evaluate.eval_mae()

Mean absolute error using the forecast sample median as point estimate.

Usage

Source

evaluate.eval_mae(
    pred,
    truth,
)

A pure JAX scalar kernel (see Metric). pred and truth are moved to device memory first (float_view()), so either (or both) may be host-committed, e.g. draws sampled with device="host". An integer operand (the draws of a count model) is cast to the default float dtype in the same step.

Parameters

pred: Real[ArrayLike, " sample *batch"]

Forecast samples with the sample axis first.

truth: Real[ArrayLike, " *batch"]

Ground-truth values (matching pred without the sample axis).

Returns

Array

The mean absolute error as a scalar array.

Raises

ValueError

If truth.shape is not pred.shape[1:] (see Metric).