SMAPE

class SMAPE(mode: str = MetricAggregationMode.per_segment, **kwargs)

Bases: etna.metrics.base.Metric

Symmetric mean absolute percentage error metric with multi-segment computation support.

$$SMAPE(y\mathrm{\_}true,y\mathrm{\_}pred)=\frac{2\cdot 100\mathrm{\%}}{n}\cdot \frac{\sum _{i=0}^{n-1}\mid y\mathrm{\_}tru{e}_i-y\mathrm{\_}pre{d}_i\mid }{\mid y\mathrm{\_}tru{e}_i\mid +\mid y\mathrm{\_}pre{d}_i\mid }$$

Notes

You can read more about logic of multi-segment metrics in Metric docs.

Init metric.

Parameters

• mode ('macro' or 'per-segment') – metrics aggregation mode

• kwargs – metric’s computation arguments

Inherited-members

Methods

to_dict()

Collect all information about etna object in dict.

Attributes

greater_is_better	Whether higher metric value is better.
name	Name of the metric for representation.

property greater_is_better: bool

Whether higher metric value is better.