通过学习斯坦福公开课的线性规划和梯度下降，参考他人代码自己做了测试，写了个类以后有时间再去扩展，代码注释以后再加，作业好多：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
|
import numpy as npimport matplotlib.pyplot as pltimport randomclass dataMinning: datasets = [] labelsets = [] addressD = '' #Data folder addressL = '' #Label folder npDatasets = np.zeros(1) npLabelsets = np.zeros(1) cost = [] numIterations = 0 alpha = 0 theta = np.ones(2) #pCols = 0 #dRows = 0 def __init__(self,addressD,addressL,theta,numIterations,alpha,datasets=None): if datasets is None: self.datasets = [] else: self.datasets = datasets self.addressD = addressD self.addressL = addressL self.theta = theta self.numIterations = numIterations self.alpha = alpha def readFrom(self): fd = open(self.addressD,'r') for line in fd: tmp = line[:-1].split() self.datasets.append([int(i) for i in tmp]) fd.close() self.npDatasets = np.array(self.datasets) fl = open(self.addressL,'r') for line in fl: tmp = line[:-1].split() self.labelsets.append([int(i) for i in tmp]) fl.close() tm = [] for item in self.labelsets: tm = tm + item self.npLabelsets = np.array(tm) def genData(self,numPoints,bias,variance): self.genx = np.zeros(shape = (numPoints,2)) self.geny = np.zeros(shape = numPoints) for i in range(0,numPoints): self.genx[i][0] = 1 self.genx[i][1] = i self.geny[i] = (i + bias) + random.uniform(0,1) * variance def gradientDescent(self): xTrans = self.genx.transpose() # i = 0 while i < self.numIterations: hypothesis = np.dot(self.genx,self.theta) loss = hypothesis - self.geny #record the cost self.cost.append(np.sum(loss ** 2)) #calculate the gradient gradient = np.dot(xTrans,loss) #updata, gradientDescent self.theta = self.theta - self.alpha * gradient i = i + 1 def show(self): print 'yes' if __name__ == "__main__": c = dataMinning('c:\\city.txt','c:\\st.txt',np.ones(2),100000,0.000005) c.genData(100,25,10) c.gradientDescent() cx = range(len(c.cost)) plt.figure(1) plt.plot(cx,c.cost) plt.ylim(0,25000) plt.figure(2) plt.plot(c.genx[:,1],c.geny,'b.') x = np.arange(0,100,0.1) y = x * c.theta[1] + c.theta[0] plt.plot(x,y) plt.margins(0.2) plt.show() |
图1. 迭代过程中的误差cost
图2. 数据散点图和解直线
总结
以上就是本文关于Python编程实现线性回归和批量梯度下降法代码实例的全部内容，希望对大家有所帮助。如有不足之处，欢迎留言指出。感谢朋友们对本站的支持！
原文链接：https://www.cnblogs.com/Key-Ky/archive/2013/12/10/3468290.html
