def test_case_statistics(self):
from pm4py.statistics.traces.generic.pandas import case_statistics
df = self.get_dataframe()
case_statistics.get_cases_description(df)
case_statistics.get_variants_df(df)
case_statistics.get_variant_statistics(df)
#case_statistics.get_variant_statistics_with_case_duration(df)
case_statistics.get_events(df, "N77802")
case_statistics.get_variants_df_with_case_duration(df)
case_statistics.get_variants_df_and_list(df)
case_statistics.get_kde_caseduration(df)
def get_variants_list(log, parameters=None):
"""
Gets the list of variants (along with their count) from the particular log type
Parameters
------------
log
Log
parameters
Parameters of the algorithm
Returns
-------------
variants_list
List of variants of the log (along with their count)
"""
from pm4py.statistics.traces.generic.pandas import case_statistics as pd_case_statistics
from pm4py.statistics.traces.generic.log import case_statistics as log_case_statistics
variants_list = []
if type(log) is pd.DataFrame:
pd_variants = pd_case_statistics.get_variant_statistics(
log, parameters=parameters)
for var in pd_variants:
varkeys = list(var.keys())
del varkeys[varkeys.index("variant")]
variants_list.append((var["variant"], var[varkeys[0]]))
else:
log_variants = log_case_statistics.get_variant_statistics(
log, parameters=parameters)
for var in log_variants:
varkeys = list(var.keys())
del varkeys[varkeys.index("variant")]
variants_list.append((var["variant"], var[varkeys[0]]))
return variants_list
def test_filtering_variants(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 = pd.read_csv(input_log)
dataframe = dataframe_utils.convert_timestamp_columns_in_df(dataframe)
variants = case_statistics.get_variant_statistics(dataframe)
chosen_variants = [variants[0]["variant"]]
dataframe = variants_filter.apply(dataframe, chosen_variants)
del dataframe
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.generic.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(pm4_constants.DEFAULT_VARIANT_SEP)
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 apply(log, parameters=None):
"""
Calculates the Working Together metric
Parameters
------------
log
Log
parameters
Possible parameters of the algorithm
Returns
-----------
tuple
Tuple containing the metric matrix and the resources list. Moreover, last boolean indicates that the metric is
not directed.
"""
if parameters is None:
parameters = {}
import numpy
from pm4py.statistics.traces.generic.pandas import case_statistics
resource_key = exec_utils.get_param_value(Parameters.RESOURCE_KEY, parameters, xes.DEFAULT_RESOURCE_KEY)
parameters_variants = {case_statistics.Parameters.ACTIVITY_KEY: resource_key,
case_statistics.Parameters.ATTRIBUTE_KEY: resource_key}
variants_occ = {x["variant"]: x["case:concept:name"] for x in
case_statistics.get_variant_statistics(log, parameters=parameters_variants)}
variants_resources = list(variants_occ.keys())
resources = [variants_util.get_activities_from_variant(y) for y in variants_resources]
flat_list = sorted(list(set([item for sublist in resources for item in sublist])))
metric_matrix = numpy.zeros((len(flat_list), len(flat_list)))
for idx, rv in enumerate(resources):
rvj = variants_resources[idx]
ord_res_list = sorted(list(set(rv)))
for i in range(len(ord_res_list) - 1):
res_i = flat_list.index(ord_res_list[i])
for j in range(i + 1, len(ord_res_list)):
res_j = flat_list.index(ord_res_list[j])
metric_matrix[res_i, res_j] += float(variants_occ[rvj]) / float(len(log))
metric_matrix[res_j, res_i] += float(variants_occ[rvj]) / float(len(log))
return [metric_matrix, flat_list, False]
def apply_auto_filter(df, parameters=None):
"""
Apply an automatic filter on variants
Parameters
-----------
df
Dataframe
parameters
Parameters of the algorithm, including:
Parameters.CASE_ID_KEY -> Column that contains the Case ID
Parameters.ACTIVITY_KEY -> Column that contains the activity
variants_df -> If provided, avoid recalculation of the variants dataframe
Parameters.DECREASING_FACTOR -> Decreasing factor that should be passed to the algorithm
Returns
-----------
df
Filtered dataframe
"""
if parameters is None:
parameters = {}
case_id_glue = exec_utils.get_param_value(Parameters.CASE_ID_KEY,
parameters, CASE_CONCEPT_NAME)
decreasing_factor = exec_utils.get_param_value(
Parameters.DECREASING_FACTOR, parameters,
filtering_constants.DECREASING_FACTOR)
variants_df = case_statistics.get_variants_df(df, parameters=parameters)
parameters["variants_df"] = variants_df
variants = case_statistics.get_variant_statistics(df,
parameters=parameters)
admitted_variants = []
if len(variants) > 0:
current_variant_count = variants[0][case_id_glue]
for i in range(len(variants)):
if variants[i][
case_id_glue] >= decreasing_factor * current_variant_count:
admitted_variants.append(variants[i]["variant"])
else:
break
current_variant_count = variants[i][case_id_glue]
return apply(df, admitted_variants, parameters=parameters)
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.generic.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(pm4_constants.DEFAULT_VARIANT_SEP)
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):
"""
Calculates the Subcontracting metric
Parameters
------------
log
Log
parameters
Possible parameters of the algorithm:
Parameters.N -> n of the algorithm proposed in the Wil SNA paper
Returns
-----------
tuple
Tuple containing the metric matrix and the resources list
"""
if parameters is None:
parameters = {}
import numpy
from pm4py.statistics.traces.generic.pandas import case_statistics
resource_key = exec_utils.get_param_value(Parameters.RESOURCE_KEY,
parameters,
xes.DEFAULT_RESOURCE_KEY)
n = exec_utils.get_param_value(Parameters.N, parameters, 2)
parameters_variants = {
case_statistics.Parameters.ACTIVITY_KEY: resource_key,
case_statistics.Parameters.ATTRIBUTE_KEY: resource_key
}
variants_occ = {
x["variant"]: x["case:concept:name"]
for x in case_statistics.get_variant_statistics(
log, parameters=parameters_variants)
}
variants_resources = list(variants_occ.keys())
resources = [
variants_util.get_activities_from_variant(y)
for y in variants_resources
]
flat_list = sorted(
list(set([item for sublist in resources for item in sublist])))
metric_matrix = numpy.zeros((len(flat_list), len(flat_list)))
sum_i_to_j = {}
for idx, rv in enumerate(resources):
rvj = variants_resources[idx]
for i in range(len(rv) - n):
res_i = flat_list.index(rv[i])
res_i_n = flat_list.index(rv[i + n])
if res_i == res_i_n:
if res_i not in sum_i_to_j:
sum_i_to_j[res_i] = {}
for j in range(i + 1, i + n):
res_j = flat_list.index(rv[j])
if res_j not in sum_i_to_j[res_i]:
sum_i_to_j[res_i][res_j] = 0
sum_i_to_j[res_i][res_j] += variants_occ[rvj]
dividend = 0
for idx, rv in enumerate(resources):
rvj = variants_resources[idx]
dividend = dividend + variants_occ[rvj] * (len(rv) - 1)
for key1 in sum_i_to_j:
for key2 in sum_i_to_j[key1]:
metric_matrix[key1][key2] = sum_i_to_j[key1][key2] / dividend
return [metric_matrix, flat_list, True]
def apply(log, parameters=None):
"""
Calculates the HW metric
Parameters
------------
log
Log
parameters
Possible parameters of the algorithm:
Paramters.BETA -> beta value as described in the Wil SNA paper
Returns
-----------
tuple
Tuple containing the metric matrix and the resources list. Moreover, last boolean indicates that the metric is
directed.
"""
if parameters is None:
parameters = {}
import numpy
from pm4py.statistics.traces.generic.pandas import case_statistics
resource_key = exec_utils.get_param_value(Parameters.RESOURCE_KEY, parameters, xes.DEFAULT_RESOURCE_KEY)
beta = exec_utils.get_param_value(Parameters.BETA, parameters, 0)
parameters_variants = {case_statistics.Parameters.ACTIVITY_KEY: resource_key,
case_statistics.Parameters.ATTRIBUTE_KEY: resource_key}
variants_occ = {x["variant"]: x["case:concept:name"] for x in
case_statistics.get_variant_statistics(log, parameters=parameters_variants)}
variants_resources = list(variants_occ.keys())
resources = [variants_util.get_activities_from_variant(y) for y in variants_resources]
flat_list = sorted(list(set([item for sublist in resources for item in sublist])))
metric_matrix = numpy.zeros((len(flat_list), len(flat_list)))
sum_i_to_j = {}
for idx, rv in enumerate(resources):
rvj = variants_resources[idx]
for i in range(len(rv) - 1):
res_i = flat_list.index(rv[i])
if not res_i in sum_i_to_j:
sum_i_to_j[res_i] = {}
for j in range(i + 1, len(rv)):
res_j = flat_list.index(rv[j])
if not res_j in sum_i_to_j[res_i]:
sum_i_to_j[res_i][res_j] = 0
if beta == 0:
sum_i_to_j[res_i][res_j] += variants_occ[rvj]
break
else:
sum_i_to_j[res_i][res_j] += variants_occ[rvj] * (beta ** (j - i - 1))
dividend = 0
for idx, rv in enumerate(resources):
rvj = variants_resources[idx]
if beta == 0:
dividend = dividend + variants_occ[rvj] * (len(rv) - 1)
else:
dividend = dividend + variants_occ[rvj] * (len(rv) - 1)
for key1 in sum_i_to_j:
for key2 in sum_i_to_j[key1]:
metric_matrix[key1][key2] = sum_i_to_j[key1][key2] / dividend
return [metric_matrix, flat_list, True]
