factory as csv_exporter
csv_exporter.export(event_log, "outputFile1.csv")
os.remove("outputFile1.csv")
from pm4py.objects.log.exporter.csv import factory as csv_exporter
csv_exporter.export(log, "outputFile2.csv")
os.remove("outputFile2.csv")
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.import_log(log_path)
print("\n\n")
print("log loaded")
print("Number of traces - ", len(log))
event_log = log_conv_fact.apply(log,
variant=log_conv_fact.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.export_log(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_factory.apply(log, parameters=parameters)
gviz = dfg_vis_factory.apply(dfg,
log=log,
variant="frequency",
parameters=parameters)
# dfg_vis_factory.view(gviz)
dfg_vis_factory.save(
gviz, "xescert_images\\" + logName.replace("xes", "png"))
print("Reimporting log file just exported - ", exp_log_name)
log = xes_importer.import_log(exp_log_name)
print("log loaded", exp_log_name)
print("Number of traces - ", len(log))
event_log = log_conv_fact.apply(log,
variant=log_conv_fact.TO_EVENT_STREAM)
print("Number of events - ", len(event_log))
print("Classifiers ", log.classifiers)
def apply_events(log, dt1, dt2, parameters=None):
"""
Get a new log containing all the events contained in the given interval
Parameters
-----------
log
Log
dt1
Lower bound to the interval
dt2
Upper bound to the interval
parameters
Possible parameters of the algorithm, including:
timestamp_key -> Attribute to use as timestamp
Returns
------------
filtered_log
Filtered log
"""
if parameters is None:
parameters = {}
timestamp_key = parameters[
PARAMETER_CONSTANT_TIMESTAMP_KEY] if PARAMETER_CONSTANT_TIMESTAMP_KEY in parameters else DEFAULT_TIMESTAMP_KEY
dt1 = get_dt_from_string(dt1)
dt2 = get_dt_from_string(dt2)
stream = log_converter.apply(log, variant=log_converter.TO_EVENT_STREAM)
filtered_stream = EventStream([x for x in stream if dt1 < x[timestamp_key].replace(tzinfo=None) < dt2])
filtered_log = log_converter.apply(filtered_stream)
return filtered_log
def test_importExportXEStoCSV(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.import_log(os.path.join(INPUT_DATA_DIR, "running-example.xes"))
event_log = log_conv_fact.apply(log, variant=log_conv_fact.TO_EVENT_STREAM)
csv_exporter.export(event_log, os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
event_log_newimport = csv_importer.import_event_stream(
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
log_imported_after_export = log_conv_fact.apply(event_log_newimport)
self.assertEqual(len(log), len(log_imported_after_export))
os.remove(os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
def test_prefiltering_dataframe(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"
input_log = os.path.join(INPUT_DATA_DIR, "running-example.csv")
dataframe = csv_import_adapter.import_dataframe_from_path_wo_timeconversion(input_log, sep=',')
dataframe = attributes_filter.filter_df_keeping_spno_activities(dataframe, activity_key="concept:name")
dataframe = case_filter.filter_on_ncases(dataframe, case_id_glue="case:concept:name")
dataframe = csv_import_adapter.convert_timestamp_columns_in_df(dataframe)
dataframe = dataframe.sort_values('time:timestamp')
event_log = log_conv_fact.apply(dataframe, variant=log_conv_fact.TO_EVENT_STREAM)
log = log_conv_fact.apply(event_log)
del log
def test_xesimp_csvexp(self):
log0 = xes_importer.apply(
os.path.join("input_data", "running-example.xes"))
log = log_conv_factory.apply(log0,
variant=log_conv_factory.TO_EVENT_LOG)
stream = log_conv_factory.apply(
log0, variant=log_conv_factory.TO_EVENT_STREAM)
df = log_conv_factory.apply(log0,
variant=log_conv_factory.TO_DATAFRAME)
csv_exporter_factory.export(log, "ru.csv")
csv_exporter_factory.export(stream, "ru.csv")
csv_exporter_factory.export(df, "ru.csv")
os.remove('ru.csv')
def test_pdimp_xesexp(self):
log0 = csv_import_adapter.import_dataframe_from_path(
os.path.join("input_data", "running-example.csv"))
log = log_conv_factory.apply(log0,
variant=log_conv_factory.TO_EVENT_LOG)
stream = log_conv_factory.apply(
log0, variant=log_conv_factory.TO_EVENT_STREAM)
df = log_conv_factory.apply(log0,
variant=log_conv_factory.TO_DATAFRAME)
xes_exporter_factory.apply(log, "ru.xes")
xes_exporter_factory.apply(stream, "ru.xes")
xes_exporter_factory.apply(df, "ru.xes")
os.remove('ru.xes')
def apply_events(log, values, parameters=None):
"""
Filter log by keeping only events with an attribute value that belongs to the provided values list
Parameters
-----------
log
log
values
Allowed attributes
parameters
Parameters of the algorithm, including:
activity_key -> Attribute identifying the activity in the log
positive -> Indicate if events should be kept/removed
Returns
-----------
filtered_log
Filtered log
"""
if parameters is None:
parameters = {}
attribute_key = parameters[
PARAMETER_CONSTANT_ATTRIBUTE_KEY] if PARAMETER_CONSTANT_ATTRIBUTE_KEY in parameters else DEFAULT_NAME_KEY
positive = parameters["positive"] if "positive" in parameters else True
stream = log_conv_fact.apply(log, variant=log_conv_fact.TO_EVENT_STREAM)
if positive:
stream = EventStream(
list(filter(lambda x: x[attribute_key] in values, stream)))
else:
stream = EventStream(
list(filter(lambda x: x[attribute_key] not in values, stream)))
filtered_log = log_conv_fact.apply(stream)
# filtered_log = EventLog()
# for trace in log:
# new_trace = Trace()
# for j in range(len(trace)):
# if attribute_key in trace[j]:
# attribute_value = trace[j][attribute_key]
# if (positive and attribute_value in values) or (not positive and attribute_value not in values):
# new_trace.append(trace[j])
# if len(new_trace) > 0:
# for attr in trace.attributes:
# new_trace.attributes[attr] = trace.attributes[attr]
# filtered_log.append(new_trace)
return filtered_log
def apply(log, parameters=None, variant=HANDOVER):
"""
Calculates a SNA metric
Parameters
------------
log
Log
parameters
Possible parameters of the algorithm
variant
Variant of the algorithm to apply. Possible values:
handover, working_together
Returns
-----------
tuple
Tuple containing the metric matrix and the resources list
"""
if parameters is None:
parameters = {}
if variant in VERSIONS_LOG:
log = conv_factory.apply(log, parameters=parameters)
return VERSIONS_LOG[variant](log, parameters=parameters)
raise Exception("metric not implemented yet")
def apply(obj,
petri_net,
initial_marking,
final_marking,
parameters=None,
version=VERSION_STATE_EQUATION_A_STAR):
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_util.DEFAULT_TIMESTAMP_KEY
if pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_CASEID_KEY] = log_util.CASE_ATTRIBUTE_GLUE
if isinstance(obj, pm4py.objects.log.log.Trace):
return apply_trace(obj, petri_net, initial_marking, final_marking,
parameters, version)
else:
return apply_log(
log_converter.apply(obj, parameters, log_converter.TO_EVENT_LOG),
petri_net, initial_marking, final_marking, parameters, version)
def apply(log, parameters=None, variant=DEFAULT_VARIANT):
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_util.DEFAULT_TIMESTAMP_KEY
if pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_CASEID_KEY] = log_util.CASE_ATTRIBUTE_GLUE
if isinstance(log, pandas.core.frame.DataFrame):
dfg = df_statistics.get_dfg_graph(
log,
case_id_glue=parameters[
pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY],
activity_key=parameters[
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY],
timestamp_key=parameters[
pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY])
return VERSIONS_DFG[variant](dfg, parameters=parameters)
return VERSIONS[variant](log_conversion.apply(log, parameters,
log_conversion.TO_EVENT_LOG),
parameters)
def apply(log, parameters=None, version=ALPHA_VERSION_CLASSIC):
"""
Apply the Alpha Miner on top of a trace log
Parameters
-----------
log
Trace log
version
Variant of the algorithm to use (classic)
parameters
Possible parameters of the algorithm, including:
activity key -> Name of the attribute that contains the activity
Returns
-----------
net
Petri net
marking
Initial marking
final_marking
Final marking
"""
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
return VERSIONS[version](log_conversion.apply(log, parameters,
log_conversion.TO_TRACE_LOG),
parameters)
def download_csv_log(self):
"""
Downloads the CSV log as string
"""
dataframe = conversion_factory.apply(self.log, variant=conversion_factory.TO_DATAFRAME)
log_string = dataframe.to_string()
return log_string
def generate_xes_from_dataframe(dataframe):
try:
# convert the csv imported in dataframe to xes log
xes_log = conversion_factory.apply(dataframe)
return xes_log
except Error:
print("Invalid input")
def transient_analysis_from_dataframe(df, delay, parameters=None):
"""
Gets the transient analysis from a dataframe and a delay
Parameters
-------------
df
Pandas dataframe
delay
Time delay
parameters
Parameters of the algorithm
Returns
-------------
transient_result
Transient analysis result
"""
if parameters is None:
parameters = {}
activity_key = parameters[
constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
case_id_glue = parameters[
constants.
PARAMETER_CONSTANT_CASEID_KEY] if constants.PARAMETER_CONSTANT_CASEID_KEY in parameters else CASE_CONCEPT_NAME
timestamp_key = parameters[
constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] if constants.PARAMETER_CONSTANT_TIMESTAMP_KEY in parameters else xes.DEFAULT_TIMESTAMP_KEY
log = log_conv_factory.apply(df,
variant=log_conv_factory.DF_TO_EVENT_LOG_1V,
parameters=parameters)
# gets the simple Petri net through simple miner
net, im, fm = simple_factory.apply(log,
parameters=parameters,
classic_output=True)
activities_count = dict(df.groupby(activity_key).size())
dfg_performance = df_statistics.get_dfg_graph(df,
measure="performance",
perf_aggregation_key="mean",
case_id_glue=case_id_glue,
activity_key=activity_key,
timestamp_key=timestamp_key)
spaths = get_shortest_paths(net)
aggregated_statistics = get_decorations_from_dfg_spaths_acticount(
net, dfg_performance, spaths, activities_count, variant="performance")
# gets the stochastic map out of the dataframe and the Petri net
s_map = smap_builder.get_map_exponential_from_aggstatistics(
aggregated_statistics, parameters=parameters)
return transient_analysis_from_petri_net_and_smap(net,
im,
s_map,
delay,
parameters=parameters)
def get_kde_date_attribute_json(log, attribute=DEFAULT_TIMESTAMP_KEY, parameters=None):
"""
Gets the KDE estimation for the distribution of a date attribute values
(expressed as JSON)
Parameters
-------------
log
Event stream object (if log, is converted)
attribute
Date attribute to analyse
parameters
Possible parameters of the algorithm, including:
graph_points -> number of points to include in the graph
Returns
--------------
x
X-axis values to represent
y
Y-axis values to represent
"""
if type(log) is EventLog:
event_log = log_conv_fact.apply(log, variant=log_conv_fact.TO_EVENT_STREAM)
else:
event_log = log
values = [event[attribute].replace(tzinfo=None) for event in event_log if attribute in event]
return attributes_common.get_kde_date_attribute_json(values, parameters=parameters)
def get_kde_numeric_attribute(log, attribute, parameters=None):
"""
Gets the KDE estimation for the distribution of a numeric attribute values
Parameters
-------------
log
Event stream object (if log, is converted)
attribute
Numeric attribute to analyse
parameters
Possible parameters of the algorithm, including:
graph_points -> number of points to include in the graph
Returns
--------------
x
X-axis values to represent
y
Y-axis values to represent
"""
if type(log) is EventLog:
event_log = log_conv_fact.apply(log, variant=log_conv_fact.TO_EVENT_STREAM)
else:
event_log = log
values = [event[attribute] for event in event_log if attribute in event]
return attributes_common.get_kde_numeric_attribute(values, parameters=parameters)
def apply(log, parameters=None, variant=CLASSIC):
"""
Discovers a Petri net using Heuristics Miner
Parameters
------------
log
Event log
parameters
Possible parameters of the algorithm,
including: activity_key, case_id_glue, timestamp_key,
dependency_thresh, and_measure_thresh, min_act_count, min_dfg_occurrences, dfg_pre_cleaning_noise_thresh,
loops_length_two_thresh
variant
Variant of the algorithm (classic)
Returns
------------
net
Petri net
im
Initial marking
fm
Final marking
"""
if isinstance(log, pandas.core.frame.DataFrame):
return VERSIONS_PANDAS[variant](log, parameters=parameters)
return VERSIONS[variant](conv_factory.apply(log, parameters=parameters),
parameters=parameters)
def convert_to_log(frame: DataFrame) -> EventLog:
"""
Converts a DataFrame to an EventLog.
:param frame: the DataFrame
:return: the resulting EventLog
"""
return event_log_factory.apply(frame)
def apply(log, parameters=None):
"""
Gets the roles (group of different activities done by similar resources)
out of the log
Parameters
-------------
log
Log object
parameters
Possible parameters of the algorithm
Returns
------------
roles
List of different roles inside the log
"""
if parameters is None:
parameters = {}
resource_key = parameters[
constants.
PARAMETER_CONSTANT_RESOURCE_KEY] if constants.PARAMETER_CONSTANT_RESOURCE_KEY in parameters else xes.DEFAULT_RESOURCE_KEY
activity_key = parameters[
constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
stream = log_conv_factory.apply(log,
variant=log_conv_factory.TO_EVENT_STREAM)
activity_resource_couples = Counter(
(event[resource_key], event[activity_key]) for event in stream)
return algorithm.apply(activity_resource_couples, parameters=parameters)
def apply(log,
petri_net,
initial_marking,
final_marking,
parameters=None,
variant="token_replay"):
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_util.DEFAULT_TIMESTAMP_KEY
if pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_CASEID_KEY] = log_util.CASE_ATTRIBUTE_GLUE
return VERSIONS[variant](log_conversion.apply(log, parameters,
log_conversion.TO_EVENT_LOG),
petri_net,
initial_marking,
final_marking,
parameters=parameters)
def get_variants_matrix(log, parameters=None):
"""
Gets the variants matrix from a log object
Parameters
-------------
log
Log
parameters
Parameters of the algorithm: activity_key
Returns
-------------
variants_matrix
Variants matrix
activities
Sorted (by name) activities of the log
"""
if parameters is None:
parameters = {}
activity_key = parameters[
constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
parameters[constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = activity_key
parameters[constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = activity_key
if type(log) is EventStream:
log = conversion_factory.apply(log, parameters=parameters)
variants_list = get_variants_list(log, parameters=parameters)
activities = get_activities_list(log, parameters=parameters)
return get_variants_matrix_from_variants_list(variants_list,
activities,
parameters=parameters)
def table_to_log(table, parameters=None):
"""
Converts a Pyarrow table to an event log
Parameters
------------
table
Pyarrow table
parameters
Possible parameters of the algorithm
"""
if parameters is None:
parameters = {}
dict0 = table.to_pydict()
keys = list(dict0.keys())
# for legacy format support
if LEGACY_PARQUET_CASECONCEPTNAME in keys:
for key in keys:
dict0[key.replace(LEGACY_PARQUET_TP_REPLACER,
":")] = dict0.pop(key)
stream = EventStream([dict(zip(dict0, i)) for i in zip(*dict0.values())])
return log_conv_factory.apply(stream, parameters=parameters)
def export_log_tree(log):
"""
Get XES log XML tree from a PM4Py log
Parameters
-----------
log
PM4Py log
Returns
-----------
tree
XML tree
"""
# If the log is in log_instance.EventStream, then transform it into log_instance.EventLog format
if type(log) is log_instance.EventStream:
log = log_converter.apply(log)
root = etree.Element(xes_util.TAG_LOG)
# add attributes at the log level
export_attributes(log, root)
# add extensions at the log level
export_extensions(log, root)
# add globals at the log level
export_globals(log, root)
# add classifiers at the log level
export_classifiers(log, root)
# add traces at the log level
export_traces(log, root)
tree = etree.ElementTree(root)
return tree
def apply(log,
net,
initial_marking,
final_marking,
parameters=None,
variant="token_replay"):
"""
Factory method to apply token-based replay
Parameters
-----------
log
Log
net
Petri net
initial_marking
Initial marking
final_marking
Final marking
parameters
Parameters of the algorithm, including:
pm4py.util.constants.PARAMETER_CONSTANT_ACTIVITY_KEY -> Activity key
variant
Variant of the algorithm to use
"""
return VERSIONS[variant](log_converter.apply(log, parameters,
log_converter.TO_TRACE_LOG),
net,
initial_marking,
final_marking,
parameters=parameters)
def apply_numeric_events(log, int1, int2, parameters=None):
"""
Apply a filter on events (numerical filter)
Parameters
--------------
log
Log
int1
Lower bound of the interval
int2
Upper bound of the interval
parameters
Possible parameters of the algorithm:
PARAMETER_CONSTANT_ATTRIBUTE_KEY => indicates which attribute to filter
positive => keep or remove traces with such events?
Returns
--------------
filtered_log
Filtered log
"""
if parameters is None:
parameters = {}
attribute_key = parameters[
PARAMETER_CONSTANT_ATTRIBUTE_KEY] if PARAMETER_CONSTANT_ATTRIBUTE_KEY in parameters else DEFAULT_NAME_KEY
positive = parameters["positive"] if "positive" in parameters else True
stream = log_conv_fact.apply(log, variant=log_conv_fact.TO_EVENT_STREAM)
if positive:
stream = EventStream(
list(
filter(
lambda x: attribute_key in x and int1 <= x[attribute_key]
<= int2, stream)))
else:
stream = EventStream(
list(
filter(
lambda x: attribute_key in x and
(x[attribute_key] < int1 or x[attribute_key] > int2),
stream)))
filtered_log = log_conv_fact.apply(stream)
return filtered_log
def import_event_stream(path, parameters=None):
"""
Imports a CSV file from the given path
Parameters
----------
path:
Input CSV file path
parameters
Parameters of the algorithm, including
sep -> column separator
quotechar -> (if specified) Character that starts/end big strings in CSV
nrows -> (if specified) Maximum number of rows to read from the CSV
sort -> Boolean value that tells if the CSV should be ordered
sort_field -> If sort option is enabled, then the CSV is automatically sorted by the specified column
Returns
-------
log : :class:`pm4py.log.log.EventLog`
An event log
"""
sep = ","
quotechar = None
nrows = None
sort = False
sort_field = "time:timestamp"
insert_event_indexes = False
timest_format = None
timest_columns = None
if parameters is None:
parameters = {}
if "sep" in parameters:
sep = parameters["sep"]
if "quotechar" in parameters:
quotechar = parameters["quotechar"]
if "nrows" in parameters:
nrows = parameters["nrows"]
if "sort" in parameters:
sort = parameters["sort"]
if "sort_field" in parameters:
sort_field = parameters["sort_field"]
if "insert_event_indexes" in parameters:
insert_event_indexes = parameters["insert_event_indexes"]
if "timest_format" in parameters:
timest_format = parameters["timest_format"]
if "timest_columns" in parameters:
timest_columns = parameters["timest_columns"]
df = import_dataframe_from_path(path, sep=sep, quotechar=quotechar, nrows=nrows, sort=sort, sort_field=sort_field,
timest_format=timest_format, timest_columns=timest_columns)
event_log = log_conv_fact.apply(df, variant=log_conv_fact.TO_EVENT_STREAM)
if insert_event_indexes:
event_log.insert_event_index_as_event_attribute()
return event_log
def convert(self, filePath):
"""
function that converts csv files into event logs
:param filePath: the path to the file
:return: event log
"""
csvEventStream = csv_importer.import_event_stream(filePath)
return conversion_factory.apply(csvEventStream)
def apply(log, parameters=None, variant=DFG_NATIVE):
"""
Calculates DFG graph (frequency or performance) starting from a log
Parameters
----------
log
Log
parameters
Possible parameters passed to the algorithms:
aggregationMeasure -> performance aggregation measure (min, max, mean, median)
activity_key -> Attribute to use as activity
timestamp_key -> Attribute to use as timestamp
variant
Variant of the algorithm to use, possible values:
native, frequency, performance, frequency_greedy, performance_greedy
Returns
-------
dfg
DFG graph
"""
if parameters is None:
parameters = {}
if pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY not in parameters:
parameters[pmutil.constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_util.DEFAULT_NAME_KEY
if pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_util.DEFAULT_TIMESTAMP_KEY
if pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY not in parameters:
parameters[
pmutil.constants.
PARAMETER_CONSTANT_CASEID_KEY] = pmutil.constants.CASE_ATTRIBUTE_GLUE
if isinstance(log, pandas.core.frame.DataFrame):
log = csv_import_adapter.convert_timestamp_columns_in_df(
log,
timest_columns=[
parameters[pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY]
])
dfg_frequency, dfg_performance = df_statistics.get_dfg_graph(
log,
measure="both",
activity_key=parameters[
pmutil.constants.PARAMETER_CONSTANT_ACTIVITY_KEY],
timestamp_key=parameters[
pmutil.constants.PARAMETER_CONSTANT_TIMESTAMP_KEY],
case_id_glue=parameters[
pmutil.constants.PARAMETER_CONSTANT_CASEID_KEY])
if 'native' in variant or 'frequency' in variant:
return dfg_frequency
else:
return dfg_performance
return VERSIONS[variant](log_conversion.apply(log, parameters,
log_conversion.TO_EVENT_LOG),
parameters=parameters)