Skip to main content

Precision

Metric
DashAI.back.metrics.classification.Precision

Fraction of positive predictions that are actually correct.

Precision (also called positive predictive value) measures the ability of the classifier to avoid labelling negative samples as positive. It is the metric of choice when the cost of false positives is high — e.g. in spam detection, flagging a legitimate email is more costly than missing a spam.

For binary tasks the standard binary precision is used. For multiclass tasks, macro averaging (unweighted mean over all classes) is applied.

::

Precision = TP / (TP + FP)

Range: [0, 1], higher is better (MAXIMIZE = True).

References​

Methods​

score(true_labels: 'DashAIDataset', probs_pred_labels: 'np.ndarray', multiclass: Optional[bool] = None) -> float

Defined on Precision

Calculate precision between true labels and predicted labels.

Parameters

true_labels : DashAIDataset
A DashAI dataset with labels.
probs_pred_labels : np.ndarray
A two-dimensional matrix in which each column represents a class and the row values represent the probability that an example belongs to the class associated with the column.
multiclass : bool, optional
Whether the task is a multiclass classification. If None, it will be determined automatically from the number of unique labels.

Returns

float
Precision score between true labels and predicted labels

get_metadata(cls: 'BaseMetric') -> Dict[str, Any]

Defined on BaseMetric

Get metadata values for the current metric.

Returns

Dict[str, Any]
Dictionary with the metadata

is_multiclass(true_labels: 'np.ndarray') -> bool

Defined on ClassificationMetric

Determine if the classification problem is multiclass (more than 2 classes).

Parameters

true_labels : np.ndarray
Array of true labels.

Returns

bool
True if the problem has more than 2 unique classes, False otherwise.

Compatible with​