# 第五章 神经网络

标准BP

# coding: utf-8
# 标准的BP 我们没运行一条数据改变更新一次参数,在一次数据集的遍历只把误差累计起来，各参数的导数只用每次求得的导数更新，不用累计！
import pandas as pd
from pandas import *
import numpy as np
from numpy import *
x = pd.read_csv(r"C:\Users\zmy\Desktop\titanic\xigua4.csv",header=None,nrows=8)
x = x.transpose()
x = array(x)
result = pd.read_csv(r"C:\Users\zmy\Desktop\titanic\xigua4.csv",header=None,skiprows=8,nrows=1)
result = result.transpose()
result = array(result)
result = result - 1

#bp算法
m,n = shape(x)
t = 1
v = np.random.rand(n,n+1) # 输入层与隐含层的权值
w = np.random.rand(n+1, t)# 隐含层和输出层的权值
thy = np.random.rand(n+1)# 隐含层的阈值
tho = np.random.rand(t)# 输出层的阈值
out = np.zeros((m,t))# 输出层的输出值
bn = np.zeros(n+1)#隐含层的输出值
gj = np.zeros(t)
eh = np.zeros(n+1)
xk = 1

kn = 0 # 迭代次数
sn = 0 #
old_ey = 0
ii = 5
while(1):
ii -= 1
kn = kn + 1
ey = 0
for i in range(0,m):
#计算隐含层输出
for j in range(0, n+1):
ca = 0
for h in range(0, n):
ca = ca + v[h][j] * x[i][h]
bn[j] = 1/(1+exp(-ca+thy[j]))
# 计算输出层输出
for h1 in range(0,t):
ba = 0
for h2 in range(0,n+1):
ba = ba + w[h2][h1] * bn[h2]
out[i][h1] = 1 / (1+ exp(-ba + tho[h1]))
# 计算累积误差
for h1 in range(0,t):
ey = ey + pow((out[i][h1] - result[i]), 2)/2
# print 'ey', ey
# 计算gj
for h1 in range(0,t):
gj[h1] =  out[i][h1]*(1-out[i][h1])*(result[i] - out[i][h1])
# print out[i][h1],result[i]
# 计算eh
for h1 in range(0,n+1):
for h2 in range(0, t):
eh[h1] = bn[h1] * (1 - bn[h1]) * w[h1][h2]*gj[h2]
# 更新w
for h2 in range(0, t):
for h1 in range(0,n+1):
w[h1][h2] = w[h1][h2] + xk * gj[h2] * bn[h1]
#更新输出阈值
for h1 in range(0,t):
tho[h1] = tho[h1] - xk * gj[h1]
# 更新输入层与隐含层的权值
for h2 in range(0, n + 1):
for h1 in range(0, n):
v[h1][h2] = v[h1][h2] + xk * eh[h2] * x[i][h1]
#更新隐含层阈值
for h1 in range(0,n+1):
thy[h1] = thy[h1] - xk * eh[h1]
if(abs(ey-old_ey) < 0.0001):
# print abs(ey-old_ey)
sn = sn + 1
if(sn == 100):
break

else:
old_ey = ey
# ey = 0
sn = 0

for i in range(0,m):
for j in range(0,t):
print i,out[i][j], result[i]

结果为： （行标，预测值，实际值）

0 0.00433807645401 [0]

1 0.00532600009637 [0]

2 0.00427358256359 [0]

3 0.0208781402544 [0]

4 0.0189059379881 [0]

5 0.989732982598 [1]

6 0.990855525385 [1]

7 0.968537961141 [1]

8 0.998602511829 [1]

9 0.998036011905 [1]

10 0.015951504667 [0]

11 0.0151684814171 [0]

12 0.0116095552438 [0]

13 0.998160689389 [1]

14 0.998935912 [1]

15 0.990103694861 [1]

16 0.988335990994 [1]

累计BP

# coding: utf-8
# 累计BP 相对于标准BP是每次把所有的数据都运行完，把所有的误差都累计起来在更新参数
import pandas as pd
import numpy as np
from pandas import *
from numpy import *

x = pd.read_csv(r'C:\Users\zmy\Desktop\titanic\xigua4.csv', header=None, nrows=8)
y = pd.read_csv(r'C:\Users\zmy\Desktop\titanic\xigua4.csv', header= None, skiprows=8,nrows=1)
y = y-1
x = x.transpose()
x = array(x)
y = array(y)
y = y.transpose()

Eta = 1 # 学习率
t = 1 # 输出
m, n = shape(x) # 数据集的行与列
w = np.random.rand(n+1, n) # 隐含层与输出层的权重
v = np.random.rand(n, n+1) # 输入层与隐含层的权重
Zta = np.random.rand(t) # 输出层阈值
Gamma = np.random.rand(n+1) # 隐含层阈值
bn = zeros((m,n+1)) # 隐含层输出
yk = zeros((m,t)) # 输出层输出
Alpha = zeros(n)

gj = zeros(m)
eh = zeros((m,n+1))

k = 0
sn = 0
old_ey = 0
while(1):
k += 1
ey = 0
for i in range(0, m):
for h1 in range(0, n+1):
temp = 0
for h2 in range(0, n):
temp = temp + v[h2][h1] * x[i][h2]
bn[i][h1] = 1 / (1+ exp(-temp+ Gamma[h1]))

for h1 in range(0, t):
temp = 0
for h2 in range(0, n+1):
temp += w[h2][h1] * bn[i][h2]
yk[i][h1] = 1 / (1 + exp(-temp + Zta[h1]))
# 计算累计误差
for h1 in range(0,t):
ey += pow(yk[i][h1] - y[i], 2) / 2

for h1 in range(0, m):
gj[h1] = yk[h1][0] * (1 - yk[h1][0]) * (y[h1] - yk[h1][0])
for i in range(0, m):
for h1 in range(n+1):
temp = 0
for h2 in range(0, t):
temp += w[h1][h2] * gj[i]
eh[i][h1] = bn[i][h1] * (1 - bn[i][h1]) * temp
w1 = zeros((n+1, t))
v1 = zeros((n,n+1))
Zta1 = zeros(t)
Gamma1 = zeros(n+1)
# 计算四个参数的导数
for i in range(0, m):
for h1 in range(0, t):
Zta1[h1] += (-1) * gj[i] * Eta
for h2 in range(0, n+1):
w1[h2][h1] += Eta * gj[i] * bn[i][h2]

for h1 in range(0, n+1):
Gamma1[h1] += Eta * (-1) * eh[i][h1]
for h2 in range(0, n):
v1[h2][h1] += Eta * eh[i][h1] * x[i][h2]
# 更新参数
v = v + v1
w = w + w1
Gamma = Gamma + Gamma1
Zta = Zta + Zta1
if (abs(old_ey-ey) < 0.0001) :
sn += 1
if sn == 100:
break
else:
old_ey = ey
sn = 0

for i in range(0,m):
for j in range(0,t):
print i,yk[i][j], y[i]

结果输出

0 9.28395603439e-05 [0]

1 0.00408553765608 [0]

2 0.00750763695368 [0]

3 0.0285684849738 [0]

4 0.00591863864577 [0]

5 0.985047169485 [1]

6 0.991935228407 [1]

7 0.968524769653 [1]

8 0.996291194651 [1]

9 0.996365288109 [1]

10 0.00064978194805 [0]

11 0.0158218829283 [0]

12 0.0127356648444 [0]

13 0.996965938838 [1]

14 0.999528551401 [1]

15 0.999273125275 [1]

16 0.991180793173 [1]