Ctrl+K

climpred.metrics._smape

Contents

climpred.metrics._smape#

climpred.metrics._smape(forecast: Dataset, verif: Dataset, dim: str | List[str] | None = None, **metric_kwargs: Any) → Dataset[source]#

Symmetric Mean Absolute Percentage Error (sMAPE).

Similar to the Mean Absolute Percentage Error (mape), but sums the forecast and observation mean in the denominator.

sMAPE = \frac{1}{n} \sum \frac{|f-o|}{|f|+|o|}

Parameters:

  • forecast – Forecast.

  • verif – Verification data.

  • dim – Dimension(s) to perform metric over.

  • metric_kwargs – see xskillscore.smape()

Notes

minimum

0.0

maximum

1.0

perfect

0.0

orientation

negative

See also

Example

>>> HindcastEnsemble.verify(
...     metric="smape", comparison="e2o", alignment="same_verifs", dim="init"
... )
<xarray.Dataset>
Dimensions:  (lead: 10)
Coordinates:
  * lead     (lead) int32 1 2 3 4 5 6 7 8 9 10
    skill    <U11 'initialized'
Data variables:
    SST      (lead) float64 0.3801 0.3906 0.4044 0.3819 ... 0.4822 0.5054 0.5295
Attributes:
    prediction_skill_software:     climpred https://climpred.readthedocs.io/
    skill_calculated_by_function:  HindcastEnsemble.verify()
    number_of_initializations:     64
    number_of_members:             10
    alignment:                     same_verifs
    metric:                        smape
    comparison:                    e2o
    dim:                           init
    reference:                     []
Contents