qhjqhj00 mdocekal-multi-label-precision-recall-accuracy-fscore
Metric
mdocekal/multi_label_precision_recall_accuracy_fscorefrom the HuggingFaceevaluatelibrary.
When to invoke
User asks to compute mdocekal/multi_label_precision_recall_accuracy_fscore or wants HF evaluate's canonical version.
Recipe
import evaluate
metric = evaluate.load("mdocekal/multi_label_precision_recall_accuracy_fscore")
result = metric.compute(predictions=preds, references=refs)
print(result)
Don'ts
- Don't assume your in-house
mdocekal/multi_label_precision_recall_accuracy_fscorematches HF — version conventions vary. - Many evaluate metrics have task-specific arguments (
average=,lang=,model_type=); read the metric card before reporting numbers.