def variant_to_trace(variant, parameters=None):
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters,
xes_constants.DEFAULT_NAME_KEY)
variant_delimiter = exec_utils.get_param_value(
Parameters.PARAMETER_VARIANT_DELIMITER, parameters,
constants.DEFAULT_VARIANT_SEP)
from pm4py.objects.log.obj import Trace, Event
trace = Trace()
if type(variant) is tuple or type(variant) is list:
for act in variant:
event = Event({activity_key: act})
trace.append(event)
elif type(variant) is str:
var_act = variant.split(variant_delimiter)
for act in var_act:
event = Event({activity_key: act})
trace.append(event)
return trace
def form_log_from_dictio_couple(first_cases_repr,
second_cases_repr,
enable_multiplier=False):
"""
Form a log from a couple of dictionary, to use for
root cause analysis
Parameters
-------------
first_cases_repr
First cases representation
second_cases_repr
Second cases representation
enable_multiplier
Enable balancing of classes
Returns
------------
log
Trace log object
"""
log = EventLog()
if enable_multiplier:
multiplier_first = int(
max(
float(len(second_cases_repr)) / float(len(first_cases_repr)),
1))
multiplier_second = int(
max(
float(len(first_cases_repr)) / float(len(second_cases_repr)),
1))
else:
multiplier_first = 1
multiplier_second = 1
for j in range(multiplier_first):
for i in range(len(first_cases_repr)):
trace = Trace()
event = Event(first_cases_repr[i])
trace.append(event)
log.append(trace)
for j in range(multiplier_second):
for i in range(len(second_cases_repr)):
trace = Trace()
event = Event(second_cases_repr[i])
trace.append(event)
log.append(trace)
return log
def apply_tree_variants(variants, parameters=None):
"""
Apply the IM algorithm to a dictionary of variants obtaining a process tree
Parameters
----------
variants
Variants
parameters
Parameters of the algorithm, including:
Parameters.ACTIVITY_KEY -> attribute of the log to use as activity name
(default concept:name)
Returns
----------
process_tree
Process tree
"""
log = EventLog()
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters,
xes_constants.DEFAULT_NAME_KEY)
var_keys = list(variants.keys())
for var in var_keys:
trace = Trace()
activities = variants_util.get_activities_from_variant(var)
for act in activities:
trace.append(Event({activity_key: act}))
log.append(trace)
return apply_tree(log, parameters=parameters)
def list_of_str_to_trace(activities: List[str]) -> Trace:
t = Trace()
for a in activities:
e = Event()
e["concept:name"] = a
t.append(e)
return t
def apply(df, parameters=None):
"""
Convert a dataframe into a log containing 1 case per variant (only control-flow
perspective is considered)
Parameters
-------------
df
Dataframe
parameters
Parameters of the algorithm
Returns
-------------
log
Event log
"""
from pm4py.statistics.traces.pandas import case_statistics
if parameters is None:
parameters = {}
variant_stats = case_statistics.get_variant_statistics(df, parameters=parameters)
activity_key = parameters[
pm4_constants.PARAMETER_CONSTANT_ACTIVITY_KEY] if pm4_constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
log = EventLog()
for vd in variant_stats:
variant = vd['variant'].split(",")
trace = Trace()
for activity in variant:
event = Event()
event[activity_key] = activity
trace.append(event)
log.append(trace)
return log
def apply(log, parameters=None):
"""
Converts the event log to an event stream
Parameters
----------
log: :class:`pm4py.log.log.EventLog`
An Event log
include_case_attributes:
Default is True
case_attribute_prefix:
Default is 'case:'
enable_deepcopy
Enables deepcopy (avoid references between input and output objects)
Returns
-------
log : :class:`pm4py.log.log.EventLog`
An Event stream
"""
if parameters is None:
parameters = {}
stream_post_processing = exec_utils.get_param_value(
Parameters.STREAM_POST_PROCESSING, parameters, False)
case_pref = exec_utils.get_param_value(Parameters.CASE_ATTRIBUTE_PREFIX,
parameters, 'case:')
enable_deepcopy = exec_utils.get_param_value(Parameters.DEEP_COPY,
parameters, True)
include_case_attributes = exec_utils.get_param_value(
Parameters.INCLUDE_CASE_ATTRIBUTES, parameters, True)
compress = exec_utils.get_param_value(Parameters.COMPRESS, parameters,
True)
if pkgutil.find_loader("pandas"):
import pandas
if isinstance(log, pandas.DataFrame):
extensions = __detect_extensions(log)
list_events = pandas_utils.to_dict_records(log)
if stream_post_processing:
list_events = __postprocess_stream(list_events)
if compress:
list_events = __compress(list_events)
for i in range(len(list_events)):
list_events[i] = Event(list_events[i])
log = log_instance.EventStream(list_events,
attributes={'origin': 'csv'})
for ex in extensions:
log.extensions[ex.name] = {
xes_constants.KEY_PREFIX: ex.prefix,
xes_constants.KEY_URI: ex.uri
}
if isinstance(log, EventLog):
return __transform_event_log_to_event_stream(
log,
include_case_attributes=include_case_attributes,
case_attribute_prefix=case_pref,
enable_deepcopy=enable_deepcopy)
return log
def apply(tree: ProcessTree, parameters : Optional[Dict[Union[str, Parameters], Any]] = None) -> EventLog:
"""
Performs an extensive playout of the process tree
Parameters
-------------
tree
Process tree
parameters
Possible parameters, including:
- Parameters.MIN_TRACE_LENGTH => minimum length of a trace (default: 1)
- Parameters.MAX_TRACE_LENGTH => maximum length of a trace (default: min_allowed_trace_length)
- Parameters.MAX_LOOP_OCC => maximum number of occurrences for a loop (default: MAX_TRACE_LENGTH)
- Parameters.ACTIVITY_KEY => activity key
- Parameters.MAX_LIMIT_NUM_TRACES => maximum number to the limit of traces; the playout shall stop when the number is reached (default: 100000)
Returns
-------------
log
Event log
"""
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes_constants.DEFAULT_NAME_KEY)
# to save memory in the returned log, allocate each activity once. to know the list of activities of the
# process tree, use the footprints module
fp_tree = fp_discovery.apply(tree, parameters=parameters)
activities = fp_tree["activities"]
activities = {act: Event({activity_key: act}) for act in activities}
min_allowed_trace_length = bottomup_discovery.get_min_trace_length(tree, parameters=parameters)
min_trace_length = exec_utils.get_param_value(Parameters.MIN_TRACE_LENGTH, parameters, 1)
max_trace_length = exec_utils.get_param_value(Parameters.MAX_TRACE_LENGTH, parameters, min_allowed_trace_length)
max_loop_occ = exec_utils.get_param_value(Parameters.MAX_LOOP_OCC, parameters, int(max_trace_length / 2))
max_limit_num_traces = exec_utils.get_param_value(Parameters.MAX_LIMIT_NUM_TRACES, parameters, 100000)
return_set_strings = exec_utils.get_param_value(Parameters.RETURN_SET_STRINGS, parameters, False)
bottomup = bottomup_discovery.get_bottomup_nodes(tree, parameters=parameters)
min_rem_dict = bottomup_discovery.get_min_rem_dict(tree, parameters=parameters)
max_rem_dict = bottomup_discovery.get_max_rem_dict(tree, parameters=parameters)
playout_dictio = {}
for i in range(len(bottomup)):
get_playout(bottomup[i], playout_dictio, min_trace_length, max_trace_length, max_loop_occ, min_rem_dict,
max_rem_dict, max_limit_num_traces)
tree_playout_traces = playout_dictio[tree][TRACES]
if return_set_strings:
return tree_playout_traces
log = EventLog()
for tr0 in tree_playout_traces:
trace = Trace()
for act in tr0:
trace.append(activities[act])
log.append(trace)
return log
def execute_script():
L = EventLog()
e1 = Event()
e1["concept:name"] = "A"
e2 = Event()
e2["concept:name"] = "B"
e3 = Event()
e3["concept:name"] = "C"
e4 = Event()
e4["concept:name"] = "D"
t = Trace()
t.append(e1)
t.append(e2)
t.append(e3)
t.append(e4)
for i in range(10000):
L.append(deepcopy(t))
print(len(L))
def apply(df, parameters=None):
"""
Convert a dataframe into a log containing N case per variant (only control-flow
perspective is considered)
Parameters
-------------
df
Dataframe
parameters
Parameters of the algorithm
Returns
-------------
log
Event log
"""
from pm4py.statistics.traces.pandas import case_statistics
if parameters is None:
parameters = {}
return_variants = parameters[
RETURN_VARIANTS] if RETURN_VARIANTS in parameters else False
case_glue = parameters[
pm4_constants.
PARAMETER_CONSTANT_CASEID_KEY] if pm4_constants.PARAMETER_CONSTANT_CASEID_KEY in parameters else pm4_constants.CASE_CONCEPT_NAME
activity_key = parameters[
pm4_constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if pm4_constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
variant_stats = case_statistics.get_variant_statistics(
df, parameters=parameters)
log = EventLog()
all_variants_log = {}
for vd in variant_stats:
variant = vd['variant'].split(",")
variant_count = vd[case_glue]
trace = Trace()
for activity in variant:
event = Event()
event[activity_key] = activity
trace.append(event)
all_variants_log[vd['variant']] = []
for i in range(variant_count):
log.append(trace)
all_variants_log[vd['variant']].append(len(log) - 1)
if return_variants:
return log, all_variants_log
return log
def insert_artificial_start_end(log: EventLog, parameters: Optional[Dict[Any, Any]] = None) -> EventLog:
"""
Inserts the artificial start/end activities in an event log
Parameters
-------------------
log
Event log
parameters
Parameters of the algorithm, including:
- Parameters.ACTIVITY_KEY: the activity
- Parameters.TIMESTAMP_KEY: the timestamp
Returns
------------------
log
Enriched log
"""
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes_constants.DEFAULT_NAME_KEY)
timestamp_key = exec_utils.get_param_value(Parameters.TIMESTAMP_KEY, parameters, xes_constants.DEFAULT_TIMESTAMP_KEY)
artificial_start_activity = exec_utils.get_param_value(Parameters.PARAM_ARTIFICIAL_START_ACTIVITY, parameters,
constants.DEFAULT_ARTIFICIAL_START_ACTIVITY)
artificial_end_activity = exec_utils.get_param_value(Parameters.PARAM_ARTIFICIAL_END_ACTIVITY, parameters,
constants.DEFAULT_ARTIFICIAL_END_ACTIVITY)
for trace in log:
start_event = Event({activity_key: artificial_start_activity})
end_event = Event({activity_key: artificial_end_activity})
if trace:
if timestamp_key in trace[0]:
start_event[timestamp_key] = trace[0][timestamp_key] - datetime.timedelta(seconds=1)
if timestamp_key in trace[-1]:
end_event[timestamp_key] = trace[-1][timestamp_key] + datetime.timedelta(seconds=1)
trace.insert(0, start_event)
trace.append(end_event)
return log
def acyclic_net_variants(net,
initial_marking,
final_marking,
activity_key=xes_util.DEFAULT_NAME_KEY):
"""
Given an acyclic accepting Petri net, initial and final marking extracts a set of variants (in form of traces)
replayable on the net.
Warning: this function is based on a marking exploration. If the accepting Petri net contains loops, the method
will not work properly as it stops the search if a specific marking has already been encountered.
Parameters
----------
:param net: An acyclic workflow net
:param initial_marking: The initial marking of the net.
:param final_marking: The final marking of the net.
:param activity_key: activity key to use
Returns
-------
:return: variants: :class:`list` Set of variants - in the form of Trace objects - obtainable executing the net
"""
active = {(initial_marking, ())}
visited = set()
variants = set()
while active:
curr_marking, curr_partial_trace = active.pop()
curr_pair = (curr_marking, curr_partial_trace)
enabled_transitions = semantics.enabled_transitions(net, curr_marking)
for transition in enabled_transitions:
if transition.label is not None:
next_partial_trace = curr_partial_trace + (transition.label, )
else:
next_partial_trace = curr_partial_trace
next_marking = semantics.execute(transition, net, curr_marking)
next_pair = (next_marking, next_partial_trace)
if next_marking == final_marking:
variants.add(next_partial_trace)
else:
# If the next marking is not in visited, if the next marking+partial trace is different from the current one+partial trace
if next_pair not in visited and curr_pair != next_pair:
active.add(next_pair)
visited.add(curr_pair)
trace_variants = []
for variant in variants:
trace = Trace()
for activity_label in variant:
trace.append(Event({activity_key: activity_label}))
trace_variants.append(trace)
return trace_variants
def read_trace(self) -> Trace:
if self.i < self.no_traces:
case_id = self.c_unq[self.i]
si = self.c_ind[self.i]
ei = si + self.c_counts[self.i]
trace = Trace(
attributes={xes_constants.DEFAULT_TRACEID_KEY: case_id})
for j in range(si, ei):
event = Event({
xes_constants.DEFAULT_NAME_KEY:
self.activities[j],
xes_constants.DEFAULT_TIMESTAMP_KEY:
self.timestamps[j]
})
trace.append(event)
self.i = self.i + 1
return trace
def parse_event_log_string(
traces: Collection[str],
sep: str = ",",
activity_key: str = xes_constants.DEFAULT_NAME_KEY,
timestamp_key: str = xes_constants.DEFAULT_TIMESTAMP_KEY,
case_id_key: str = xes_constants.DEFAULT_TRACEID_KEY) -> EventLog:
"""
Parse a collection of traces expressed as strings
(e.g., ["A,B,C,D", "A,C,B,D", "A,D"])
to an event log
Parameters
------------------
traces
Collection of traces expressed as strings
sep
Separator used to split the activities of a string trace
activity_key
The attribute that should be used as activity
timestamp_key
The attribute that should be used as timestamp
case_id_key
The attribute that should be used as case identifier
Returns
-----------------
log
Event log
"""
log = EventLog()
this_timest = 10000000
for index, trace in enumerate(traces):
activities = trace.split(sep)
trace = Trace()
trace.attributes[case_id_key] = str(index)
for act in activities:
event = Event({
activity_key:
act,
timestamp_key:
datetime.datetime.fromtimestamp(this_timest)
})
trace.append(event)
this_timest = this_timest + 1
log.append(trace)
return log
def generate_log(pt0, no_traces=100):
"""
Generate a log out of a process tree
Parameters
------------
pt
Process tree
no_traces
Number of traces contained in the process tree
Returns
------------
log
Trace log object
"""
pt = deepcopy(pt0)
# different taus must give different ID in log generation!!!!
# so we cannot use the default process tree class
# we use this different one!
pt = GenerationTree(pt)
log = EventLog()
# assigns to each event an increased timestamp from 1970
curr_timestamp = 10000000
for i in range(no_traces):
ex_seq = execute(pt)
ex_seq_labels = pt_util.project_execution_sequence_to_labels(ex_seq)
trace = Trace()
trace.attributes[xes.DEFAULT_NAME_KEY] = str(i)
for label in ex_seq_labels:
event = Event()
event[xes.DEFAULT_NAME_KEY] = label
event[xes.DEFAULT_TIMESTAMP_KEY] = datetime.datetime.fromtimestamp(curr_timestamp)
trace.append(event)
curr_timestamp = curr_timestamp + 1
log.append(trace)
return log
def apply(
tree: ProcessTree,
parameters: Optional[Dict[Union[str, Parameters],
Any]] = None) -> EventLog:
"""
Gets the top-bottom playout of a process tree
Parameters
---------------
tree
Process tree
parameters
Parameters of the algorithm, including:
- Parameters.ACTIVITY_KEY: activity key
- Parameters.NO_TRACES: number of traces that should be returned
Returns
---------------
log
Event log
"""
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters,
xes_constants.DEFAULT_NAME_KEY)
no_traces = exec_utils.get_param_value(Parameters.NO_TRACES, parameters,
1000)
execution_sequences = get_num_ex_sequences(tree, no_traces)
log = EventLog()
for seq in execution_sequences:
trace = Trace()
for el in seq:
if el.label is not None:
event = Event({activity_key: el.label})
trace.append(event)
log.append(trace)
return log
def keep_only_one_attribute_per_event(log, attribute_key):
"""
Keeps only one attribute per event
Parameters
---------------
log
Event log
attribute_key
Attribute key
"""
new_log = EventLog()
if log is not None:
for trace in log:
new_trace = Trace()
for ev in trace:
new_trace.append(Event({attribute_key: ev[attribute_key]}))
new_log.append(new_trace)
return new_log
def form_fake_log(prefixes_keys, activity_key=xes_util.DEFAULT_NAME_KEY):
"""
Form fake log for replay (putting each prefix as separate trace to align)
Parameters
----------
prefixes_keys
Keys of the prefixes (to form a log with a given order)
activity_key
Activity key (must be provided if different from concept:name)
"""
fake_log = EventLog()
for prefix in prefixes_keys:
trace = Trace()
prefix_activities = prefix.split(constants.DEFAULT_VARIANT_SEP)
for activity in prefix_activities:
event = Event()
event[activity_key] = activity
trace.append(event)
fake_log.append(trace)
return fake_log
def check_is_fitting(*args, activity_key=xes_constants.DEFAULT_NAME_KEY):
"""
Checks if a trace object is fit against a process model
Parameters
-----------------
trace
Trace object (trace / variant)
model
Model (process tree, Petri net, BPMN, ...)
activity_key
Activity key (optional)
Returns
-----------------
is_fit
Boolean value (True if the trace fits; False if the trace does not)
"""
from pm4py.util import variants_util
from pm4py.convert import convert_to_process_tree, convert_to_petri_net
trace = args[0]
model = args[1:]
try:
model = convert_to_process_tree(*model)
except:
# the model cannot be expressed as a process tree, let's say if at least can be expressed as a Petri net
model = convert_to_petri_net(*model)
if not isinstance(trace, Trace):
activities = variants_util.get_activities_from_variant(trace)
trace = Trace()
for act in activities:
trace.append(Event({activity_key: act}))
if isinstance(model, ProcessTree):
return __check_is_fit_process_tree(trace, model, activity_key=activity_key)
elif isinstance(model, tuple) and isinstance(model[0], PetriNet):
return __check_is_fit_petri_net(trace, model[0], model[1], model[2], activity_key=activity_key)
def import_from_context(context, num_traces, parameters=None):
"""
Import a XES log from an iterparse context
Parameters
--------------
context
Iterparse context
num_traces
Number of traces of the XES log
parameters
Parameters of the algorithm
Returns
--------------
log
Event log
"""
if parameters is None:
parameters = {}
max_no_traces_to_import = exec_utils.get_param_value(Parameters.MAX_TRACES, parameters, sys.maxsize)
timestamp_sort = exec_utils.get_param_value(Parameters.TIMESTAMP_SORT, parameters, False)
timestamp_key = exec_utils.get_param_value(Parameters.TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
reverse_sort = exec_utils.get_param_value(Parameters.REVERSE_SORT, parameters, False)
show_progress_bar = exec_utils.get_param_value(Parameters.SHOW_PROGRESS_BAR, parameters, True)
date_parser = dt_parser.get()
progress = None
if pkgutil.find_loader("tqdm") and show_progress_bar:
from tqdm.auto import tqdm
progress = tqdm(total=num_traces, desc="parsing log, completed traces :: ")
log = None
trace = None
event = None
tree = {}
for tree_event, elem in context:
if tree_event == _EVENT_START: # starting to read
parent = tree[elem.getparent()] if elem.getparent() in tree else None
if elem.tag.endswith(xes_constants.TAG_STRING):
if parent is not None:
tree = __parse_attribute(elem, parent, elem.get(xes_constants.KEY_KEY),
elem.get(xes_constants.KEY_VALUE), tree)
continue
elif elem.tag.endswith(xes_constants.TAG_DATE):
try:
dt = date_parser.apply(elem.get(xes_constants.KEY_VALUE))
tree = __parse_attribute(elem, parent, elem.get(xes_constants.KEY_KEY), dt, tree)
except TypeError:
logging.info("failed to parse date: " + str(elem.get(xes_constants.KEY_VALUE)))
except ValueError:
logging.info("failed to parse date: " + str(elem.get(xes_constants.KEY_VALUE)))
continue
elif elem.tag.endswith(xes_constants.TAG_EVENT):
if event is not None:
raise SyntaxError('file contains <event> in another <event> tag')
event = Event()
tree[elem] = event
continue
elif elem.tag.endswith(xes_constants.TAG_TRACE):
if len(log) >= max_no_traces_to_import:
break
if trace is not None:
raise SyntaxError('file contains <trace> in another <trace> tag')
trace = Trace()
tree[elem] = trace.attributes
continue
elif elem.tag.endswith(xes_constants.TAG_FLOAT):
if parent is not None:
try:
val = float(elem.get(xes_constants.KEY_VALUE))
tree = __parse_attribute(elem, parent, elem.get(xes_constants.KEY_KEY), val, tree)
except ValueError:
logging.info("failed to parse float: " + str(elem.get(xes_constants.KEY_VALUE)))
continue
elif elem.tag.endswith(xes_constants.TAG_INT):
if parent is not None:
try:
val = int(elem.get(xes_constants.KEY_VALUE))
tree = __parse_attribute(elem, parent, elem.get(xes_constants.KEY_KEY), val, tree)
except ValueError:
logging.info("failed to parse int: " + str(elem.get(xes_constants.KEY_VALUE)))
continue
elif elem.tag.endswith(xes_constants.TAG_BOOLEAN):
if parent is not None:
try:
val0 = elem.get(xes_constants.KEY_VALUE)
val = False
if str(val0).lower() == "true":
val = True
tree = __parse_attribute(elem, parent, elem.get(xes_constants.KEY_KEY), val, tree)
except ValueError:
logging.info("failed to parse boolean: " + str(elem.get(xes_constants.KEY_VALUE)))
continue
elif elem.tag.endswith(xes_constants.TAG_LIST):
if parent is not None:
# lists have no value, hence we put None as a value
tree = __parse_attribute(elem, parent, elem.get(xes_constants.KEY_KEY), None, tree)
continue
elif elem.tag.endswith(xes_constants.TAG_ID):
if parent is not None:
tree = __parse_attribute(elem, parent, elem.get(xes_constants.KEY_KEY),
elem.get(xes_constants.KEY_VALUE), tree)
continue
elif elem.tag.endswith(xes_constants.TAG_EXTENSION):
if log is None:
raise SyntaxError('extension found outside of <log> tag')
if elem.get(xes_constants.KEY_NAME) is not None and elem.get(
xes_constants.KEY_PREFIX) is not None and elem.get(xes_constants.KEY_URI) is not None:
log.extensions[elem.get(xes_constants.KEY_NAME)] = {
xes_constants.KEY_PREFIX: elem.get(xes_constants.KEY_PREFIX),
xes_constants.KEY_URI: elem.get(xes_constants.KEY_URI)}
continue
elif elem.tag.endswith(xes_constants.TAG_GLOBAL):
if log is None:
raise SyntaxError('global found outside of <log> tag')
if elem.get(xes_constants.KEY_SCOPE) is not None:
log.omni_present[elem.get(xes_constants.KEY_SCOPE)] = {}
tree[elem] = log.omni_present[elem.get(xes_constants.KEY_SCOPE)]
continue
elif elem.tag.endswith(xes_constants.TAG_CLASSIFIER):
if log is None:
raise SyntaxError('classifier found outside of <log> tag')
if elem.get(xes_constants.KEY_KEYS) is not None:
classifier_value = elem.get(xes_constants.KEY_KEYS)
if "'" in classifier_value:
log.classifiers[elem.get(xes_constants.KEY_NAME)] = [x for x in classifier_value.split("'")
if x.strip()]
else:
log.classifiers[elem.get(xes_constants.KEY_NAME)] = classifier_value.split()
continue
elif elem.tag.endswith(xes_constants.TAG_LOG):
if log is not None:
raise SyntaxError('file contains > 1 <log> tags')
log = EventLog()
tree[elem] = log.attributes
continue
elif tree_event == _EVENT_END:
if elem in tree:
del tree[elem]
elem.clear()
if elem.getprevious() is not None:
try:
del elem.getparent()[0]
except TypeError:
pass
if elem.tag.endswith(xes_constants.TAG_EVENT):
if trace is not None:
trace.append(event)
event = None
continue
elif elem.tag.endswith(xes_constants.TAG_TRACE):
log.append(trace)
if progress is not None:
progress.update()
trace = None
continue
elif elem.tag.endswith(xes_constants.TAG_LOG):
continue
# gracefully close progress bar
if progress is not None:
progress.close()
del context, progress
if timestamp_sort:
log = sorting.sort_timestamp(log, timestamp_key=timestamp_key, reverse_sort=reverse_sort)
# sets the activity key as default classifier in the log's properties
log.properties[constants.PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_constants.DEFAULT_NAME_KEY
log.properties[constants.PARAMETER_CONSTANT_ATTRIBUTE_KEY] = xes_constants.DEFAULT_NAME_KEY
# sets the default timestamp key
log.properties[constants.PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_constants.DEFAULT_TIMESTAMP_KEY
# sets the default resource key
log.properties[constants.PARAMETER_CONSTANT_RESOURCE_KEY] = xes_constants.DEFAULT_RESOURCE_KEY
# sets the default transition key
log.properties[constants.PARAMETER_CONSTANT_TRANSITION_KEY] = xes_constants.DEFAULT_TRANSITION_KEY
# sets the default group key
log.properties[constants.PARAMETER_CONSTANT_GROUP_KEY] = xes_constants.DEFAULT_GROUP_KEY
return log
def import_log_from_file_object(f,
encoding,
file_size=sys.maxsize,
parameters=None):
"""
Import a log object from a (XML) file object
Parameters
-----------
f
file object
encoding
Encoding
file_size
Size of the file (measured on disk)
parameters
Parameters of the algorithm, including
Parameters.TIMESTAMP_SORT -> Specify if we should sort log by timestamp
Parameters.TIMESTAMP_KEY -> If sort is enabled, then sort the log by using this key
Parameters.REVERSE_SORT -> Specify in which direction the log should be sorted
Parameters.MAX_TRACES -> Specify the maximum number of traces to import from the log (read in order in the XML file)
Parameters.MAX_BYTES -> Maximum number of bytes to read
Parameters.SKYP_BYTES -> Number of bytes to skip
Parameters.SET_ATTRIBUTES_TO_READ -> Names of the attributes that should be parsed. If not specified,
then, all the attributes are parsed.
Returns
-----------
log
Log file
"""
values_dict = {}
date_parser = dt_parser.get()
set_attributes_to_read = exec_utils.get_param_value(
Parameters.SET_ATTRIBUTES_TO_READ, parameters, None)
max_no_traces_to_import = exec_utils.get_param_value(
Parameters.MAX_TRACES, parameters, sys.maxsize)
timestamp_sort = exec_utils.get_param_value(Parameters.TIMESTAMP_SORT,
parameters, False)
timestamp_key = exec_utils.get_param_value(
Parameters.TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
reverse_sort = exec_utils.get_param_value(Parameters.REVERSE_SORT,
parameters, False)
skip_bytes = exec_utils.get_param_value(Parameters.SKIP_BYTES, parameters,
False)
max_bytes_to_read = exec_utils.get_param_value(Parameters.MAX_BYTES,
parameters, sys.maxsize)
if file_size > max_bytes_to_read:
skip_bytes = file_size - max_bytes_to_read
log = EventLog()
tracecount = 0
trace = None
event = None
f.seek(skip_bytes)
for line in f:
content = line.decode(encoding).split("\"")
if len(content) > 0:
tag = content[0].split("<")[-1]
if trace is not None:
if event is not None:
if len(content) == 5:
key, value = read_attribute_key_value(
tag, content, date_parser, values_dict,
set_attributes_to_read)
if value is not None:
event[key] = value
elif tag.startswith("/event"):
trace.append(event)
event = None
elif tag.startswith("event"):
event = Event()
elif len(content) == 5:
key, value = read_attribute_key_value(
tag, content, date_parser, values_dict,
set_attributes_to_read)
if value is not None:
trace.attributes[key] = value
elif tag.startswith("/trace"):
log.append(trace)
tracecount += 1
if tracecount > max_no_traces_to_import:
break
trace = None
elif tag.startswith("trace"):
trace = Trace()
if timestamp_sort:
log = sorting.sort_timestamp(log,
timestamp_key=timestamp_key,
reverse_sort=reverse_sort)
# sets the activity key as default classifier in the log's properties
log.properties[
constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] = xes_constants.DEFAULT_NAME_KEY
log.properties[
constants.
PARAMETER_CONSTANT_ATTRIBUTE_KEY] = xes_constants.DEFAULT_NAME_KEY
# sets the default timestamp key
log.properties[
constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] = xes_constants.DEFAULT_TIMESTAMP_KEY
# sets the default resource key
log.properties[
constants.
PARAMETER_CONSTANT_RESOURCE_KEY] = xes_constants.DEFAULT_RESOURCE_KEY
# sets the default transition key
log.properties[
constants.
PARAMETER_CONSTANT_TRANSITION_KEY] = xes_constants.DEFAULT_TRANSITION_KEY
# sets the default group key
log.properties[
constants.
PARAMETER_CONSTANT_GROUP_KEY] = xes_constants.DEFAULT_GROUP_KEY
return log
def to_interval(log, parameters=None):
"""
Converts a log to interval format (e.g. an event has two timestamps)
from lifecycle format (an event has only a timestamp, and a transition lifecycle)
Parameters
-------------
log
Log (expressed in the lifecycle format)
parameters
Possible parameters of the method (activity, timestamp key, start timestamp key, transition ...)
Returns
-------------
log
Interval event log
"""
if parameters is None:
parameters = {}
timestamp_key = parameters[
constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] if constants.PARAMETER_CONSTANT_TIMESTAMP_KEY in parameters else xes.DEFAULT_TIMESTAMP_KEY
start_timestamp_key = parameters[
constants.
PARAMETER_CONSTANT_START_TIMESTAMP_KEY] if constants.PARAMETER_CONSTANT_START_TIMESTAMP_KEY in parameters else xes.DEFAULT_START_TIMESTAMP_KEY
transition_key = parameters[
constants.
PARAMETER_CONSTANT_TRANSITION_KEY] if constants.PARAMETER_CONSTANT_TRANSITION_KEY in parameters else xes.DEFAULT_TRANSITION_KEY
activity_key = parameters[
constants.
PARAMETER_CONSTANT_ACTIVITY_KEY] if constants.PARAMETER_CONSTANT_ACTIVITY_KEY in parameters else xes.DEFAULT_NAME_KEY
business_hours = parameters[
"business_hours"] if "business_hours" in parameters else False
worktiming = parameters["worktiming"] if "worktiming" in parameters else [
7, 17
]
weekends = parameters["weekends"] if "weekends" in parameters else [6, 7]
if log is not None and len(log) > 0:
if "PM4PY_TYPE" in log.attributes and log.attributes[
"PM4PY_TYPE"] == "interval":
return log
if log[0] is not None and len(log[0]) > 0:
first_event = log[0][0]
if start_timestamp_key in first_event:
return log
new_log = EventLog()
new_log.attributes["PM4PY_TYPE"] = "interval"
for trace in log:
new_trace = Trace()
for attr in trace.attributes:
new_trace.attributes[attr] = trace.attributes[attr]
activities_start = {}
for event in trace:
activity = event[activity_key]
transition = event[
transition_key] if transition_key in event else "complete"
timestamp = event[timestamp_key]
if transition.lower() == "start":
if activity not in activities_start:
activities_start[activity] = list()
activities_start[activity].append(event)
elif transition.lower() == "complete":
start_event = None
start_timestamp = event[timestamp_key]
if activity in activities_start and len(
activities_start[activity]) > 0:
start_event = activities_start[activity].pop(0)
start_timestamp = start_event[timestamp_key]
new_event = Event()
for attr in event:
if not attr == timestamp_key and not attr == transition_key:
new_event[attr] = event[attr]
if start_event is not None:
for attr in start_event:
if not attr == timestamp_key and not attr == transition_key:
new_event["@@startevent_" +
attr] = start_event[attr]
new_event[start_timestamp_key] = start_timestamp
new_event[timestamp_key] = timestamp
new_event["@@duration"] = (
timestamp - start_timestamp).total_seconds()
if business_hours:
bh = BusinessHours(
start_timestamp.replace(tzinfo=None),
timestamp.replace(tzinfo=None),
worktiming=worktiming,
weekends=weekends)
new_event["@@approx_bh_duration"] = bh.getseconds()
new_trace.append(new_event)
new_trace = sorting.sort_timestamp_trace(new_trace,
start_timestamp_key)
new_log.append(new_trace)
return new_log
return log
def from_dict_to_event(event_dict):
timestamp_field_name = "time:timestamp"
if timestamp_field_name in event_dict.keys():
event_dict[timestamp_field_name] = dt_parser.get().apply(
event_dict[timestamp_field_name])
return Event(event_dict)
def apply(
dfg: Dict[Tuple[str, str], int],
start_activities: Dict[str, int],
end_activities: Dict[str, int],
parameters: Optional[Dict[Union[str, Parameters], Any]] = None
) -> Union[EventLog, Dict[Tuple[str, str], int]]:
"""
Applies the playout algorithm on a DFG, extracting the most likely traces according to the DFG
Parameters
---------------
dfg
*Complete* DFG
start_activities
Start activities
end_activities
End activities
parameters
Parameters of the algorithm, including:
- Parameters.ACTIVITY_KEY => the activity key of the simulated log
- Parameters.TIMESTAMP_KEY => the timestamp key of the simulated log
- Parameters.MAX_NO_VARIANTS => the maximum number of variants generated by the method (default: 3000)
- Parameters.MIN_WEIGHTED_PROBABILITY => the minimum overall weighted probability that makes the method stop
(default: 1)
- Parameters.MAX_NO_OCC_PER_ACTIVITY => the maximum number of occurrences per activity in the traces of the log
(default: 2)
- Parameters.INTERRUPT_SIMULATION_WHEN_DFG_COMPLETE => interrupts the simulation when the DFG of the simulated
log has the same keys to the DFG of the original log
(all behavior is contained) (default: False)
- Parameters.ADD_TRACE_IF_TAKES_NEW_ELS_TO_DFG => adds a simulated trace to the simulated log only if it adds
elements to the simulated DFG, e.g., it adds behavior;
skip insertion otherwise (default: False)
- Parameters.RETURN_VARIANTS => returns the traces as variants with a likely number of occurrences
Returns
---------------
simulated_log
Simulated log
"""
if parameters is None:
parameters = {}
timestamp_key = exec_utils.get_param_value(
Parameters.TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters,
xes_constants.DEFAULT_NAME_KEY)
max_no_variants = exec_utils.get_param_value(Parameters.MAX_NO_VARIANTS,
parameters, 3000)
min_weighted_probability = exec_utils.get_param_value(
Parameters.MIN_WEIGHTED_PROBABILITY, parameters, 1.0)
interrupt_simulation_when_dfg_complete = exec_utils.get_param_value(
Parameters.INTERRUPT_SIMULATION_WHEN_DFG_COMPLETE, parameters, False)
add_trace_if_takes_new_els_to_dfg = exec_utils.get_param_value(
Parameters.ADD_TRACE_IF_TAKES_NEW_ELS_TO_DFG, parameters, False)
return_variants = exec_utils.get_param_value(Parameters.RETURN_VARIANTS,
parameters, False)
max_execution_time = exec_utils.get_param_value(
Parameters.MAX_EXECUTION_TIME, parameters, sys.maxsize)
# keep track of the DFG, start activities and end activities of the (ongoing) simulation
simulated_traces_dfg = set()
simulated_traces_sa = set()
simulated_traces_ea = set()
interrupt_break_condition = False
overall_probability = 0.0
final_traces = []
start_time = time.time()
for tr, p in get_traces(dfg,
start_activities,
end_activities,
parameters=parameters):
if (interrupt_simulation_when_dfg_complete
and interrupt_break_condition
) or not (len(final_traces) < max_no_variants
and overall_probability <= min_weighted_probability):
break
current_time = time.time()
if (current_time - start_time) > max_execution_time:
break
overall_probability += p
diff_sa = {tr[0]}.difference(simulated_traces_sa)
diff_ea = {tr[-1]}.difference(simulated_traces_ea)
diff_dfg = {(tr[i], tr[i + 1])
for i in range(len(tr) - 1)
}.difference(simulated_traces_dfg)
adds_something = len(diff_sa) > 0 or len(diff_ea) > 0 or len(
diff_dfg) > 0
if add_trace_if_takes_new_els_to_dfg and not adds_something:
# interrupt the addition if the ADD_TRACE_IF_TAKES_NEW_ELS_TO_DFG is set to True,
# and the trace does not really change the information on the DFG, start activities,
# end activities
continue
# update the start activities, end activities, DFG of the original log
simulated_traces_sa = simulated_traces_sa.union(diff_sa)
simulated_traces_ea = simulated_traces_ea.union(diff_ea)
simulated_traces_dfg = simulated_traces_dfg.union(diff_dfg)
# memorize the difference between the original DFG and the DFG of the simulated log
diff_original_sa = set(start_activities).difference(
simulated_traces_sa)
diff_original_ea = set(end_activities).difference(simulated_traces_ea)
diff_original_dfg = set(dfg).difference(simulated_traces_dfg)
interrupt_break_condition = len(diff_original_sa) == 0 and len(
diff_original_ea) == 0 and len(diff_original_dfg) == 0
final_traces.append((-p, tr))
if interrupt_simulation_when_dfg_complete and interrupt_break_condition:
break
# make sure that the traces are strictly ordered by their probability
# (generally, the order is already pretty good, since the states are visited in the queue based on their order,
# but not always 100% consistent)
final_traces = sorted(final_traces)
if return_variants:
# returns the variants instead of the log
variants = []
for p, tr in final_traces:
variants.append({
"variant": constants.DEFAULT_VARIANT_SEP.join(tr),
"count": math.ceil(-p * max_no_variants)
})
return variants
else:
event_log = EventLog()
# assigns to each event an increased timestamp from 1970
curr_timestamp = 10000000
for index, tr in enumerate(final_traces):
log_trace = Trace(
attributes={
xes_constants.DEFAULT_TRACEID_KEY: str(index),
"probability": -tr[0]
})
for act in tr[1]:
log_trace.append(
Event({
activity_key:
act,
timestamp_key:
datetime.datetime.fromtimestamp(curr_timestamp)
}))
# increases by 1 second
curr_timestamp += 1
event_log.append(log_trace)
return event_log
def run(self):
"""
Runs the thread
"""
if self.enable_diagnostics:
diagnostics = SimulationDiagnostics(self)
diagnostics.start()
from intervaltree import IntervalTree, Interval
logging.basicConfig()
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)
net, im, fm, smap, source, sink, start_time = self.net, self.im, self.fm, self.map, self.source, self.sink, self.start_time
places_interval_trees = self.places_interval_trees
transitions_interval_trees = self.transitions_interval_trees
cases_ex_time = self.cases_ex_time
current_time = start_time
self.internal_thread_start_time = time()
rem_time = self.get_rem_time()
acquired_places = set()
acquired = source.semaphore.acquire(timeout=rem_time)
if acquired:
acquired_places.add(source)
source.assigned_time.append(current_time)
current_marking = im
et = enabled_transitions(net, current_marking)
first_event = None
last_event = None
while not fm <= current_marking or len(et) == 0:
et = list(enabled_transitions(net, current_marking))
ct = stochastic_utils.pick_transition(et, smap)
simulated_execution_plus_waiting_time = -1
while simulated_execution_plus_waiting_time < 0:
simulated_execution_plus_waiting_time = smap[ct].get_value(
) if ct in smap else 0.0
# establish how much time we need to wait before firing the transition
# (it depends on the input places tokens)
waiting_time = 0
for arc in ct.out_arcs:
place = arc.target
sem_value = int(place.semaphore._value)
rem_time = self.get_rem_time()
acquired = place.semaphore.acquire(timeout=rem_time)
if acquired:
acquired_places.add(place)
rem_time = self.get_rem_time()
if rem_time == 0:
break
if sem_value == 0:
waiting_time = max(
waiting_time,
place.assigned_time.pop(0) -
current_time) if place.assigned_time else waiting_time
if rem_time == 0:
for place in acquired_places:
place.semaphore.release()
break
# if the waiting time is greater than 0, add an interval to the interval tree denoting
# the waiting times for the given transition
if waiting_time > 0:
transitions_interval_trees[ct].add(
Interval(current_time, current_time + waiting_time))
# get the actual execution time of the transition as a difference between simulated_execution_plus_waiting_time
# and the waiting time
execution_time = max(
simulated_execution_plus_waiting_time - waiting_time, 0)
# increase the timing based on the waiting time and the execution time of the transition
current_time = current_time + waiting_time + execution_time
for arc in ct.out_arcs:
place = arc.target
place.assigned_time.append(current_time)
place.assigned_time = sorted(place.assigned_time)
current_marking = weak_execute(ct, current_marking)
if ct.label is not None:
eve = Event({
xes_constants.DEFAULT_NAME_KEY:
ct.label,
xes_constants.DEFAULT_TIMESTAMP_KEY:
datetime.datetime.fromtimestamp(current_time)
})
last_event = eve
if first_event is None:
first_event = last_event
self.list_cases[self.id].append(eve)
for arc in ct.in_arcs:
place = arc.source
p_ex_time = place.assigned_time.pop(0)
if current_time - p_ex_time > 0:
places_interval_trees[place].add(
Interval(p_ex_time, current_time))
place.assigned_time.append(current_time)
place.assigned_time = sorted(place.assigned_time)
place.semaphore.release()
# sleep before starting next iteration
sleep((waiting_time + execution_time) / self.small_scale_factor)
if first_event is not None and last_event is not None:
cases_ex_time.append(
last_event[xes_constants.DEFAULT_TIMESTAMP_KEY].timestamp() -
first_event[xes_constants.DEFAULT_TIMESTAMP_KEY].timestamp())
else:
cases_ex_time.append(0)
places_to_free = set(current_marking).union(acquired_places)
for place in places_to_free:
place.semaphore.release()
rem_time = self.get_rem_time()
if rem_time > 0:
self.terminated_correctly = True
if self.enable_diagnostics:
logger.info(
str(time()) + " terminated successfully thread ID " +
str(self.id))
if self.enable_diagnostics:
if rem_time == 0:
if self.enable_diagnostics:
logger.info(
str(time()) + " terminated for timeout thread ID " +
str(self.id))
if self.enable_diagnostics:
diagnostics.diagn_open = False
def to_interval(log, parameters=None):
"""
Converts a log to interval format (e.g. an event has two timestamps)
from lifecycle format (an event has only a timestamp, and a transition lifecycle)
Parameters
-------------
log
Log (expressed in the lifecycle format)
parameters
Possible parameters of the method (activity, timestamp key, start timestamp key, transition ...)
Returns
-------------
log
Interval event log
"""
if parameters is None:
parameters = {}
timestamp_key = exec_utils.get_param_value(Parameters.TIMESTAMP_KEY,
parameters,
xes.DEFAULT_TIMESTAMP_KEY)
start_timestamp_key = exec_utils.get_param_value(
Parameters.START_TIMESTAMP_KEY, parameters,
xes.DEFAULT_START_TIMESTAMP_KEY)
transition_key = exec_utils.get_param_value(Parameters.TRANSITION_KEY,
parameters,
xes.DEFAULT_TRANSITION_KEY)
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters, xes.DEFAULT_NAME_KEY)
lifecycle_instance_key = exec_utils.get_param_value(
Parameters.LIFECYCLE_INSTANCE_KEY, parameters,
xes.DEFAULT_INSTANCE_KEY)
business_hours = exec_utils.get_param_value(Parameters.BUSINESS_HOURS,
parameters, False)
worktiming = exec_utils.get_param_value(Parameters.WORKTIMING, parameters,
[7, 17])
weekends = exec_utils.get_param_value(Parameters.WEEKENDS, parameters,
[6, 7])
if log is not None and len(log) > 0:
if "PM4PY_TYPE" in log.attributes and log.attributes[
"PM4PY_TYPE"] == "interval":
return log
if log[0] is not None and len(log[0]) > 0:
first_event = log[0][0]
if start_timestamp_key in first_event:
return log
new_log = EventLog(attributes=copy(log.attributes),
extensions=copy(log.extensions),
classifiers=copy(log.classifiers),
omni_present=copy(log.omni_present),
properties=copy(log.properties))
new_log.attributes["PM4PY_TYPE"] = "interval"
new_log.properties[
constants.
PARAMETER_CONSTANT_START_TIMESTAMP_KEY] = xes.DEFAULT_START_TIMESTAMP_KEY
for trace in log:
new_trace = Trace()
for attr in trace.attributes:
new_trace.attributes[attr] = trace.attributes[attr]
activities_start = {}
for event in trace:
activity = event[activity_key]
instance = event[
lifecycle_instance_key] if lifecycle_instance_key in event else None
activity = (activity, instance)
transition = event[
transition_key] if transition_key in event else "complete"
timestamp = event[timestamp_key]
if transition.lower() == "start":
if activity not in activities_start:
activities_start[activity] = list()
activities_start[activity].append(event)
elif transition.lower() == "complete":
start_event = None
start_timestamp = event[timestamp_key]
if activity in activities_start and len(
activities_start[activity]) > 0:
start_event = activities_start[activity].pop(0)
start_timestamp = start_event[timestamp_key]
new_event = Event()
for attr in event:
if not attr == timestamp_key and not attr == transition_key:
new_event[attr] = event[attr]
if start_event is not None:
for attr in start_event:
if not attr == timestamp_key and not attr == transition_key:
new_event["@@startevent_" +
attr] = start_event[attr]
new_event[start_timestamp_key] = start_timestamp
new_event[timestamp_key] = timestamp
new_event["@@duration"] = (
timestamp - start_timestamp).total_seconds()
if business_hours:
bh = BusinessHours(
start_timestamp.replace(tzinfo=None),
timestamp.replace(tzinfo=None),
worktiming=worktiming,
weekends=weekends)
new_event["@@approx_bh_duration"] = bh.getseconds()
new_trace.append(new_event)
new_trace = sorting.sort_timestamp_trace(new_trace,
start_timestamp_key)
new_log.append(new_trace)
return new_log
return log
def to_lifecycle(log, parameters=None):
"""
Converts a log from interval format (e.g. an event has two timestamps)
to lifecycle format (an event has only a timestamp, and a transition lifecycle)
Parameters
-------------
log
Log (expressed in the interval format)
parameters
Possible parameters of the method (activity, timestamp key, start timestamp key, transition ...)
Returns
-------------
log
Lifecycle event log
"""
if parameters is None:
parameters = {}
timestamp_key = parameters[
constants.
PARAMETER_CONSTANT_TIMESTAMP_KEY] if constants.PARAMETER_CONSTANT_TIMESTAMP_KEY in parameters else xes.DEFAULT_TIMESTAMP_KEY
start_timestamp_key = parameters[
constants.
PARAMETER_CONSTANT_START_TIMESTAMP_KEY] if constants.PARAMETER_CONSTANT_START_TIMESTAMP_KEY in parameters else xes.DEFAULT_START_TIMESTAMP_KEY
transition_key = parameters[
constants.
PARAMETER_CONSTANT_TRANSITION_KEY] if constants.PARAMETER_CONSTANT_TRANSITION_KEY in parameters else xes.DEFAULT_TRANSITION_KEY
if log is not None and len(log) > 0:
if "PM4PY_TYPE" in log.attributes and log.attributes[
"PM4PY_TYPE"] == "lifecycle":
return log
if log[0] is not None and len(log[0]) > 0:
first_event = log[0][0]
if transition_key in first_event:
return log
new_log = EventLog()
new_log.attributes["PM4PY_TYPE"] = "lifecycle"
for trace in log:
new_trace = Trace()
for attr in trace.attributes:
new_trace.attributes[attr] = trace.attributes[attr]
list_events = []
for index, event in enumerate(trace):
new_event_start = Event()
new_event_complete = Event()
for attr in event:
if not attr == timestamp_key and not attr == start_timestamp_key:
new_event_start[attr] = event[attr]
new_event_complete[attr] = event[attr]
new_event_start[timestamp_key] = event[start_timestamp_key]
new_event_start[transition_key] = "start"
new_event_start["@@custom_lif_id"] = 0
new_event_start["@@origin_ev_idx"] = index
new_event_complete[timestamp_key] = event[timestamp_key]
new_event_complete[transition_key] = "complete"
new_event_complete["@@custom_lif_id"] = 1
new_event_complete["@@origin_ev_idx"] = index
list_events.append(new_event_start)
list_events.append(new_event_complete)
list_events = sorted(
list_events,
key=lambda x:
(x[timestamp_key], x["@@origin_ev_idx"], x["@@custom_lif_id"]))
for ev in list_events:
new_trace.append(ev)
new_log.append(new_trace)
return new_log
return log
def read_event(self):
"""
Gets the next event from the iterator
Returns
------------
event
Event
"""
tree = self.tree
while True:
tree_event, elem = next(self.context)
if tree_event == _EVENT_START:
parent = tree[
elem.getparent()] if elem.getparent() in tree else None
if elem.tag.endswith(xes_constants.TAG_TRACE):
self.trace = Trace()
tree[elem] = self.trace.attributes
self.reading_trace = True
continue
if elem.tag.endswith(xes_constants.TAG_EVENT):
self.event = Event()
tree[elem] = self.event
self.reading_event = True
continue
if self.reading_event or self.reading_trace:
if elem.tag.endswith(xes_constants.TAG_STRING):
if parent is not None:
tree = parse_attribute(
elem, parent, elem.get(xes_constants.KEY_KEY),
elem.get(xes_constants.KEY_VALUE), tree)
continue
elif elem.tag.endswith(xes_constants.TAG_DATE):
try:
dt = self.date_parser.apply(
elem.get(xes_constants.KEY_VALUE))
tree = parse_attribute(
elem, parent, elem.get(xes_constants.KEY_KEY),
dt, tree)
except TypeError:
logging.info(
"failed to parse date: " +
str(elem.get(xes_constants.KEY_VALUE)))
except ValueError:
logging.info(
"failed to parse date: " +
str(elem.get(xes_constants.KEY_VALUE)))
continue
elif elem.tag.endswith(xes_constants.TAG_FLOAT):
if parent is not None:
try:
val = float(elem.get(xes_constants.KEY_VALUE))
tree = parse_attribute(
elem, parent,
elem.get(xes_constants.KEY_KEY), val, tree)
except ValueError:
logging.info(
"failed to parse float: " +
str(elem.get(xes_constants.KEY_VALUE)))
continue
elif elem.tag.endswith(xes_constants.TAG_INT):
if parent is not None:
try:
val = int(elem.get(xes_constants.KEY_VALUE))
tree = parse_attribute(
elem, parent,
elem.get(xes_constants.KEY_KEY), val, tree)
except ValueError:
logging.info(
"failed to parse int: " +
str(elem.get(xes_constants.KEY_VALUE)))
continue
elif elem.tag.endswith(xes_constants.TAG_BOOLEAN):
if parent is not None:
try:
val0 = elem.get(xes_constants.KEY_VALUE)
val = False
if str(val0).lower() == "true":
val = True
tree = parse_attribute(
elem, parent,
elem.get(xes_constants.KEY_KEY), val, tree)
except ValueError:
logging.info(
"failed to parse boolean: " +
str(elem.get(xes_constants.KEY_VALUE)))
continue
elif elem.tag.endswith(xes_constants.TAG_LIST):
if parent is not None:
# lists have no value, hence we put None as a value
tree = parse_attribute(
elem, parent, elem.get(xes_constants.KEY_KEY),
None, tree)
continue
elif elem.tag.endswith(xes_constants.TAG_ID):
if parent is not None:
tree = parse_attribute(
elem, parent, elem.get(xes_constants.KEY_KEY),
elem.get(xes_constants.KEY_VALUE), tree)
continue
elif tree_event == _EVENT_END:
if elem in tree:
del tree[elem]
elem.clear()
if elem.getprevious() is not None:
try:
del elem.getparent()[0]
except TypeError:
pass
if elem.tag.endswith(xes_constants.TAG_EVENT):
self.reading_event = False
if self.acceptance_condition(self.event):
for attr in self.trace.attributes:
self.event[constants.CASE_ATTRIBUTE_PREFIX +
attr] = self.trace.attributes[attr]
return self.event
continue
elif elem.tag.endswith(xes_constants.TAG_TRACE):
self.reading_trace = False
continue
elif elem.tag.endswith(xes_constants.TAG_LOG):
self.reading_log = False
break
def preprocess_log(log, activities=None, parameters=None):
"""
Preprocess a log to enable correlation mining
Parameters
--------------
log
Log object
activities
(if provided) list of activities of the log
parameters
Parameters of the algorithm
Returns
--------------
transf_stream
Transformed stream
activities_grouped
Grouped activities
activities
List of activities of the log
"""
if parameters is None:
parameters = {}
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters,
xes_constants.DEFAULT_NAME_KEY)
timestamp_key = exec_utils.get_param_value(
Parameters.TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
start_timestamp_key = exec_utils.get_param_value(
Parameters.START_TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
index_key = exec_utils.get_param_value(Parameters.INDEX_KEY, parameters,
DEFAULT_INDEX_KEY)
if type(log) is pd.DataFrame:
# keep only the two columns before conversion
log = log[list(set([activity_key, timestamp_key,
start_timestamp_key]))]
parameters["deepcopy"] = False
parameters["include_case_attributes"] = False
log = converter.apply(log,
variant=converter.TO_EVENT_STREAM,
parameters=parameters)
transf_stream = EventStream()
for idx, ev in enumerate(log):
transf_stream.append(
Event({
activity_key: ev[activity_key],
timestamp_key: ev[timestamp_key].timestamp(),
start_timestamp_key: ev[start_timestamp_key].timestamp(),
index_key: idx
}))
transf_stream = sorted(
transf_stream,
key=lambda x: (x[start_timestamp_key], x[timestamp_key], x[index_key]))
if activities is None:
activities = sorted(list(set(x[activity_key] for x in transf_stream)))
activities_grouped = {
x: [y for y in transf_stream if y[activity_key] == x]
for x in activities
}
return transf_stream, activities_grouped, activities
def apply(frequency_dfg: Dict[Tuple[str, str], int],
start_activities: Dict[str, int],
end_activities: Dict[str, int],
parameters: Optional[Dict[Any, Any]] = None) -> EventLog:
"""
Simulates a log out with the transition probabilities provided by the frequency DFG,
and the time deltas provided by the performance DFG
Parameters
---------------
frequency_dfg
Frequency DFG
start_activities
Start activities
end_activities
End activities
parameters
Parameters of the algorithm, including:
- Parameters.NUM_TRACES: the number of traces of the simulated log
- Parameters.ACTIVITY_KEY: the activity key to be used in the simulated log
- Parameters.TIMESTAMP_KEY: the timestamp key to be used in the simulated log
- Parameters.CASE_ID_KEY: the case identifier key to be used in the simulated log
- Parameters.CASE_ARRIVAL_RATE: the average distance (in seconds) between the start of two cases (default: 1)
- Parameters.PERFORMANCE_DFG: (mandatory) the performance DFG that is used for the time deltas.
Returns
---------------
simulated_log
Simulated log
"""
if parameters is None:
parameters = {}
num_traces = exec_utils.get_param_value(Parameters.NUM_TRACES, parameters,
1000)
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY,
parameters,
xes_constants.DEFAULT_NAME_KEY)
timestamp_key = exec_utils.get_param_value(
Parameters.TIMESTAMP_KEY, parameters,
xes_constants.DEFAULT_TIMESTAMP_KEY)
case_id_key = exec_utils.get_param_value(Parameters.CASE_ID_KEY,
parameters,
xes_constants.DEFAULT_TRACEID_KEY)
case_arrival_rate = exec_utils.get_param_value(
Parameters.CASE_ARRIVAL_RATE, parameters, 1)
performance_dfg = copy(
exec_utils.get_param_value(Parameters.PERFORMANCE_DFG, parameters,
None))
frequency_dfg = copy(frequency_dfg)
artificial_start_activity = exec_utils.get_param_value(
Parameters.PARAM_ARTIFICIAL_START_ACTIVITY, parameters,
constants.DEFAULT_ARTIFICIAL_START_ACTIVITY)
artificial_end_activity = exec_utils.get_param_value(
Parameters.PARAM_ARTIFICIAL_END_ACTIVITY, parameters,
constants.DEFAULT_ARTIFICIAL_END_ACTIVITY)
for sa in start_activities:
frequency_dfg[(artificial_start_activity, sa)] = start_activities[sa]
performance_dfg[(artificial_start_activity, sa)] = 0
for ea in end_activities:
frequency_dfg[(ea, artificial_end_activity)] = end_activities[ea]
performance_dfg[(ea, artificial_end_activity)] = 0
choices = {}
for el in frequency_dfg:
if not el[0] in choices:
choices[el[0]] = {}
choices[el[0]][el[1]] = frequency_dfg[el]
if performance_dfg is None:
raise Exception(
"performance DFG simulation requires the Parameters.PERFORMANCE_DFG ('performance_dfg') parameter specification."
)
log = EventLog()
curr_st = 10000000
for i in range(num_traces):
curr_st += case_arrival_rate
curr_t = curr_st
trace = Trace(attributes={case_id_key: str(i)})
log.append(trace)
curr_act = artificial_start_activity
while True:
next_act = dict_based_choice(choices[curr_act])
if next_act == artificial_end_activity or next_act is None:
break
perf = performance_dfg[(curr_act, next_act)]
if type(perf) is dict:
perf = perf["mean"]
perf = 0 if perf == 0 else exponential(perf)
curr_t += perf
curr_act = next_act
eve = Event({
activity_key: curr_act,
timestamp_key: datetime.fromtimestamp(curr_t)
})
trace.append(eve)
return log