rice_run.py 文件源码

def xgboost(train_sample, validation_sample, features, model_param):
    def evalmape(preds, dtrain):
        labels = dtrain.get_label()
        preds = np.power(log_base, preds) - 1
        # return a pair metric_name, result
        # since preds are margin(before logistic transformation, cutoff at 0)
        return 'mape', np.abs((labels - preds) / labels).sum() / len(labels)

    param = {'max_depth': model_param['depth'], 'eta': model_param['lr'], 'silent': 1, 'objective': 'reg:linear', 'booster': 'gbtree',
             'subsample': model_param['sample'],
             'seed':model_param['seed'],
             'colsample_bytree':1, 'min_child_weight':1, 'gamma':0}
    param['eval_metric'] = 'mae'
    num_round = model_param['tree']
    log_base = np.e
    plst = param.items()
    dtrain = xgb.DMatrix(train_sample[features], np.log1p(train_sample['volume'])/np.log(log_base))
    dtest = xgb.DMatrix(validation_sample[features], validation_sample['volume'])
    watchlist = [(dtest, 'eval'), (dtrain, 'train')]
    bst = xgb.train(plst, dtrain, num_round, watchlist, feval=evalmape)
    xgboost_prob = np.power(log_base, bst.predict(dtest)) - 1
    # MAPE
    print_mape(validation_sample['volume'], xgboost_prob, 'XGBOOST')
    return xgboost_prob