def get_kde_date_attribute(log, attribute=DEFAULT_TIMESTAMP_KEY, parameters=None):
"""
Gets the KDE estimation for the distribution of a date attribute values
Parameters
-------------
log
Event stream object (if log, is converted)
attribute
Date attribute to analyse
parameters
Possible parameters of the algorithm, including:
graph_points -> number of points to include in the graph
Returns
--------------
x
X-axis values to represent
y
Y-axis values to represent
"""
if type(log) is EventLog:
event_log = log_conversion.apply(log, variant=log_conversion.TO_EVENT_STREAM)
else:
event_log = log
values = [event[attribute].replace(tzinfo=None) for event in event_log if attribute in event]
return attributes_common.get_kde_date_attribute(values, parameters=parameters)
def get_kde_date_attribute(df,
attribute=DEFAULT_TIMESTAMP_KEY,
parameters=None):
"""
Gets the KDE estimation for the distribution of a date attribute values
Parameters
-------------
df
Pandas dataframe
attribute
Date attribute to analyse
parameters
Possible parameters of the algorithm, including:
graph_points -> number of points to include in the graph
Returns
--------------
x
X-axis values to represent
y
Y-axis values to represent
"""
if parameters is None:
parameters = {}
max_no_of_points_to_sample = exec_utils.get_param_value(
Parameters.MAX_NO_POINTS_SAMPLE, parameters, 100000)
red_df = df.dropna(subset=[attribute])
if len(red_df) > max_no_of_points_to_sample:
red_df = red_df.sample(n=max_no_of_points_to_sample)
date_values = list(red_df[attribute])
return attributes_common.get_kde_date_attribute(date_values,
parameters=parameters)
