六、回归与聚类算法 - 岭回归

目录

1、带有L2正则化的线性回归 - 岭回归

1.1 API

2、正则化程度的变化对结果的影响

3、波士顿房价预测

1. 线性回归
2. 欠拟合与过拟合
3. 线性回归的改进 - 岭回归
4. 分类算法：逻辑回归
5. 模型保存与加载
6. 无监督学习：K-means算法

1、带有L2正则化的线性回归 - 岭回归

1.1 API

2、正则化程度的变化对结果的影响

• 正则化力度越大，权重系数越小
• 正则化力度越小，权重系数越大

3、波士顿房价预测

from sklearn.datasets import load_boston
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression, SGDRegressor, Ridge


def linear1():
    # 正规方程的优化方法对波士顿房价进行预测
    # 1、获取数据
    boston = load_boston()
    # 2、划分数据集
    x_train,x_test,y_train,y_test=train_test_split(boston.data,boston.target,random_state=22)
    # 3、标准化
    transfer = StandardScaler()
    x_train=transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)
    # 4、预估器
    estimator = LinearRegression()
    estimator.fit(x_train,y_train)
    # 5、得出模型
    print("正规方程-权重系数为：\n",estimator.coef_)
    print("正规方程-偏置为：\n",estimator.intercept_)
    # 6、模型评估
    y_predict = estimator.predict(x_test)
    print("正规方程-预测房价：\n",y_predict)
    errror = mean_squared_error(y_test,y_predict)
    print("正规方程-均方差误差：\n",errror)
    return None


def linear2():
    # 梯度下降的优化方法对波士顿房价进行预测
    # 1、获取数据
    boston = load_boston()
    # 2、划分数据集
    x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
    # 3、标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)
    # 4、预估器
    estimator = SGDRegressor()
    estimator.fit(x_train, y_train)
    # 5、得出模型
    print("梯度下降-权重系数为：\n", estimator.coef_)
    print("梯度下降-偏置为：\n", estimator.intercept_)
    # 6、模型评估
    y_predict = estimator.predict(x_test)
    print("梯度下降-预测房价：\n", y_predict)
    errror = mean_squared_error(y_test, y_predict)
    print("梯度下降-均方差误差：\n", errror)
    return None


def linear3():
    # 岭回归对波士顿房价进行预测
    # 1、获取数据
    boston = load_boston()
    # 2、划分数据集
    x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
    # 3、标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)
    # 4、预估器
    estimator = Ridge()
    estimator.fit(x_train, y_train)
    # 5、得出模型
    print("岭回归-权重系数为：\n", estimator.coef_)
    print("岭回归-偏置为：\n", estimator.intercept_)
    # 6、模型评估
    y_predict = estimator.predict(x_test)
    print("岭回归-预测房价：\n", y_predict)
    errror = mean_squared_error(y_test, y_predict)
    print("岭回归-均方差误差：\n", errror)
    return None

if __name__ == "__main__":
    # 代码1 ：正规方程的优化方法对波士顿房价进行预测
    linear1()
    # 代码2：梯度下降的优化方法对波士顿房价进行预测
    linear2()
    # 代码3：岭回归对波士顿房价进行预测
    linear3()