Spaces:

evaluate-metric

/

accuracy

like 19

Running

The examples on this metric card seem to be missing an import evaluate or from evaluate import load step, e.g. one has:

>>> accuracy_metric = evaluate.load("accuracy")
>>> results = accuracy_metric.compute(references=[0, 1], predictions=[0, 1])
>>> print(results)
{'accuracy': 1.0}

It would be nice to include the import so that users can copy-paste the snippet and it "just works".