pytorch：Logistic回归

一时失言乱红尘 2022-01-31 07:47 327阅读 0赞

import matplotlib.pyplot as plt
    from torch import nn, optim
    import numpy as np
    import torch
    from torch.autograd import Variable
    # 设置字体为中文
    plt.rcParams['font.sans-serif'] = ['SimHei']
    plt.rcParams['axes.unicode_minus'] = False
    # 读取数据
    def readText():
        with open('data.txt', 'r') as f:
            data_list = f.readlines()
            data_list = [i.split('\n')[0] for i in data_list]
            data_list = [i.split(',') for i in data_list]
            data = [(float(i[0]), float(i[1]), int(i[2])) for i in data_list]
            x_data = [[float(i[0]), float(i[1])] for i in data_list]
            y_data = [float(i[2]) for i in data_list]
        return data, x_data, y_data
    # 原始数据可视化
    def visualize(data):
        x0 = list(filter(lambda x: x[-1] == 0.0, data))  # 找出类别为0的数据集
        x1 = list(filter(lambda x: x[-1] == 1.0, data))  # 找出类别为1的数据集
        plot_x0_0 = [i[0] for i in x0]  # 类别0的x
        plot_x0_1 = [i[1] for i in x0]  # 类别0的y
        plot_x1_0 = [i[0] for i in x1]  # 类别1的x
        plot_x1_1 = [i[1] for i in x1]  # 类别1的y
        plt.plot(plot_x0_0, plot_x0_1, 'ro', label='类别 0')
        plt.plot(plot_x1_0, plot_x1_1, 'bo', label='类别 1')
        plt.legend()  # 显示图例
        plt.title(label='原始数据分布情况')
        plt.show()
    def visualize_after(data):
        x0 = list(filter(lambda x: x[-1] == 0.0, data))  # 找出类别为0的数据集
        x1 = list(filter(lambda x: x[-1] == 1.0, data))  # 找出类别为1的数据集
        plot_x0_0 = [i[0] for i in x0]  # 类别0的x
        plot_x0_1 = [i[1] for i in x0]  # 类别0的y
        plot_x1_0 = [i[0] for i in x1]  # 类别1的x
        plot_x1_1 = [i[1] for i in x1]  # 类别1的y
        plt.plot(plot_x0_0, plot_x0_1, 'ro', label='类别 0')
        plt.plot(plot_x1_0, plot_x1_1, 'bo', label='类别 1')
        # 绘制分类函数
        w0, w1 = model.lr.weight[0]
        w0 = w0.data.item()
        w1 = w1.data.item()
        b = model.lr.bias.item()
        plot_x = np.arange(30, 100, 0.1)
        plot_y = (-w0 * plot_x - b) / w1
        plt.plot(plot_x, plot_y, 'yo', label='分类线')
        plt.legend()  # 显示图例
        plt.title(label='分类线可视化')
        plt.show()
    # Logistic回归模型
    class LogisticRegression(nn.Module):
        def __init__(self):
            super(LogisticRegression, self).__init__()
            self.lr = nn.Linear(2, 1)
            self.sm = nn.Sigmoid()  # 激活函数类型为sigmoid,经过激活函数，值控制在0到1之间
        def forward(self, x):
            x = self.lr(x)
            x = self.sm(x)
            return x
    # 主函数
    if __name__ == '__main__':
        data, x_data, y_data = readText()  # 读取数据
    
        x_data = torch.from_numpy(np.array(x_data))
        y_data = torch.from_numpy(np.array(y_data))
    
        visualize(data)  # 可视化（观察原始数据分布情况）
        # 获取到模型
        model = LogisticRegression()
        if torch.cuda.is_available():
            model.cuda()
        # 损失函数以及梯度下降
        criterion = nn.BCELoss()  # 二分类的损失函数
        optimizer = optim.SGD(model.parameters(), lr=1e-3, momentum=0.9)
    
        ctn = []
        lo = []
        for epoch in range(50000):
            if torch.cuda.is_available():
                x = Variable(x_data).cuda()
                y = Variable(y_data).cuda()
            else:
                x = Variable(x_data)
                y = Variable(y_data)
    
            x = torch.tensor(x, dtype=torch.float32)
            out = model(x)
            y = torch.tensor(y, dtype=torch.float32)
            loss = criterion(out, y)
            print_loss = loss.data.item()
            mask = out.ge(0.5).float()  # 大于0.5则输出为1
            correct = (mask == y).sum()  # 统计输出为1的个数
            acc = correct.item() / x.size(0)
    
            optimizer.zero_grad()  # 梯度清零
            loss.backward()  # 反向传播
            optimizer.step()  # 更新梯度
    
            ctn.append(epoch+1)
            lo.append(print_loss)
    
            if (epoch+1) % 1000 == 0:
                print('*'*10)
                print('epoch {}'.format(epoch+1))
                print('loss is {:.4f}'.format(print_loss))
                print('acc is {:.4f}'.format(acc))
        visualize_after(data)
        # 绘制训练次数与损失值之间的关系
        plt.plot(ctn,lo)
        plt.title(label='训练次数与损失值关系')
        plt.xlabel('训练次数')
        plt.ylabel('损失值')
        plt.show()

实验数据：

34.62365962451697,78.0246928153624,0
    30.2867107622687,43.89499752400101,0
    35.84740876993872,72.90219802708364,0
    60.18259938620976,86.3855209546826,1
    79.0327360507101,75.3443764369103,1
    45.08327747668339,56.3163717815305,0
    61.10666453684766,96.51142588489624,1
    75.02474556738889,46.55401354116538,1
    76.09878670226257,87.42056971926803,1
    84.43281996120035,43.53339331072109,1
    95.86155507093572,38.22527805795094,0
    75.01365838958247,30.60326323428011,0
    82.30705337399482,76.48196330235604,1
    69.36458875970939,97.71869196188608,1
    39.53833914367223,76.03681085115882,0
    53.9710521485623,89.20735013750265,1
    69.07014406283025,52.74046973016765,1
    67.9468554771161746,67.857410673128,0

实验结果：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3Nvbmd4aWFvbGluZ2Jhb2Jhbw_size_16_color_FFFFFF_t_70][]![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3Nvbmd4aWFvbGluZ2Jhb2Jhbw_size_16_color_FFFFFF_t_70 1][]![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3Nvbmd4aWFvbGluZ2Jhb2Jhbw_size_16_color_FFFFFF_t_70 2][]

注意事项：

（1）数据太少，没有找到完整数据。

（2）注意类型转换，float64转为float32，对应代码为：

x = torch.tensor(x, dtype=torch.float32)
     out = model(x)
     y = torch.tensor(y, dtype=torch.float32)

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3Nvbmd4aWFvbGluZ2Jhb2Jhbw_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20190516081656860.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3Nvbmd4aWFvbGluZ2Jhb2Jhbw==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3Nvbmd4aWFvbGluZ2Jhb2Jhbw_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20190516081707352.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3Nvbmd4aWFvbGluZ2Jhb2Jhbw==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3Nvbmd4aWFvbGluZ2Jhb2Jhbw_size_16_color_FFFFFF_t_70 2]: /images/20220131/d9c8eb5df28a4299b614cca00fb97e2f.png