Robert

Not work...My python version is 2.7

Cause there so many pd.read_csv..so when trackback the code ,which operaion should I change 'keep_defau.lt_na=False‘.I've changed some but the result is negative..

Emmm, I added 'keep_default_na=False' in code "off_train = pd.read_csv('data/ccf_offline_stage1_train.csv',header=None,keep_default_na=False)"& "on_train = pd.read_csv('data/ccf_online_stage1_train.csv',header=None,keep_default_na=False)" But the error still exist like below =-= : t3['user_merchant_any'] = 1 (112803, 52) (257126, 53) Traceback (most...

I changed some code then ,when running xgb.py occurs error below: "Check failed: !auc_error AUC: the dataset only contains pos or neg samples" But the label column in dataset1.csv is...

Nice work! Anyone know the enviroment requirement file of EPR?