__init__.py 文件源码

def regression_with_xgboost(x_train, y_train, X_test, Y_test, features=None, use_cv=True, use_sklean=False, xgb_params=None):
    train_data = xgb.DMatrix(x_train, label=y_train, missing=float('nan'))
    test_data = xgb.DMatrix(X_test, Y_test, missing=float('nan'))
    evallist  = [(test_data,'eval'), (train_data,'train')]

    #if xgb_params == None:
    #    xgb_params = get_default_xgboost_params()

    if not use_cv:
        num_rounds = 10
    else:
        cvresult = xgb.cv(xgb_params, train_data, num_boost_round=100, nfold=5,
            metrics={'rmse'}, show_progress=True)
        print cvresult
        num_rounds = len(cvresult)
    gbdt = None
    if(use_sklean):
        #gbdt = xgboost.XGBRegressor(max_depth=3, learning_rate=0.1, n_estimators=100, silent=True, objective='reg:linear', nthread=-1, gamma=0, min_child_weight=1, max_delta_step=0, subsample=1, colsample_bytree=1, colsample_bylevel=1, reg_alpha=0, reg_lambda=1, scale_pos_weight=1, base_score=0.5, seed=0, missing=None)
        xgb_params['n_estimators'] = num_rounds
        gbdt = xgboost.XGBRegressor(xgb_params)

        gbdt.fit(x_train, y_train)
        y_pred = gbdt.predict(X_test)

        return gbdt, y_pred
    else:
        #gbdt = xgb.train( xgb_params, train_data, num_rounds, evallist, verbose_eval = True, early_stopping_rounds=5)
        gbdt = xgb.train( xgb_params, train_data, num_rounds, evallist, verbose_eval = True)

        ceate_feature_map_for_feature_importance(features)
        show_feature_importance(gbdt, feature_names=features)

        y_pred = gbdt.predict(xgb.DMatrix(X_test, missing=float("nan")))
        return XGBoostModel(gbdt), y_pred