Pytorch学习(3)LogisticRegression 回归实现

掌握要点：

１．LogisticRegression回归的基本原理，公式推导

２．利用Pytorch训练的整个流程，包括数据处理，训练

# Logistic Regression

import torch
from torch import nn
from torch.autograd import Variable
from torch import optim
import numpy as np
import matplotlib.pyplot as plt

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]), float(i[2])) for i in data_list]
    
x0 = list(filter(lambda x: x[-1] == 0.0, data))
x1 = list(filter(lambda x: x[-1] == 1.0, data))
plot_x0_0 = [i[0] for i in x0]
plot_x0_1 = [i[1] for i in x0]
plot_x1_0 = [i[0] for i in x1]
plot_x1_1 = [i[1] for i in x1]

plt.plot(plot_x0_0, plot_x0_1, 'ro', label='x_0')
plt.plot(plot_x1_0, plot_x1_1, 'bo', label='x_1')
plt.legend(loc = 'best')

class LogisticRegression(nn.Module):
    def __init__(self):
        super(LogisticRegression, self).__init__()
        self.lr = nn.Linear(2, 1)   #two inputs and onr output
        self.sm = nn.Sigmoid()
    
    def forward(self, x):
        x = self.lr(x)
        x = self.sm(x)
        return x
   
logistic_model = LogisticRegression()

# define LOss and optimizer
criterion = nn.BCELoss()   # 2 classify
optimizer = torch.optim.SGD(logistic_model.parameters(), lr = 1e-3,
                            momentum = 0.9)

# prepare train data
data_x = [i[:2] for i in data]
data_y = [i[-1] for i in data]
x_data = torch.from_numpy(np.array(data_x, dtype=np.float32))
y_data = torch.from_numpy(np.array(data_y, dtype=np.float32))

# train
num_epoch = 50000
loss_all = []
acc_all = []
for epoch in range(num_epoch):
    x = Variable(x_data)
    y = Variable(y_data)
    
    # forward
    out = logistic_model(x)
    loss = criterion(out, y)
    print_loss = loss.data.item()
    mask = out.ge(0.5).float()
    correct = (mask.squeeze(1) == y).sum()
    acc = correct.data.item() / x.size(0)
    
    # backward
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    
    loss_all.append(print_loss)
    acc_all.append(acc)
    
    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))
        
# plot the line
w0, w1 = logistic_model.lr.weight[0]
w0 = w0.data.item()
w1 = w1.data.item()
b = logistic_model.lr.bias.data[0].item()
plot_x = np.arange(30, 100, 0.1)
plot_y = (-w0 * plot_x -b) / w1
plt.plot(plot_x, plot_y)
plt.show()

plt.figure()
index = np.arange(len(loss_all))
plt.plot(index, loss_all, 'r')
plt.legend(['train_loss'])
plt.show()

plt.figure()
plt.plot(index, acc_all, 'b')
plt.legend(['accuracy'])
plt.show()

问题探究：

（１）filter( )函数

（２）lambda 表达式

（３）nn.BCELoss()

（４）提取tensor中的值采用item( )方法，书上描述的print_loss = loss.data[0]总是报错

（５）w0, w1 = logistic_model.lr.weight[0]  理解获取参数的过程