sdv.metrics.timeseries.TimeSeriesDetectionMetric

class sdv.metrics.timeseries.TimeSeriesDetectionMetric[source]

Base class for Machine Learning Detection based metrics on time series.

These metrics build a Machine Learning Classifier that learns to tell the synthetic data apart from the real data, which later on is evaluated using Cross Validation.

The output of the metric is one minus the average ROC AUC score obtained.

name

Name to use when reports about this metric are printed.

Type

str

goal

The goal of this metric.

Type

sdmetrics.goal.Goal

min_value

Minimum value or values that this metric can take.

Type

Union[float, tuple[float]]

max_value

Maximum value or values that this metric can take.

Type

Union[float, tuple[float]]

__init__()

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__()

Initialize self.

compute(real_data, synthetic_data[, …])

Compute this metric.

get_subclasses([include_parents])

Recursively find subclasses of this metric.

normalize(raw_score)

Returns the raw_score as is, since it is already normalized.

Attributes

goal

max_value

min_value

name