Kashif Mape

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

qhjqhj00 b308e26 766 B Updated 3 repo stars

File contents

kashif-mape

Metric kashif/mape from the HuggingFace evaluate library.

When to invoke

User asks to compute kashif/mape or wants HF evaluate's canonical version.

Recipe

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

Don'ts

  • Don't assume your in-house kashif/mape 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/kashif-mape commit b308e26b30

Frequently asked questions

npx skillmds add qhjqhj00/kashif-mape