tfma.metrics.PositiveLikelihoodRatio

Positive likelihood ratio (LR+).

tfma.metrics.PositiveLikelihoodRatio(
    thresholds: Optional[List[float]] = None,
    name: Text = POSITIVE_LIKELIHOOD_RATIO_NAME
)

thresholds Thresholds to use. Defaults to [0.5].
name Metric name.

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[Text]] = None,
    output_names: Optional[List[Text]] = None,
    sub_keys: Optional[List[tfma.metrics.SubKey]] = None,
    class_weights: Optional[Dict[int, float]] = None,
    query_key: Optional[Text] = None,
    is_diff: Optional[bool] = False
) -> tfma.metrics.MetricComputations

Creates computations associated with metric.

get_config

View source

get_config() -> tfma.types.Extracts

Returns serializable config.

result

View source

result(
    tp: float,
    tn: float,
    fp: float,
    fn: float
) -> float

Function for computing metric value from TP, TN, FP, FN values.