test_submission.py 文件源码

def cross_validate(train):
    #separate training and validation set
    X_train,X_valid= split_train_validation(train)
    scores = []; preds = []
    for i in xrange(len(X_train)):
        #convert X_train, Y_train etc... to xgboost matrix
        dtrain = xgb.DMatrix(X_train[i][['phone_brand','device_model','timestamp']], label = X_train[i]['group'],missing=np.nan) 
        dvalid = xgb.DMatrix(X_valid[i][['phone_brand','device_model','timestamp']], label = X_valid[i]['group'],missing=np.nan)

        #predict with xgboost
        parameters = {'max_depth':4,'eta':0.1,'silent':1, 'subsample':0.8,'colsample_bytree':0.8,
                'objective':'multi:softprob','booster':'gbtree','early_stopping_rounds':50,
                'num_class':12,'num_boost_round':1000,'eval_metric':'mlogloss'}
        plst = parameters.items()
        bst = xgb.train(plst, dtrain)
        pred = bst.predict(dvalid)

        scores.append(log_loss(X_valid[i]['group'].tolist(),pred))
        pred = pd.DataFrame(pred, index = X_valid[i].index, columns=target_encoder.classes_)
        preds.append(pred)
    return scores, preds