You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When using LightGBMBooster.saveNativeModel() function, it looks like the model doesn't include original column names, but using "Column_*" instead. Do I miss any config here? @little-eyes@imatiach-msft
The text was updated successfully, but these errors were encountered:
I think this is because I use spark pipeline model, where assembles all feature columns into one vector, and the lightgbm library doesn't have the original feature column names.. Not sure any good solution to add column names back, or need to implement sth like https://github.com/jpmml/jpmml-sparkml-xgboost?
@ywskycn yes, this is definitely something that needs to be fixed and @little-eyes already saw this issue before. I need to figure out a way to pass the column names to vector assembler and then from vector assembler pass them to native lightgbm code. It's something that would need to be investigated.
closing as PR to include column names (when they are available on slot metadata in features column) has been merged, see PR #526
The fix should be available in next release.
When using LightGBMBooster.saveNativeModel() function, it looks like the model doesn't include original column names, but using "Column_*" instead. Do I miss any config here? @little-eyes @imatiach-msft
The text was updated successfully, but these errors were encountered: