def apply(log, parameters):
"""
Apply the IM_F algorithm to a log obtaining a Petri net along with an initial and final marking
Parameters
-----------
log
Log
parameters
Parameters of the algorithm, including:
Parameters.ACTIVITY_KEY -> attribute of the log to use as activity name
(default concept:name)
Returns
-----------
net
Petri net
initial_marking
Initial marking
final_marking
Final marking
"""
if pkgutil.find_loader("pandas"):
import pandas as pd
from pm4py.statistics.variants.pandas import get as variants_get
if type(log) is pd.DataFrame:
vars = variants_get.get_variants_count(log, parameters=parameters)
return apply_variants(vars, parameters=parameters)
log = converter.apply(log, parameters=parameters)
net, initial_marking, final_marking = tree_to_petri.apply(apply_tree(log, parameters))
return net, initial_marking, final_marking
def filter_variants_top_k(log, k, parameters=None):
"""
Keeps the top-k variants of the log
Parameters
-------------
log
Event log
k
Number of variants that should be kept
parameters
Parameters
Returns
-------------
filtered_log
Filtered log
"""
if parameters is None:
parameters = {}
variants = variants_get.get_variants_count(log, parameters=parameters)
variant_count = []
for variant in variants:
variant_count.append([variant, variants[variant]])
variant_count = sorted(variant_count,
key=lambda x: (x[1], x[0]),
reverse=True)
variant_count = variant_count[:min(k, len(variant_count))]
variants_to_filter = [x[0] for x in variant_count]
return apply(log, variants_to_filter, parameters=parameters)
def apply(log, parameters=None):
"""
Apply the IM algorithm to a log obtaining a Petri net along with an initial and final marking
Parameters
-----------
log
Log
parameters
Parameters of the algorithm, including:
Parameters.ACTIVITY_KEY -> attribute of the log to use as activity name
(default concept:name)
Returns
-----------
net
Petri net
initial_marking
Initial marking
final_marking
Final marking
"""
if type(log) is pd.DataFrame:
vars = variants_get.get_variants_count(log, parameters=parameters)
return apply_variants(vars, parameters=parameters)
else:
log = converter.apply(log, parameters=parameters)
net, initial_marking, final_marking = tree_to_petri.apply(
apply_tree(log, parameters))
return net, initial_marking, final_marking
def filter_variants_by_coverage_percentage(log,
min_coverage_percentage,
parameters=None):
"""
Filters the variants of the log by a coverage percentage
(e.g., if min_coverage_percentage=0.4, and we have a log with 1000 cases,
of which 500 of the variant 1, 400 of the variant 2, and 100 of the variant 3,
the filter keeps only the traces of variant 1 and variant 2).
Parameters
---------------
log
Event log
min_coverage_percentage
Minimum allowed percentage of coverage
parameters
Parameters
Returns
---------------
filtered_log
Filtered log
"""
if parameters is None:
parameters = {}
case_id_glue = exec_utils.get_param_value(Parameters.CASE_ID_KEY,
parameters, CASE_CONCEPT_NAME)
variants = variants_get.get_variants_count(log, parameters=parameters)
allowed_variants = [
x for x, y in variants.items()
if y >= min_coverage_percentage * log[case_id_glue].nunique()
]
return apply(log, allowed_variants, parameters=parameters)
def apply_tree(log, parameters):
"""
Apply the IM_FF algorithm to a log obtaining a process tree
Parameters
----------
log
Log
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
"""
if parameters is None:
parameters = {}
if pkgutil.find_loader("pandas"):
import pandas as pd
from pm4py.statistics.variants.pandas import get as variants_get
if type(log) is pd.DataFrame:
vars = variants_get.get_variants_count(log, parameters=parameters)
return apply_tree_variants(vars, parameters=parameters)
activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters,
pmutil.xes_constants.DEFAULT_NAME_KEY)
log = converter.apply(log, parameters=parameters)
# keep only the activity attribute (since the others are not used)
log = filtering_utils.keep_only_one_attribute_per_event(log, activity_key)
noise_threshold = exec_utils.get_param_value(Parameters.NOISE_THRESHOLD, parameters,
shared_constants.NOISE_THRESHOLD_IMF)
dfg = [(k, v) for k, v in dfg_inst.apply(log, parameters=parameters).items() if v > 0]
c = Counts()
activities = attributes_get.get_attribute_values(log, activity_key)
start_activities = list(start_activities_get.get_start_activities(log, parameters=parameters).keys())
end_activities = list(end_activities_get.get_end_activities(log, parameters=parameters).keys())
contains_empty_traces = False
traces_length = [len(trace) for trace in log]
if traces_length:
contains_empty_traces = min([len(trace) for trace in log]) == 0
# set the threshold parameter based on f and the max value in the dfg:
max_value = 0
for key, value in dfg:
if value > max_value:
max_value = value
threshold = noise_threshold * max_value
recursion_depth = 0
sub = subtree.make_tree(log, dfg, dfg, dfg, activities, c, recursion_depth, noise_threshold, threshold,
start_activities, end_activities,
start_activities, end_activities, parameters=parameters)
process_tree = get_tree_repr_implain.get_repr(sub, 0, contains_empty_traces=contains_empty_traces)
# Ensures consistency to the parent pointers in the process tree
tree_consistency.fix_parent_pointers(process_tree)
# Fixes a 1 child XOR that is added when single-activities flowers are found
tree_consistency.fix_one_child_xor_flower(process_tree)
# folds the process tree (to simplify it in case fallthroughs/filtering is applied)
process_tree = util.fold(process_tree)
return process_tree
def apply_tree(log, parameters=None):
"""
Apply the IM algorithm to a log obtaining a process tree
Parameters
----------
log
Log
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
"""
if parameters is None:
parameters = {}
if type(log) is pd.DataFrame:
vars = variants_get.get_variants_count(log, parameters=parameters)
return apply_tree_variants(vars, parameters=parameters)
else:
activity_key = exec_utils.get_param_value(
Parameters.ACTIVITY_KEY, parameters,
pmutil.xes_constants.DEFAULT_NAME_KEY)
log = converter.apply(log, parameters=parameters)
# since basic IM is influenced once per variant, it makes sense to keep one trace per variant
log = filtering_utils.keep_one_trace_per_variant(log,
parameters=parameters)
# keep only the activity attribute (since the others are not used)
log = filtering_utils.keep_only_one_attribute_per_event(
log, activity_key)
dfg = [(k, v)
for k, v in dfg_inst.apply(log, parameters=parameters).items()
if v > 0]
c = Counts()
activities = attributes_filter.get_attribute_values(log, activity_key)
start_activities = list(
start_activities_filter.get_start_activities(
log, parameters=parameters).keys())
end_activities = list(
end_activities_filter.get_end_activities(
log, parameters=parameters).keys())
contains_empty_traces = False
traces_length = [len(trace) for trace in log]
if traces_length:
contains_empty_traces = min([len(trace) for trace in log]) == 0
recursion_depth = 0
sub = subtree.make_tree(log, dfg, dfg, dfg, activities, c,
recursion_depth, 0.0, start_activities,
end_activities, start_activities,
end_activities, parameters)
process_tree = get_tree_repr_implain.get_repr(
sub, 0, contains_empty_traces=contains_empty_traces)
# Ensures consistency to the parent pointers in the process tree
tree_consistency.fix_parent_pointers(process_tree)
# Fixes a 1 child XOR that is added when single-activities flowers are found
tree_consistency.fix_one_child_xor_flower(process_tree)
# folds the process tree (to simplify it in case fallthroughs/filtering is applied)
process_tree = util.fold(process_tree)
return process_tree
