回归问题

叁歲伎倆 2024-04-17 19:52 26阅读 0赞

# 1.内容 #

鸢尾花分类识别

# 2.代码 #

Adveritising.py

#!/usr/bin/python
    # -*- coding:utf-8 -*-
    
    import csv
    import numpy as np
    import matplotlib.pyplot as plt
    import pandas as pd
    from sklearn.model_selection import train_test_split
    from sklearn.linear_model import LinearRegression
    
    
    if __name__ == "__main__":
        path = '8.Advertising.csv'
        # # 读写方式1：手写读取数据 - 请自行分析，在8.2.Iris代码中给出类似的例子
        # f = file(path)
        # x = []
        # y = []
        # for i, d in enumerate(f):
        #     if i == 0:
        #         continue
        #     d = d.strip() #将无关字符去掉
        #     if not d:
        #         continue
        #     d = map(float, d.split(','))
        #     x.append(d[1:-1])
        #     y.append(d[-1])
        # print x
        # print y
        # x = np.array(x)
        # y = np.array(y)
    
        # # 2：Python自带库
        # f = file(path, 'rb')
        # print f
        # d = csv.reader(f)
        # for line in d:
        #     print line
        # f.close()
    
        # # 3：numpy读入
        # p = np.loadtxt(path, delimiter=',', skiprows=1)
        # print p
    
        # 4：pandas读入
        data = pd.read_csv(path)    # TV、Radio、Newspaper、Sales
        x = data[['TV', 'Radio', 'Newspaper']]
        # x = data[['TV', 'Radio']]
        y = data['Sales']
        print x
        print y
    
        # # 绘制1
        plt.plot(data['TV'], y, 'ro', label='TV')
        plt.plot(data['Radio'], y, 'g^', label='Radio')
        plt.plot(data['Newspaper'], y, 'mv', label='Newspaer')
        plt.legend(loc='lower right')
        plt.grid()
        plt.show()
        # #
        # # 绘制2
        # plt.figure(figsize=(9,12))
        # plt.subplot(311)
        # plt.plot(data['TV'], y, 'ro')
        # plt.title('TV')
        # plt.grid()
        # plt.subplot(312)
        # plt.plot(data['Radio'], y, 'g^')
        # plt.title('Radio')
        # plt.grid()
        # plt.subplot(313)
        # plt.plot(data['Newspaper'], y, 'b*')
        # plt.title('Newspaper')
        # plt.grid()
        # plt.tight_layout()
        # plt.show()
    
        x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1)
        # print x_train, y_train
        linreg = LinearRegression()
        model = linreg.fit(x_train, y_train)
        print model
        print linreg.coef_
        print linreg.intercept_
    
        y_hat = linreg.predict(np.array(x_test))
        mse = np.average((y_hat - np.array(y_test)) ** 2)  # Mean Squared Error
        rmse = np.sqrt(mse)  # Root Mean Squared Error
        print mse, rmse
    
        t = np.arange(len(x_test))
        plt.plot(t, y_test, 'r-', linewidth=2, label='Test')
        plt.plot(t, y_hat, 'g-', linewidth=2, label='Predict')
        plt.legend(loc='upper right')
        plt.grid()
        plt.show()

LinearRegression\_CV.py

#!/usr/bin/python
    # -*- coding:utf-8 -*-
    
    import numpy as np
    import matplotlib.pyplot as plt
    import pandas as pd
    from sklearn.model_selection import train_test_split
    from sklearn.linear_model import Lasso, Ridge
    from sklearn.model_selection import GridSearchCV
    
    
    if __name__ == "__main__":
        # pandas读入
        data = pd.read_csv('8.Advertising.csv')    # TV、Radio、Newspaper、Sales
        x = data[['TV', 'Radio', 'Newspaper']]
        # x = data[['TV', 'Radio']]
        y = data['Sales']
        print x
        print y
    
        x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1) #可以指定训练集的比例，默认0.75
        # print x_train, y_train
        model = Lasso() # Lasso回归
        # model = Ridge() #岭回归
    
        alpha_can = np.logspace(-3, 2, 10)
        lasso_model = GridSearchCV(model, param_grid={
        'alpha': alpha_can}, cv=5) #交叉验证
        lasso_model.fit(x, y)
        print '验证参数：\n', lasso_model.best_params_
    
        y_hat = lasso_model.predict(np.array(x_test))
        mse = np.average((y_hat - np.array(y_test)) ** 2)  # Mean Squared Error
        rmse = np.sqrt(mse)  # Root Mean Squared Error
        print mse, rmse
    
        t = np.arange(len(x_test))
        plt.plot(t, y_test, 'r-', linewidth=2, label='Test')
        plt.plot(t, y_hat, 'g-', linewidth=2, label='Predict')
        plt.legend(loc='upper right')
        plt.grid()
        plt.show()

Iris\_LR.py

#!/usr/bin/python
    # -*- coding:utf-8 -*-
    
    import numpy as np
    from sklearn.linear_model import LogisticRegression
    import matplotlib.pyplot as plt
    import matplotlib as mpl
    from sklearn import preprocessing
    import pandas as pd
    from sklearn.preprocessing import StandardScaler
    from sklearn.pipeline import Pipeline
    
    
    def iris_type(s):
        it = {
        'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
        return it[s]
    
    
    if __name__ == "__main__":
        path = u'8.iris.data'  # 数据文件路径
    
        # # # 方法1：手写读取数据
        # # f = file(path)
        # # x = []
        # # y = []
        # # for d in f:
        # #     d = d.strip()
        # #     if d:
        # #         d = d.split(',')
        # #         y.append(d[-1])
        # #         x.append(map(float, d[:-1]))
        # # print '原始数据X：\n', x
        # # print '原始数据Y：\n', y
        # # x = np.array(x)
        # # print 'Numpy格式X：\n', x
        # # y = np.array(y)
        # # print 'Numpy格式Y - 1:\n', y
        # # y[y == 'Iris-setosa'] = 0
        # # y[y == 'Iris-versicolor'] = 1
        # # y[y == 'Iris-virginica'] = 2
        # # print 'Numpy格式Y - 2:\n', y
        # # y = y.astype(dtype=np.int) #安全转换
        # # print 'Numpy格式Y - 3:\n', y
        #
        # # 2：使用sklearn的数据预处理
        # df = pd.read_csv(path, header=0)
        # x = df.values[:, :-1]
        # y = df.values[:, -1]
        # print 'x = \n', x
        # print 'y = \n', y
        # le = preprocessing.LabelEncoder() #做编码
        # le.fit(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'])
        # print le.classes_
        # y = le.transform(y)
        # print 'Last Version, y = \n', y
        #
        # # 3：路径，浮点型数据，逗号分隔，第4列使用函数iris_type单独处理
        data = np.loadtxt(path, dtype=float, delimiter=',', converters={
        4: iris_type})
        print data
        # 将数据的0到3列组成x，第4列得到y
        x, y = np.split(data, (4,), axis=1)
    
        # 为了可视化，仅使用前两列特征
        x = x[:, :2]
        #
        print x
        print y
        #
        # x = StandardScaler().fit_transform(x)
        # lr = LogisticRegression()   # Logistic回归模型
        #     lr.fit(x, y.ravel())        # 根据数据[x,y]，计算回归参数
        #
        # 等价形式，类似生产线
        lr = Pipeline([('sc', StandardScaler()),
                            ('clf', LogisticRegression()) ])
        lr.fit(x, y.ravel()) #学习，ravel行列转换
    
        # 画图
        N, M = 500, 500     # 横纵各采样多少个值
        x1_min, x1_max = x[:, 0].min(), x[:, 0].max()   # 第0列的范围
        x2_min, x2_max = x[:, 1].min(), x[:, 1].max()   # 第1列的范围
        t1 = np.linspace(x1_min, x1_max, N)
        t2 = np.linspace(x2_min, x2_max, M)
        x1, x2 = np.meshgrid(t1, t2)                    # 生成网格采样点
        x_test = np.stack((x1.flat, x2.flat), axis=1)   # 测试点
    
        # 无意义，只是为了凑另外两个维度
        # x3 = np.ones(x1.size) * np.average(x[:, 2])
        # x4 = np.ones(x1.size) * np.average(x[:, 3])
        # x_test = np.stack((x1.flat, x2.flat, x3, x4), axis=1)  # 测试点
    
        cm_light = mpl.colors.ListedColormap(['#77E0A0', '#FF8080', '#A0A0FF'])
        cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
        y_hat = lr.predict(x_test)                  # 预测值
        y_hat = y_hat.reshape(x1.shape)                 # 使之与输入的形状相同
        plt.pcolormesh(x1, x2, y_hat, cmap=cm_light)     # 预测值的显示
        plt.scatter(x[:, 0], x[:, 1], c=y, edgecolors='k', s=50, cmap=cm_dark)    # 样本的显示
        plt.xlabel('petal length')
        plt.ylabel('petal width')
        plt.xlim(x1_min, x1_max)
        plt.ylim(x2_min, x2_max)
        plt.grid()
        plt.savefig('2.png')
        plt.show()
    
        # 训练集上的预测结果
        y_hat = lr.predict(x)
        y = y.reshape(-1)
        result = y_hat == y
        print y_hat
        print result
        acc = np.mean(result)
        print '准确度: %.2f%%' % (100 * acc)

overfit.py

#!/usr/bin/python
    # -*- coding:utf-8 -*-
    
    import numpy as np
    from sklearn.linear_model import LinearRegression, RidgeCV
    from sklearn.preprocessing import PolynomialFeatures
    import matplotlib.pyplot as plt
    from sklearn.pipeline import Pipeline
    import matplotlib as mpl
    
    
    if __name__ == "__main__":
        np.random.seed(0)
        N = 9
        x = np.linspace(0, 6, N) + np.random.randn(N)
        x = np.sort(x)
        y = x**2 - 4*x - 3 + np.random.randn(N)
        x.shape = -1, 1
        y.shape = -1, 1
    
        model_1 = Pipeline([
            ('poly', PolynomialFeatures()), #给定一个度
            ('linear', LinearRegression(fit_intercept=False))])
        model_2 = Pipeline([
            ('poly', PolynomialFeatures()),
            ('linear', RidgeCV(alphas=np.logspace(-3, 2, 100), fit_intercept=False))])
        models = model_1, model_2
        mpl.rcParams['font.sans-serif'] = [u'simHei']
        mpl.rcParams['axes.unicode_minus'] = False
        np.set_printoptions(suppress=True)
    
        plt.figure(figsize=(9, 11), facecolor='w')
        d_pool = np.arange(1, N, 1)  # 阶
        m = d_pool.size
        clrs = []  # 颜色
        for c in np.linspace(16711680, 255, m):
            clrs.append('#%06x' % c)
        line_width = np.linspace(5, 2, m)
        titles = u'线性回归', u'Ridge回归'
        for t in range(2):
            model = models[t]
            plt.subplot(2, 1, t+1)
            plt.plot(x, y, 'ro', ms=10, zorder=N)
            for i, d in enumerate(d_pool):
                model.set_params(poly__degree=d)
                model.fit(x, y)
                lin = model.get_params('linear')['linear']
                if t == 0:
                    print u'%d阶，系数为：' % d, lin.coef_.ravel()
                else:
                    print u'%d阶，alpha=%.6f，系数为：' % (d, lin.alpha_), lin.coef_.ravel()
                x_hat = np.linspace(x.min(), x.max(), num=100)
                x_hat.shape = -1, 1
                y_hat = model.predict(x_hat)
                s = model.score(x, y)
                print s, '\n'
                zorder = N - 1 if (d == 2) else 0
                plt.plot(x_hat, y_hat, color=clrs[i], lw=line_width[i], label=(u'%d阶，score=%.3f' % (d, s)), zorder=zorder)
            plt.legend(loc='upper left')
            plt.grid(True)
            plt.title(titles[t], fontsize=16)
            plt.xlabel('X', fontsize=14)
            plt.ylabel('Y', fontsize=14)
        plt.tight_layout(1, rect=(0, 0, 1, 0.95))
        plt.suptitle(u'多项式曲线拟合', fontsize=18)
        plt.show()