MaxDeviation

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

Bases: etna.metrics.base.Metric

Max Deviation metric with multi-segment computation support (maximum deviation value of cumulative sums).

$$MaxDeviation(y\mathrm{\_}true,y\mathrm{\_}pred)=\underset{j}{max}|y_j|,where{y}_j=\sum _{i=1}^{j}y\mathrm{\_}pre{d}_i-y\mathrm{\_}tru{e}_i$$

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.