Jarod0411 Aucpr

Compute jarod0411/aucpr via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of jarod0411/aucpr.

qhjqhj00 8a76e9a 798 B Updated 3 repo stars

File contents

jarod0411-aucpr

Metric jarod0411/aucpr from the HuggingFace evaluate library.

When to invoke

User asks to compute jarod0411/aucpr or wants HF evaluate's canonical version.

Recipe

import evaluate
metric = evaluate.load("jarod0411/aucpr")
result = metric.compute(predictions=preds, references=refs)
print(result)

Don'ts

  • Don't assume your in-house jarod0411/aucpr matches HF — version conventions vary.
  • Many evaluate metrics have task-specific arguments (average=, lang=, model_type=); read the metric card before reporting numbers.

qhjqhj00/research-skills-pool/tree/main/skill-factory/output/jarod0411-aucpr commit 8a76e9a23a

Frequently asked questions

npx skillmds add qhjqhj00/jarod0411-aucpr