def get_kde_caseduration_json(df, parameters=None):
"""
Gets the estimation of KDE density for the case durations calculated on the Spark dataframe
(expressed as JSON)
"""
cases = get_cases_description(df, parameters=parameters)
duration_values = [x["caseDuration"] for x in cases.values()]
return case_duration_commons.get_kde_caseduration_json(
duration_values, parameters=parameters)
def get_kde_caseduration_json(log, parameters=None):
"""
Gets the estimation of KDE density for the case durations calculated on the log_skeleton
(expressed as JSON)
Parameters
--------------
log
Log object
parameters
Possible parameters of the algorithm, including:
Parameters.GRAPH_POINTS -> number of points to include in the graph
Parameters.CASE_ID_KEY -> Column hosting the Case ID
Returns
--------------
json
JSON representing the graph points
"""
cases = get_cases_description(log, parameters=parameters)
duration_values = [x["caseDuration"] for x in cases.values()]
return case_duration_commons.get_kde_caseduration_json(duration_values, parameters=parameters)
def get_kde_caseduration_json(df, parameters=None):
"""
Gets the estimation of KDE density for the case durations calculated on the log/dataframe
(expressed as JSON)
Parameters
--------------
df
Pandas dataframe
parameters
Possible parameters of the algorithm, including:
graph_points -> number of points to include in the graph
case_id_glue -> Column hosting the Case ID
Returns
--------------
json
JSON representing the graph points
"""
cases = get_cases_description(df, parameters=parameters)
duration_values = [x["caseDuration"] for x in cases.values()]
return case_duration_commons.get_kde_caseduration_json(duration_values, parameters=parameters)