pytorch入门：读取CSV文件并自己搭建一个回归神经网络

向右看齐 2023-02-14 10:29 6阅读 0赞

## 原始数据 ##

In this part of this exercise, you will implement linear regression with one  
variable to predict profits for a food truck. Suppose you are the CEO of a  
restaurant franchise and are considering different cities for opening a new  
outlet. The chain already has trucks in various cities and you have data for  
profits and populations from the cities.  
You would like to use this data to help you select which city to expand  
to next.  
The file ex1data1.txt contains the dataset for our linear regression prob-  
lem. The first column is the population of a city and the second column is  
the profit of a food truck in that city. A negative value for profit indicates a  
loss.  
截图看一下：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2t1bkFVR1VTVA_size_16_color_FFFFFF_t_70]

## 数据类型转换 ##

torch中默认的数据类型都是tensor，但读取CSV文件的时候读取的格式为dataframe（单列为series）  
抽取第一列作为x（population），第二列作为y（profit），转化顺序为  
**series -> np.array -> list ->tensor**  
转化用到的函数：  
series转np.array

np.array(x)

np.array转list

x.tolist()

list转tensor

torch.FloatTensor(x)

注意这个时候如果输出x.shape的话，结果为torch.Size(\[97\])  
我们要把它转化为97x1的数据：

x = torch.unsqueeze(torch.FloatTensor(x), dim=1)

完整代码如下：

import pandas as pd
    import torch
    import torch.nn.functional as F
    import numpy as np
    
    df = pd.read_csv(r'D:\Wu-Enda\code\ex1-linear regression\ex1data1.txt', names=['population', 'profit'])  # 读取数据并赋予列名
    print(type(df))  # <class 'pandas.core.frame.DataFrame'>
    
    x = df['population']
    print(type(x))  # <class 'pandas.core.series.Series'>
    x = np.array(x)
    print(type(x))  # <class 'numpy.ndarray'>
    x = x.tolist()
    print(type(x))  # <class 'list'>
    x = torch.unsqueeze(torch.FloatTensor(x), dim=1)
    print(type(x))  # <class 'torch.Tensor'>
    print(x.shape)  # torch.Size([97, 1])
    
    y = df['profit']
    y = np.array(y)
    y = torch.unsqueeze(torch.FloatTensor(y), dim=1)
    print(type(y))  # <class 'torch.Tensor'>
    print(y.shape)  # torch.Size([97, 1])

## 搭建神经网络（来源：B站莫烦） ##

class Net(torch.nn.Module):
        def __init__(self, n_feature, n_hidden, n_output):
            super(Net, self).__init__()
            self.hidden = torch.nn.Linear(n_feature, n_hidden)
            self.out = torch.nn.Linear(n_hidden, n_output)
    
        def forward(self, x):
            x = F.relu(self.hidden(x))
            x = self.out(x)
            return x
    
    
    net = Net(1, 10, 1)
    print(net)
    
    optimizer = torch.optim.Adam(net.parameters(), lr=0.5)
    loss_func = torch.nn.MSELoss()  # 均方差
    
    for t in range(100):
        prediction = net(x)
    
        loss = loss_func(prediction, y)  # 一定要prediction在前, y在后
    
        optimizer.zero_grad()  # 梯度降零
        loss.backward()
        optimizer.step()
        if t % 5 == 0:
    	    # plot and show learning process
    	    plt.cla()
    	    plt.scatter(x.data.numpy(), y.data.numpy())
    	    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
    	    plt.text(0.5, 0, 'Loss=%.4f' % loss.data.numpy(), fontdict={
        'size': 20, 'color': 'red'})
    	    plt.pause(0.1)
    
    plt.ioff()
    plt.show()

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2t1bkFVR1VTVA_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200602142743991.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2t1bkFVR1VTVA==,size_16,color_FFFFFF,t_70