def filter_log_by_variants_percentage(log, variants, variants_percentage=0.0):
"""
Filter the log by variants percentage
Parameters
----------
log
Log
variants
Dictionary with variant as the key and the list of traces as the value
variants_percentage
Percentage of variants that should be kept (the most common variant is always kept)
Returns
----------
filtered_log
Filtered log
"""
filtered_log = EventLog()
no_of_traces = len(log)
variant_count = get_variants_sorted_by_count(variants)
already_added_sum = 0
for i in range(len(variant_count)):
variant = variant_count[i][0]
varcount = variant_count[i][1]
percentage_already_added = already_added_sum / no_of_traces
if already_added_sum == 0 or percentage_already_added < variants_percentage:
for trace in variants[variant]:
filtered_log.append(trace)
already_added_sum = already_added_sum + varcount
return filtered_log
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 = get_variants(log, parameters=parameters)
variant_count = get_variants_sorted_by_count(variants)
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 filter_variants_variants_percentage(log,
variants,
variants_percentage=0.0):
"""
Filter the log by variants percentage
Parameters
----------
log
Log
variants
Dictionary with variant as the key and the list of traces as the value
variants_percentage
Percentage of variants that should be kept (the most common variant is always kept)
Returns
----------
filtered_log
Filtered log
"""
filtered_log = EventLog(list(),
attributes=log.attributes,
extensions=log.extensions,
classifiers=log.classifiers,
omni_present=log.omni_present,
properties=log.properties)
no_of_traces = len(log)
variant_count = get_variants_sorted_by_count(variants)
already_added_sum = 0
shall_break_under = -1
for i in range(len(variant_count)):
variant = variant_count[i][0]
varcount = variant_count[i][1]
if varcount < shall_break_under:
break
for trace in variants[variant]:
filtered_log.append(trace)
already_added_sum = already_added_sum + varcount
percentage_already_added = already_added_sum / no_of_traces
if percentage_already_added >= variants_percentage:
shall_break_under = varcount
return filtered_log
def find_auto_threshold(log, variants, decreasing_factor):
"""
Find automatically variants filtering threshold
based on specified decreasing factor
Parameters
----------
log
Log
variants
Dictionary with variant as the key and the list of traces as the value
decreasing_factor
Decreasing factor (stops the algorithm when the next variant by occurrence is below this factor
in comparison to previous)
Returns
----------
variantsPercentage
Percentage of variants to keep in the log
"""
no_of_traces = len(log)
variant_count = get_variants_sorted_by_count(variants)
already_added_sum = 0
prev_var_count = -1
percentage_already_added = 0
for i in range(len(variant_count)):
varcount = variant_count[i][1]
percentage_already_added = already_added_sum / no_of_traces
if already_added_sum == 0 or varcount > decreasing_factor * prev_var_count:
already_added_sum = already_added_sum + varcount
else:
break
prev_var_count = varcount
percentage_already_added = already_added_sum / no_of_traces
return percentage_already_added
