pytorch实现线性回归

 

In [1]:

import torch
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from torch import nn

 

In [2]:

data = pd.read_csv('./Income1.csv')
data

	Unnamed: 0	Education	Income
0	1	10.000000	26.658839
1	2	10.401338	27.306435
2	3	10.842809	22.132410
3	4	11.244147	21.169841
4	5	11.645485	15.192634
5	6	12.086957	26.398951
6	7	12.488294	17.435307
7	8	12.889632	25.507885
8	9	13.290970	36.884595
9	10	13.732441	39.666109
10	11	14.133779	34.396281
11	12	14.535117	41.497994
12	13	14.976589	44.981575
13	14	15.377926	47.039595
14	15	15.779264	48.252578
15	16	16.220736	57.034251
16	17	16.622074	51.490919
17	18	17.023411	61.336621
18	19	17.464883	57.581988
19	20	17.866221	68.553714
20	21	18.267559	64.310925
21	22	18.709030	68.959009
22	23	19.110368	74.614639
23	24	19.511706	71.867195
24	25	19.913043	76.098135
25	26	20.354515	75.775218
26	27	20.755853	72.486055
27	28	21.157191	77.355021
28	29	21.598662	72.118790
29	30	22.000000	80.260571

 

In [3]:

plt.scatter(data.Education, data.Income)
plt.xlabel('Education')
plt.ylabel('Income')

 

Out[3]:

Text(0, 0.5, 'Income')

 

 

In [4]:

# 目标 wx+b 分解写法
w = torch.randn(1, requires_grad=True)
b = torch.zeros(1, requires_grad=True)
learning_rate = 0.001
display(w, b)

 

 

tensor([-0.5873], requires_grad=True)

 

tensor([0.], requires_grad=True)

 

In [5]:

X = torch.from_numpy(data.Education.values.reshape(-1,1)).type(torch.float32)
Y = torch.from_numpy(data.Income.values.reshape(-1,1)).type(torch.float32)

 

In [6]:

# 定义训练过程
for epoch in range(5000): 
    for x, y in zip(X, Y):
        y_pred = torch.matmul(x, w) + b
        # 损失函数
        loss = (y - y_pred).pow(2).sum()

        if w.grad is not None:
            # 重置w的导数
            w.grad.data.zero_()
        if b.grad is not None:
            b.grad.data.zero_()

        # 反向传播求w,b的导数
        loss.backward()
        # 更新w,b
        with torch.no_grad():
            w.data -= w.grad.data * learning_rate
            b.data -= b.grad.data * learning_rate

 

In [7]:

display(w, b)

 

 

tensor([5.1266], requires_grad=True)

 

tensor([-32.6956], requires_grad=True)

 

In [8]:

plt.scatter(data.Education, data.Income)
plt.plot(X.numpy(), (torch.matmul(X, w)+b).data.numpy(), color='red')

 

Out[8]:

[<matplotlib.lines.Line2D at 0x23382d9b5b0>]

 

 

In [11]:

### pytorch实现线性回归——封装

 

In [12]:

model = nn.Linear(1, 1)
model

 

Out[12]:

Linear(in_features=1, out_features=1, bias=True)

 

In [15]:

# 定义损失函数
loss_fn = nn.MSELoss()
# 定义优化器，第一个参数是要更新的模型中的参数
opt = torch.optim.SGD(model.parameters(), lr=0.001)

 

In [16]:

# 训练
for epoch in range(5000):
    for x, y in zip(X, Y):
        y_pred = model(x)
        loss = loss_fn(y, y_pred)
        # 梯度清零操作
        opt.zero_grad()
        loss.backward()
        # 更新操作
        opt.step()

 

In [18]:

display(model.weight, model.bias)

 

 

Parameter containing:
tensor([[5.1265]], requires_grad=True)

 

Parameter containing:
tensor([-32.6946], requires_grad=True)