light gbm - python API vs Scikit-learn API

Question

I was trying to apply lgbm in one of my problems. For that I was going through "http://lightgbm.readthedocs.io/en/latest/Python-API.html". However, I have a basic question. Is there any difference between Training API and Scikit-learn API? Can we use both the APIs to achieve same result for the same problem?

Thanks, Dipanjan.

Answer 1

The answer to your question is yes you can provide identical results. when you configure in an identical way they provide identical results

Because sklear API is a wrapper of the native training API. this is again a wrapper c++ library. 

It is your choice of choosing which to make use of. My personal advice to use sklearn API because of 2 advantages:

1. You can use the entire sklearn toolkit.
2. If there is any requirement of switching model then its easy with sklearn. for example, your input data is in the pd.DataFrame or np.ndarray. Since the training interface is the same you can easily switch models xgboost or vowpal or lightgbm by just creating a different object and passing the same procedure.

 If you are a beginner and want to know more about Data Science the do check out the Data Science course