Skip to content

fbeta_multi_label_measure

allennlp.training.metrics.fbeta_multi_label_measure

[SOURCE]


FBetaMultiLabelMeasure

@Metric.register("fbeta_multi_label")
class FBetaMultiLabelMeasure(FBetaMeasure):
 | def __init__(
 |     self,
 |     beta: float = 1.0,
 |     average: str = None,
 |     labels: List[int] = None,
 |     threshold: float = 0.5
 | ) -> None

Compute precision, recall, F-measure and support for multi-label classification.

The precision is the ratio tp / (tp + fp) where tp is the number of true positives and fp the number of false positives. The precision is intuitively the ability of the classifier not to label as positive a sample that is negative.

The recall is the ratio tp / (tp + fn) where tp is the number of true positives and fn the number of false negatives. The recall is intuitively the ability of the classifier to find all the positive samples.

The F-beta score can be interpreted as a weighted harmonic mean of the precision and recall, where an F-beta score reaches its best value at 1 and worst score at 0.

If we have precision and recall, the F-beta score is simply: F-beta = (1 + beta ** 2) * precision * recall / (beta ** 2 * precision + recall)

The F-beta score weights recall more than precision by a factor of beta. beta == 1.0 means recall and precision are equally important.

The support is the number of occurrences of each class in y_true.

Parameters

  • beta : float, optional (default = 1.0)
    The strength of recall versus precision in the F-score.

  • average : str, optional (default = None)
    If None, the scores for each class are returned. Otherwise, this determines the type of averaging performed on the data:

    'micro': Calculate metrics globally by counting the total true positives, false negatives and false positives. 'macro': Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. 'weighted': Calculate metrics for each label, and find their average weighted by support (the number of true instances for each label). This alters 'macro' to account for label imbalance; it can result in an F-score that is not between precision and recall.

  • labels : list, optional
    The set of labels to include and their order if average is None. Labels present in the data can be excluded, for example to calculate a multi-class average ignoring a majority negative class. Labels not present in the data will result in 0 components in a macro or weighted average.

  • threshold : float, optional (default = 0.5)
    Probabilities over this threshold will be considered predictions for the corresponding class. Note that you can also use this metric with logits, in which case it would make more sense to set the threshold value to 0.0.

__call__

class FBetaMultiLabelMeasure(FBetaMeasure):
 | ...
 | def __call__(
 |     self,
 |     predictions: torch.Tensor,
 |     gold_labels: torch.Tensor,
 |     mask: Optional[torch.BoolTensor] = None
 | )

Parameters

  • predictions : torch.Tensor
    A tensor of predictions of shape (batch_size, ..., num_classes).
  • gold_labels : torch.Tensor
    A tensor of boolean labels of shape (batch_size, ..., num_classes). It must be the same shape as the predictions.
  • mask : torch.BoolTensor, optional (default = None)
    A masking tensor the same size as gold_labels.

F1MultiLabelMeasure

@Metric.register("f1_multi_label")
class F1MultiLabelMeasure(FBetaMultiLabelMeasure):
 | def __init__(
 |     self,
 |     average: str = None,
 |     labels: List[int] = None,
 |     threshold: float = 0.5
 | ) -> None