使用sklearn进行线性回归和二次回归的比较程序

待我称王封你为后i 2022-08-30 11:58 144阅读 0赞

# 使用sklearn进行线性回归和二次回归的比较程序 #

#coding=utf-8
    """ #演示内容：二次回归和线性回归的拟合效果的对比 """
    print(__doc__)
    
    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn.linear_model import LinearRegression
    from sklearn.preprocessing import PolynomialFeatures
    from matplotlib.font_manager import FontProperties
    font_set = FontProperties(fname=r"/System/Library/Fonts/STHeiti Medium.ttc", size=20) 
    
    def runplt():
        plt.figure()# 定义figure
        plt.title(u'披萨的价格和直径',fontproperties=font_set)
        plt.xlabel(u'直径（inch）',fontproperties=font_set)
        plt.ylabel(u'价格（美元）',fontproperties=font_set)
        plt.axis([0, 25, 0, 25])
        plt.grid(True)
        return plt

#演示内容：二次回归和线性回归的拟合效果的对比

#训练集和测试集数据
    X_train = [[6], [8], [10], [14], [18]]
    y_train = [[7], [9], [13], [17.5], [18]]
    X_test = [[7], [9], [11], [15]]
    y_test = [[8], [12], [15], [18]]
    
    #画出横纵坐标以及若干散点图
    plt1 = runplt()
    plt1.scatter(X_train, y_train,s=40)
    
    #给出一些点，并画出线性回归的曲线
    xx = np.linspace(0, 26, 5)
    regressor = LinearRegression()
    regressor.fit(X_train, y_train)
    yy = regressor.predict(xx.reshape(xx.shape[0], 1))
    
    plt.plot(xx, yy, label="linear equation")
    
    #多项式回归（本例中为二次回归）
    #首先生成多项式特征
    quadratic_featurizer = PolynomialFeatures(degree=2)
    X_train_quadratic = quadratic_featurizer.fit_transform(X_train)
    
    regressor_quadratic = LinearRegression()
    regressor_quadratic.fit(X_train_quadratic, y_train)
    
    #numpy.reshape（重塑）给数组一个新的形状而不改变其数据。在指定的间隔内返回均匀间隔的数字
    #给出一些点，并画出线性回归的曲线
    xx = np.linspace(0, 26, 5)
    print (xx.shape)
    print (xx.shape[0])
    xx_quadratic = quadratic_featurizer.transform(xx.reshape(xx.shape[0], 1))
    print (xx.reshape(xx.shape[0], 1).shape)
    
    plt.plot(xx, regressor_quadratic.predict(xx_quadratic), 'r-',label="quadratic equation")
    plt.legend(loc='upper left')
    plt.show()
    
    X_test_quadratic = quadratic_featurizer.transform(X_test)
    
    # 计算R^2得分 得分越高越好
    print('linear equation r-squared', regressor.score(X_test, y_test))
    print('quadratic equation r-squared', regressor_quadratic.score(X_test_quadratic, y_test))

(5,)
    5
    (5, 1)

![output\_2\_1][output_2_1]

linear equation  r-squared 0.8283656795834485
    quadratic equation r-squared 0.9785451046983036

[output_2_1]: /images/20220829/2971559a8f9b4686abd9f3a29d558d42.png