# 31st place, Some of Feature Engineering

here are some feature engineering
[https://www.kaggle.com/mks2192/feature-engineering/notebook](https://www.kaggle.com/mks2192/feature-engineering/notebook)
it takes more than kernals time so i had to run it on my PC.
This is mainly FE for cityID, subsectorID, merchantID, merchant_categoryID 
during FE i did not used target information the way we do in mean encoding. So features are free from fear of overfitting.
features coming out of this are here
[https://www.kaggle.com/mks2192/elo-features-data-7-feb](https://www.kaggle.com/mks2192/elo-features-data-7-feb)
Thanks,
PS: some of the codes are adopted from others especially
[@mitsuru](/mitsuru)
_fujiwara