Question

在XGBoost回归中预测价格，如何获取系数，模型的截距？像我们在Statsmodel中获得线性回归一样，如何获取模型摘要？参见下面的代码

import { Popover } from '@material-ui/core/'
import classnames from 'classnames'
import React from 'react'
import { withStyles } from '../styles/'
import { popoverStyles } from './styles'


const MYPopover = withStyles(popoverStyles)(class extends React.Component {

    static displayName = 'MYPopover'

    static propTypes = Popover.propTypes

    render() {

        const { props } = this

        return (
            <Popover {...{
                ...props,
                className: classnames('my-popover', props.className)
            }} />
        )
    }
})

export default MYPopover

from xgboost import XGBRegressor

# fit model no training data
model = XGBRegressor()
model.fit(X_train, y_train)

# make predictions for test data
y_pred = model.predict(X_test)

这是我建立模型并尝试获得这样的系数的方法：

print("R^2: {}".format(model.score(X_test, y_test)))
rmse = np.sqrt(mean_squared_error(y_test, y_pred))
print("Root Mean Squared Error: {}".format(rmse))

#print the intercept
print(model.intercept_)

AttributeError: Intercept (bias) is not defined for Booster type gbtree

print(model.coef_)

有人可以帮我解决这个问题吗？谢谢。

Answer 1

仅当选择线性模型作为基础学习器（booster = gblinear）时才定义系数。没有为其他基础学习者类型（例如树学习者（booster = gbtree））定义此定义。默认值为booster = gbtree

如何在XGBoost回归器中找到模型系数？

1 个答案: