# First Silver Journey

Thanks, Kaggle and ASHRAE for hosting this competition. Maybe, my place isn’t high enough to post my view, and in later competitions I won’t post until top 20-30, but that was my second participation and first silver! So, I have an overwhelming excitement and just have to share my experience with such brilliant minds.
Key points:
•   CV and final model
•   Clearing dataset
•   Feature engineering
•   Sadly, didn’t try to postprocess
CV and final model
For feature selection and engineering in CV I only used leaked data with sites 0,1,2,15. 2 folds (split by months) and compare predictions of 2017-2018 with real readings from leak data. 
With right parameters it fast and you can actually see if feature useful or not. Yes, you can overfit to this sites, but I created only general features (at least tried), checked performance a few times on public LB and decided to use it.
For final model I excluded sites 0,1,2,15 and trained without them with same 2 fold strategy. It improved private score from 1.266 to 1.262.
I wish I had time to add CatBoost but this time I used only 3 lightgbm models with different seeds and same parameters + blend them with 3 top public kernels without leaks with little different strategy from one another to add diversity.
o
[Ashrae Energy Prediction using Stratified KFold](https://www.kaggle.com/roydatascience/ashrae-energy-prediction-using-stratified-kfold)
o
[ASHRAE 2*lightGBM without Leak Data](https://www.kaggle.com/mimoudata/ashrae-2-lightgbm-without-leak-data)
o
[Ashrae: simple data cleanup (LB 1.08 no leaks)](https://www.kaggle.com/purist1024/ashrae-simple-data-cleanup-lb-1-08-no-leaks)
Blend weights: 0.66 for my 3 models, rest for public kernels.
My best LGBM parameters:
{'num_leaves': 500,
'objective': 'regression',
 'learning_rate': 0.04,
 'boosting': 'gbdt',
 'subsample': 0.4,
 'feature_fraction': 0.7,
 'n_jobs': -1,
 'seed': 19,
 'metric': 'rmse'}
Clearing dataset
Used
[Robert Stockton](https://www.kaggle.com/purist1024/ashrae-simple-data-cleanup-lb-1-08-no-leaks)
kernel, learned a lot, thanks!
Manually cleaned some worst readings by meter type, by RMSLE error, buildings in sites 9,6,10. 
I don’t think, that I should have done some of the manual cleaning based only on my intuition instead of actual understanding what those outliers mean. Maybe, I cleaned what seemed like an outlier to me but it wasn’t and presented in test data. I think so, because I have 2 models which scores higher than my final submission and best one is single model without late manual cleaning that scores 1.25 on private.
Feature engineering
I manually checked all existed features, features from kernels, features from my ideas, aggregations, frequency encodings and found only few of them useful. I deleted most of the initial features.
I didn’t do any imputations (score decreased in CV), converted all categorical values to category type, square feet and meter readings to log1p.
I even downloaded external weather history to each site with weather conditions etc. but it didn’t improve score of my CV so I decided not to use them.
I had lot of fun struggle through and learned a lot. Hope, you are having a wonderful day and looking forward to see all of you in the next competition!