def get_kde_date_attribute_json(log, attribute=DEFAULT_TIMESTAMP_KEY, parameters=None):
"""
Gets the KDE estimation for the distribution of a date attribute values
(expressed as JSON)
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_conv_fact.apply(log, variant=log_conv_fact.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_json(values, parameters=parameters)
def get_kde_date_attribute_json(df,
attribute=DEFAULT_TIMESTAMP_KEY,
parameters=None):
"""
Gets the KDE estimation for the distribution of a date attribute values
(expressed as JSON)
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
--------------
json
JSON representing the graph points
"""
values = list(df.dropna(subset=[attribute])[attribute])
return attributes_common.get_kde_date_attribute_json(values,
parameters=parameters)
def get_kde_date_attribute_json(df,
attribute=DEFAULT_TIMESTAMP_KEY,
parameters=None):
"""
Gets the KDE estimation for the distribution of a date attribute values
(expressed as JSON)
"""
values = df.select(attribute).rdd.map(lambda row: row[0]).collect()
return attributes_common.get_kde_date_attribute_json(values,
parameters=parameters)
