tensorflow_model_analysis/metrics/calibration.py [49:79]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    eval_config: Optional[config_pb2.EvalConfig] = None,
    model_name: str = '',
    output_name: str = '',
    sub_key: Optional[metric_types.SubKey] = None,
    aggregation_type: Optional[metric_types.AggregationType] = None,
    class_weights: Optional[Dict[int, float]] = None,
    example_weighted: bool = False) -> metric_types.MetricComputations:
  """Returns metric computations for mean label."""
  key = metric_types.MetricKey(
      name=name,
      model_name=model_name,
      output_name=output_name,
      sub_key=sub_key,
      example_weighted=example_weighted)

  # Make sure weighted_labels_predictions_examples are calculated.
  computations = _weighted_labels_predictions_examples(
      eval_config=eval_config,
      model_name=model_name,
      output_name=output_name,
      sub_key=sub_key,
      aggregation_type=aggregation_type,
      class_weights=class_weights,
      example_weighted=example_weighted)
  weighted_labels_predictions_key = computations[-1].keys[-1]

  def result(
      metrics: Dict[metric_types.MetricKey, Any]
  ) -> Dict[metric_types.MetricKey, Any]:
    """Returns mean label."""
    metric = metrics[weighted_labels_predictions_key]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow_model_analysis/metrics/calibration.py [175:205]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    eval_config: Optional[config_pb2.EvalConfig] = None,
    model_name: str = '',
    output_name: str = '',
    sub_key: Optional[metric_types.SubKey] = None,
    aggregation_type: Optional[metric_types.AggregationType] = None,
    class_weights: Optional[Dict[int, float]] = None,
    example_weighted: bool = False) -> metric_types.MetricComputations:
  """Returns metric computations for calibration."""
  key = metric_types.MetricKey(
      name=name,
      model_name=model_name,
      output_name=output_name,
      sub_key=sub_key,
      example_weighted=example_weighted)

  # Make sure weighted_labels_predictions_examples are calculated.
  computations = _weighted_labels_predictions_examples(
      eval_config=eval_config,
      model_name=model_name,
      output_name=output_name,
      sub_key=sub_key,
      aggregation_type=aggregation_type,
      class_weights=class_weights,
      example_weighted=example_weighted)
  weighted_labels_predictions_key = computations[-1].keys[-1]

  def result(
      metrics: Dict[metric_types.MetricKey, Any]
  ) -> Dict[metric_types.MetricKey, Any]:
    """Returns calibration."""
    metric = metrics[weighted_labels_predictions_key]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -