train.py 文件源码

def xgboost_test_offline():
    bst = xgboost_train(True)
    P = get_sku_ids_in_P()
    labels = get_labels('2016-04-11','2016-04-16')
    sub_user_index, sub_trainning_data = make_test_set('2016-04-11', '2016-04-16', )
    sub_trainning_data = xgb.DMatrix(sub_trainning_data.values)
    y = bst.predict(sub_trainning_data)
    sub_user_index['label'] = y
    pred = sub_user_index[sub_user_index['label'] >= 0.03]
    # pred = sub_user_index
    pred = pred[['user_id', 'sku_id']]
    pred = pred.groupby('user_id').first().reset_index()
    pred['user_id'] = pred['user_id'].astype(int)
    # pred = pred[pred['sku_id'].isin(P)]
    labels = labels[labels['label']==1]
    labels['user_id'] = labels['user_id'].astype(int)
    labels = labels[['user_id','sku_id']]
    labels = labels[labels['sku_id'].isin(P)]
    eval.eval(pred,labels)

    pass