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
|
import math
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
data = pd.read_csv('Advertising.csv')
datax = data['newspaper'][0:150]
datax_1 = data['newspaper'][150:200]
datay = data['sales'][0:150]
datay_1 = data['sales'][150:200]
plt.plot(datax, datay, "ob")
def jie_w(datax,datay):
suma = 0;
num = 0;
sum1=0;
for i in range(len(datax)):
suma = (datay[i]*(datax[i]-sum(datax)/len(datax)))+suma
for i in range(len(datax)):
sum1 = sum1 + datax[i]*datax[i]
num = sum1 - (sum(datax)*sum(datax))/(len(datax))
return suma/num
print("w:",jie_w(datax,datay))
def jie_b(datax,datay):
suma = 0;
tt = jie_w(datax,datay)
for i in range(len(datax)):
suma = suma + (datay[i]-tt*datax[i])
num = suma / (len(datax))
return num
k=jie_w(datax,datay)
b=jie_b(datax,datay)
print("b",b)
y1=[0,datax.max()]
y2=[b,datax.max()*k+b]
plt.plot(y1,y2,'r')
plt.show()
datax_2 = 0
for i in range(len(datax_1)):
datax_2 = datax_2+math.pow(datax_1[i+150]*k+b-datay_1[i+150],2)
wucha = datax_2/len(datax_1)
print("均方误差：",wucha)
sddsum = 0
addsum = 0
datay_av = np.mean(datay_1)
for i in range(len(datax_1)):
sddsum = math.pow(datax_1[i+150]*k+b-datay_av,2)
addsum = math.pow(datay_1[i+150] - datay_av,2)
R = sddsum/addsum
print("R的平方分析：",R)
|