机器学习_线性回归问题

线性回归

案例分析

正规方程、梯度下降、岭回归

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


def lin():  
    # 加载数据
    lb = load_boston()
    # 分割数据
    x_train, x_test, y_train, y_test = train_test_split(lb.data, lb.target, test_size=0.25)
    # 标准化处理,实例化两个标准化API
    std_x = StandardScaler()
    x_train = std_x.fit_transform(x_train)
    x_test = std_x.transform(x_test)
    std_y = StandardScaler()
    y_train = std_y.fit_transform(y_train.reshape(-1, 1))
    y_test = std_y.transform(y_test.reshape(-1, 1))
    # 正规方程求解
    lr = LinearRegression()
    lr.fit(x_train, y_train)
    print(lr.coef_)  # 这个显示回归系数
    y_lr_predict = std_y.inverse_transform(lr.predict(x_test))
    print('预测的房价是', y_lr_predict)
    print('正规方程均方误差：', mean_squared_error(std_y.inverse_transform(y_test), y_lr_predict))

    # 梯度下降预测(这里数据太少，效果貌似很不好,建议大于10万样本)
    sgd = SGDRegressor()
    sgd.fit(x_train, y_train)
    print(sgd.coef_)
    y_sgd_predict = std_y.inverse_transform(sgd.predict(x_test))
    print('预测的房价是', y_sgd_predict)
    print('梯度下降均方误差：', mean_squared_error(std_y.inverse_transform(y_test), y_sgd_predict))

if __name__ == '__main__':
    lin()

使用条件

过拟合和欠拟合

欠拟合

一般为模型过于简单

过拟合 overfitting

原始特征过多，存在一些嘈杂特征， 模型过于复杂是因为模型尝试去兼顾各个测试数据点

过拟合的解决办法

正则化，岭回归

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


def lin():  
    # 岭回归
    rd = Ridge(alpha=1)
    rd.fit(x_train, y_train)
    print(rd.coef_)
    y_rd_predict = std_y.inverse_transform(rd.predict(x_test))
    print('预测的房价是', y_rd_predict)
    print('梯度下降均方误差：', mean_squared_error(std_y.inverse_transform(y_test), y_rd_predict))
    return None