XGboost estimator will throw error when multiple evaluation metrics are given

instacart / lore

Lore makes machine learning approachable for Software Engineers and maintainable for Machine Learning Researchers

MIT License

1.55k stars 135 forks source link

XGboost estimator will throw error when multiple evaluation metrics are given #123

Open everglory99 opened 5 years ago

everglory99 commented 5 years ago

In xgboost scikit-learn fit API, the argument eval_metric can be a string for single metric or a list of string for multiple metrics. However, if we provide a list to the eval_metric, it will break the fit method in lore.estimators.xgboost.base. Specifically, in this and that. Can we support multiple eval metrics? I can submit a PR to fix this. Thanks!

montanalow commented 5 years ago

A PR would be much appreciated, including a test case that demonstrates the functionality.