def select_attributes_from_log_for_tree(
log: EventLog,
max_cases_for_attr_selection=DEFAULT_MAX_CASES_FOR_ATTR_SELECTION,
max_diff_occ=DEFAULT_MAX_CASES_FOR_ATTR_SELECTION / 4):
"""
Select attributes from log for tree
Parameters
------------
log
Log
max_cases_for_attr_selection
Maximum number of cases to consider for attribute selection
max_diff_occ
Maximum number of different occurrences
Returns
------------
"""
log = log_converter.apply(log, variant=log_converter.Variants.TO_EVENT_LOG)
if len(log) > max_cases_for_attr_selection:
filtered_log = sampling.sample(log, max_cases_for_attr_selection)
else:
filtered_log = log
event_attributes = get_all_event_attributes_from_log(filtered_log)
trace_attributes = get_all_trace_attributes_from_log(filtered_log)
event_attributes_values = {}
trace_attributes_values = {}
for attr in event_attributes:
event_attributes_values[attr] = set(
get_attribute_values(log, attr).keys())
for attr in trace_attributes:
trace_attributes_values[attr] = set(
get_trace_attribute_values(log, attr).keys())
numeric_event_attributes_to_consider = list()
string_event_attributes_to_consider = list()
numeric_trace_attributes_to_consider = list()
string_trace_attributes_to_consider = list()
for attr in event_attributes_values:
if type(list(event_attributes_values[attr])[0]) is int or type(
list(event_attributes_values[attr])[0]) is float:
numeric_event_attributes_to_consider.append(attr)
elif type(list(event_attributes_values[attr])[0]) is str and len(
event_attributes_values[attr]) < max_diff_occ:
string_event_attributes_to_consider.append(attr)
for attr in trace_attributes_values:
if type(list(trace_attributes_values[attr])[0]) is int or type(
list(trace_attributes_values[attr])[0]) is float:
numeric_trace_attributes_to_consider.append(attr)
elif type(list(trace_attributes_values[attr])[0]) is str and len(
trace_attributes_values[attr]) < max_diff_occ:
string_trace_attributes_to_consider.append(attr)
numeric_event_attributes_to_consider = check_event_attributes_presence(
log, numeric_event_attributes_to_consider)
string_event_attributes_to_consider = check_event_attributes_presence(
log, string_event_attributes_to_consider)
numeric_trace_attributes_to_consider = check_trace_attributes_presence(
log, numeric_trace_attributes_to_consider)
string_trace_attributes_to_consider = check_trace_attributes_presence(
log, string_trace_attributes_to_consider)
return string_trace_attributes_to_consider, string_event_attributes_to_consider, numeric_trace_attributes_to_consider, numeric_event_attributes_to_consider
def apply(log: Union[EventLog, EventStream, pd.DataFrame],
trace_attribute: str,
variant=VARIANT_DMM_LEVEN,
parameters: Optional[Dict[Any, Any]] = None) -> Any:
"""
Apply the hierarchical clustering to a log starting from a trace attribute.
MSc Thesis is available at: https://www.pads.rwth-aachen.de/global/show_document.asp?id=aaaaaaaaalpxgft&download=1
Defense slides are available at: https://www.pads.rwth-aachen.de/global/show_document.asp?id=aaaaaaaaalpxgqx&download=1
Parameters
----------------
log
Log
trace_attribute
Trace attribute to exploit for the clustering
variant
Variant of the algorithm to apply, possible values:
- Variants.VARIANT_DMM_LEVEN (that is the default)
- Variants.VARIANT_AVG_LEVEN
- Variants.VARIANT_DMM_VEC
- Variants.VARIANT_AVG_VEC
- Variants.DFG
Returns
-----------------
tree
Hierarchical cluster tree
leafname
Root node
"""
if parameters is None:
parameters = {}
log = log_converter.apply(log,
variant=log_converter.Variants.TO_EVENT_LOG,
parameters=parameters)
percent = 1
alpha = 0.5
list_of_vals = []
list_log = []
list_of_vals_dict = attributes_filter.get_trace_attribute_values(
log, trace_attribute)
list_of_vals_keys = list(list_of_vals_dict.keys())
for i in range(len(list_of_vals_keys)):
list_of_vals.append(list_of_vals_keys[i])
for i in range(len(list_of_vals)):
logsample = merge_log.log2sublog(log, list_of_vals[i], trace_attribute)
list_log.append(logsample)
y = exec_utils.get_variant(variant)(list_log, percent, alpha)
Z = linkage(y, method='average')
# Create dictionary for labeling nodes by their IDs
id2name = dict(zip(range(len(list_of_vals)), list_of_vals))
T = to_tree(Z, rd=False)
d3Dendro = dict(children=[], name="Root1")
merge_log.add_node(T, d3Dendro)
leafname = merge_log.label_tree(d3Dendro["children"][0], id2name)
d3Dendro = d3Dendro["children"][0]
d3Dendro["name"] = 'root'
tree = d3Dendro
trilist = bfs(tree)
trilist[0][0] = trilist[0][1] + '-' + trilist[0][2]
rootlist = []
for ele in trilist:
rootlist.append(ele[0])
return tree, leafname