def get_kde_numeric_attribute_json(log, attribute, parameters=None): """ Gets the KDE estimation for the distribution of a numeric attribute values (expressed as JSON) Parameters ------------- log Event log object (if log, is converted) attribute Numeric 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 = transform.transform_event_log_to_event_stream(log) else: event_log = log values = [event[attribute] for event in event_log if attribute in event] return attributes_common.get_kde_numeric_attribute_json( values, parameters=parameters)
def get_kde_numeric_attribute_json(df, attribute, parameters=None): """ Gets the KDE estimation for the distribution of a numeric attribute values (expressed as JSON) """ values = df.select(attribute).rdd.map(lambda row: row[0]).collect() return attributes_common.get_kde_numeric_attribute_json( values, parameters=parameters)
def get_kde_numeric_attribute_json(df, attribute, parameters=None): """ Gets the KDE estimation for the distribution of a numeric attribute values (expressed as JSON) Parameters -------------- df Pandas dataframe attribute Numeric 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_numeric_attribute_json( values, parameters=parameters)