tfma.metrics.MeanAbsoluteError

View source on GitHub

Calculates the mean of absolute error between labels and predictions.

Inherits From: Metric

tfma.metrics.MeanAbsoluteError(
    name: str = MEAN_ABSOLUTE_ERROR_NAME
)

Formula: error = abs(label - prediction)

The metric computes the mean of absolute error between labels and predictions. The labels and predictions should be floats.

Args
name	The name of the metric.

Attributes
compute_confidence_interval	Whether to compute confidence intervals for this metric. Note that this may not completely remove the computational overhead involved in computing a given metric. This is only respected by the jackknife confidence interval method.

Methods

computations

View source

computations(
    eval_config: Optional[tfma.EvalConfig] = None,
    schema: Optional[schema_pb2.Schema] = None,
    model_names: Optional[List[str]] = None,
    output_names: Optional[List[str]] = None,
    sub_keys: Optional[List[Optional[SubKey]]] = None,
    aggregation_type: Optional[AggregationType] = None,
    class_weights: Optional[Dict[int, float]] = None,
    example_weighted: bool = False,
    query_key: Optional[str] = None
) -> tfma.metrics.MetricComputations

Creates computations associated with metric.

from_config

View source

@classmethod
from_config(
    config: Dict[str, Any]
) -> 'Metric'

get_config

View source

get_config() -> Dict[str, Any]

Returns serializable config.