Class Metrics (2.10.0)

Stay organized with collections Save and categorize content based on your preferences.
Metrics(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Evaluation metrics, either in aggregate or about a specific entity.

Attributes

NameDescription
precision float
The calculated precision.
recall float
The calculated recall.
f1_score float
The calculated f1 score.
predicted_occurrences_count int
The amount of occurrences in predicted documents.
ground_truth_occurrences_count int
The amount of occurrences in ground truth documents.
predicted_document_count int
The amount of documents with a predicted occurrence.
ground_truth_document_count int
The amount of documents with a ground truth occurrence.
true_positives_count int
The amount of true positives.
false_positives_count int
The amount of false positives.
false_negatives_count int
The amount of false negatives.
total_documents_count int
The amount of documents that had an occurrence of this label.