# sharing code - UGBC

Thanks to Andrey Ustyuzhanin, Alex Rogozhnikov et al., the authors/maintainers of hep_ml, for their effort.
I have spent two evenings installing hep_ml, and three evenings running it, but I have obtained
0.991099
using just one model -
[UGradientBoostingClassifier](http://grzegorz.sionkowski.pl/zip/justUGBC.zip)
<- zip file of my solution.
Because I know neither R nor Python, the solution is written partly in R, partly in Python 2.7.
New things regarding scripts known before the end of the competition:
-- new feature (Python file)
df['NEW_FD_LT']=df['FlightDistance']/df['LifeTime'] 
of the dimension of "velocity" ;)
-- removing some specific rows from evaluation file enables to obtain 
better evaluation close to that on LB or that (not allowed) min_ANNmuon>0.4 (R file).
No mass "reconstruction".