第四讲，pytorch实现线性回归和逻辑回归

一，线性回归

import torch
import matplotlib.pyplot as plt
torch.manual_seed(10)

lr = 0.1  # 学习率

# 创建训练数据
x = torch.rand(20, 1) * 10  # x data (tensor), shape=(20, 1)
y = 2*x + (5 + torch.randn(20, 1))  # y data (tensor), shape=(20, 1)

# 构建线性回归参数
w = torch.randn((1), requires_grad=True)
b = torch.zeros((1), requires_grad=True)

for iteration in range(1000):

    # 前向传播
    wx = torch.mul(w, x)
    y_pred = torch.add(wx, b)

    # 计算 MSE loss
    loss = (0.5 * (y - y_pred) ** 2).mean()#0.5是为了在求导过程中消掉系数2

    # 反向传播
    loss.backward()#自动反向传播

    # 更新参数
    b.data.sub_(lr * b.grad)
    w.data.sub_(lr * w.grad)
    print(loss)
    print(loss.data.numpy())

    # 绘图
    if iteration % 20 == 0:

        plt.scatter(x.data.numpy(), y.data.numpy())
        plt.plot(x.data.numpy(), y_pred.data.numpy(), 'r-', lw=5)
        plt.text(2, 20, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color':  'red'})
        plt.xlim(1.5, 10)
        plt.ylim(8, 28)
        plt.title("Iteration: {}\nw: {} b: {}".format(iteration, w.data.numpy(), b.data.numpy()))
        plt.pause(0.5)

        if loss.data.numpy() < 1:
            break

二，逻辑回归

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import numpy as np
torch.manual_seed(10)#设置随机种子


# ============================ step 1/5 生成数据 ============================
sample_nums = 100
mean_value = 1.7
bias = 1
n_data = torch.ones(sample_nums, 2)#生成100行2列的1

#生成共200个点
x0 = torch.normal(mean_value * n_data, 1) + bias      # 类别0 数据 shape=(100, 2.数据增强方法)
y0 = torch.zeros(sample_nums)                         # 类别0 标签 shape=(100, 1)
x1 = torch.normal(-mean_value * n_data, 1) + bias     # 类别1 数据 shape=(100, 2.数据增强方法)
y1 = torch.ones(sample_nums)                          # 类别1 标签 shape=(100, 1)
train_x = torch.cat((x0, x1), 0)
train_y = torch.cat((y0, y1), 0)


# ============================ step 2.数据增强方法/5 选择模型 ============================
class LR(nn.Module):
    def __init__(self):
        super(LR, self).__init__()
        self.features = nn.Linear(2, 1)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):#构建前向传播过程
        x = self.features(x)
        x = self.sigmoid(x)
        return x


lr_net = LR()   # 实例化逻辑回归模型


# ============================ step 3/5 选择损失函数 ============================
loss_fn = nn.BCELoss()#二分类交叉熵损失

# ============================ step 4/5 选择优化器   ============================
lr = 0.01  # 学习率
#随机梯度下降法
optimizer = torch.optim.SGD(lr_net.parameters(), lr=lr, momentum=0.9)

# ============================ step 5/5 模型训练 ============================
for iteration in range(1000):

    # 前向传播
    y_pred = lr_net(train_x)

    # 计算 loss
    loss = loss_fn(y_pred.squeeze(), train_y)

    # 反向传播
    loss.backward()

    # 更新参数
    optimizer.step()

    # 绘图
    if iteration % 20 == 0:

        mask = y_pred.ge(0.5).float().squeeze()  # 以0.5为阈值进行分类
        correct = (mask == train_y).sum()  # 计算正确预测的样本个数
        acc = correct.item() / train_y.size(0)  # 计算分类准确率

        plt.scatter(x0.data.numpy()[:, 0], x0.data.numpy()[:, 1], c='r', label='class 0')
        plt.scatter(x1.data.numpy()[:, 0], x1.data.numpy()[:, 1], c='b', label='class 1')

        w0, w1 = lr_net.features.weight[0]
        w0, w1 = float(w0.item()), float(w1.item())
        plot_b = float(lr_net.features.bias[0].item())
        plot_x = np.arange(-6, 6, 0.1)
        plot_y = (-w0 * plot_x - plot_b) / w1

        plt.xlim(-5, 7)
        plt.ylim(-7, 7)
        plt.plot(plot_x, plot_y)

        plt.text(-5, 5, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color': 'red'})
        plt.title("Iteration: {}\nw0:{:.2f} w1:{:.2f} b: {:.2f} accuracy:{:.2%}".format(iteration, w0, w1, plot_b, acc))
        plt.legend()

        plt.show()
        plt.pause(0.5)

        if acc > 0.999:
            break

三，去中心化的逻辑回归，收敛速度慢了，体现中心化的重要性

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import numpy as np
torch.manual_seed(10)

lr = 0.01  # 学习率

# 生成虚拟数据
sample_nums = 100
mean_value = 1.7
bias = 5         # 5
n_data = torch.ones(sample_nums, 2)
x0 = torch.normal(mean_value * n_data, 1) + bias      # 类别0 数据 shape=(100, 2.数据增强方法)
y0 = torch.zeros(sample_nums)                         # 类别0 标签 shape=(100, 1)
x1 = torch.normal(-mean_value * n_data, 1) + bias     # 类别1 数据 shape=(100, 2.数据增强方法)
y1 = torch.ones(sample_nums)                          # 类别1 标签 shape=(100, 1)
train_x = torch.cat((x0, x1), 0)
train_y = torch.cat((y0, y1), 0)


# 定义模型
class LR(nn.Module):
    def __init__(self):
        super(LR, self).__init__()
        self.features = nn.Linear(2, 1)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        x = self.features(x)
        x = self.sigmoid(x)
        return x


lr_net = LR()

# 定义损失函数与优化器
loss_fn = nn.BCELoss()
optimizer = torch.optim.SGD(lr_net.parameters(), lr=0.01, momentum=0.9)

for iteration in range(1000):

    # 前向传播
    y_pred = lr_net(train_x)

    # 计算 MSE loss
    loss = loss_fn(y_pred, train_y)

    # 反向传播
    loss.backward()

    # 更新参数
    optimizer.step()

    # 绘图
    if iteration % 20 == 0:

        mask = y_pred.ge(0.5).float().squeeze()  # 以0.5为阈值进行分类
        correct = (mask == train_y).sum()  # 计算正确预测的样本个数
        acc = correct.item() / train_y.size(0)  # 计算精度

        plt.scatter(x0.data.numpy()[:, 0], x0.data.numpy()[:, 1], c='r', label='class 0')
        plt.scatter(x1.data.numpy()[:, 0], x1.data.numpy()[:, 1], c='b', label='class 1')

        w0, w1 = lr_net.features.weight[0]
        w0, w1 = float(w0.item()), float(w1.item())
        plot_b = float(lr_net.features.bias[0].item())
        plot_x = np.arange(-6, 6, 0.1)
        plot_y = (-w0 * plot_x - plot_b) / w1

        plt.xlim(-5, 10)
        plt.ylim(-7, 10)
        plt.plot(plot_x, plot_y)

        plt.text(-5, 5, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color': 'red'})
        plt.title("Iteration: {}\nw0:{:.2f} w1:{:.2f} b: {:.2f} accuracy:{:.2%}".format(iteration, w0, w1, plot_b, acc))
        plt.legend()

        plt.show()
        plt.pause(0.5)

        if acc > 0.99:
            break