#库的导入
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
#激活函数
def tanh(x):
return (np.exp(x)-np.exp(-x))/(np.exp(x)+np.exp(-x))
#激活函数偏导数
def de_tanh(x):
return (1-x**2)
#参数设置
samnum = 72 #输入数据数量
hiddenunitnum = 8 #隐含层节点数
indim = 4 #输入层节点数
outdim = 1 #输出层节点数
maxepochs = 500 #最大训练次数
errorfinal = 0.65*10**(-3) #停止迭代训练条件
learnrate = 0.001 #学习率
#输入数据的导入
df = pd.read_csv("train.csv")
df.columns = ["Co", "Cr", "Mg", "Pb", "Ti"]
Co = df["Co"]
Co = np.array(Co)
Cr = df["Cr"]
Cr = np.array(Cr)
Mg=df["Mg"]
Mg=np.array(Mg)
Pb = df["Pb"]
Pb =np.array(Pb)
Ti = df["Ti"]
Ti = np.array(Ti)
samplein = np.mat([Co,Cr,Mg,Pb])
#数据归一化，将输入数据压缩至0到1之间，便于计算，后续通过反归一化恢复原始值
sampleinminmax = np.array([samplein.min(axis=1).T.tolist()[0],samplein.max(axis=1).T.tolist()[0]]).transpose()#对应最大值最小值
sampleout = np.mat([Ti])
sampleoutminmax = np.array([sampleout.min(axis=1).T.tolist()[0],sampleout.max(axis=1).T.tolist()[0]]).transpose()#对应最大值最小值
sampleinnorm = ((np.array(samplein.T)-sampleinminmax.transpose()[0])/(sampleinminmax.transpose()[1]-sampleinminmax.transpose()[0])).transpose()
sampleoutnorm = ((np.array(sampleout.T)-sampleoutminmax.transpose()[0])/(sampleoutminmax.transpose()[1]-sampleoutminmax.transpose()[0])).transpose()
#给归一化后的数据添加噪声
noise = 0.03*np.random.rand(sampleoutnorm.shape[0],sampleoutnorm.shape[1])
sampleoutnorm += noise
#聚类生成隐含层径向基函数的中心点w1
x = sampleinnorm.transpose()
estimator=KMeans(n_clusters=8,max_iter=10000)
estimator.fit(x)
w1 = estimator.cluster_centers_
#计算得到隐含层的宽度向量b1
b1 = np.mat(np.zeros((hiddenunitnum,outdim)))
for i in range(hiddenunitnum):
cmax = 0
for j in range(hiddenunitnum):
temp_dist=np.sqrt(np.sum(np.square(w1[i,:]-w1[j,:])))
if cmax<temp_dist:
cmax=temp_dist
b1[i] = cmax/np.sqrt(2*hiddenunitnum)
#随机生成输出层的权值w2、阈值b2
scale = np.sqrt(3/((indim+outdim)*0.5))
w2 = np.random.uniform(low=-scale,high=scale,size=[hiddenunitnum,outdim])
b2 = np.random.uniform(low=-scale, high=scale, size=[outdim,1])
#将输入数据、参数设置为矩阵，便于计算
inputin=np.mat(sampleinnorm.T)
w1=np.mat(w1)
b1=np.mat(b1)
w2=np.mat(w2)
b2=np.mat(b2)
#errhistory存储误差
errhistory = np.mat(np.zeros((1,maxepochs)))
#开始训练
for i in range(maxepochs):
#前向传播计算
#hidden_out为隐含层输出
hidden_out = np.mat(np.zeros((samnum, hiddenunitnum)))
for a in range(samnum):
for j in range(hiddenunitnum):
d=(inputin[a, :] - w1[j, :]) * (inputin[a, :] - w1[j, :]).T
c=2 * b1[j, :] * b1[j, :]
hidden_out[a, j] = np.exp((-1.0 )* (d/c))
#output为输出层输出
output = tanh(hidden_out * w2 + b2)
# 计算误差
out_real = np.mat(sampleoutnorm.transpose())
err = out_real - output
loss = np.sum(np.square(err))
#判断是否停止训练
if loss < errorfinal:
break
errhistory[:,i] = loss
#反向传播计算
output=np.array(output.T)
belta=de_tanh(output).transpose()
#分别计算每个参数的误差项
dw1now = np.zeros((8,4))
db1now = np.zeros((8,1))
dw2now = np.zeros((8,1))
db2now = np.zeros((1,1))
for j in range(hiddenunitnum):
sum1 = 0.0
sum2 = 0.0
sum3 = 0.0
sum4 = 0.0
for a in range(samnum):
sum1 +=err[a,:] * belta[a,:] * hidden_out[a,j] * (inputin[a,:]-w1[j,:])
sum2 +=err[a,:] * belta[a,:] * hidden_out[a,j] * (inputin[a,:]-w1[j,:])*(inputin[a,:]-w1[j,:]).T
sum3 +=err[a,:] * belta[a,:] * hidden_out[a,j]
sum4 +=err[a,:] * belta[a,:]
dw1now[j,:]=(w2[j,:]/(b1[j,:]*b1[j,:])) * sum1
db1now[j,:] =(w2[j,:]/(b1[j,:]*b1[j,:]*b1[j,:])) * sum2
dw2now[j,:] =sum3
db2now = sum4
#根据误差项对四个参数进行更新
w1 += learnrate * dw1now
b1 += learnrate * db1now
w2 += learnrate * dw2now
b2 += learnrate * db2now
print("the iteration is:",i+1,",the loss is:",loss)
print('更新的权重w1:',w1)
print('更新的偏置b1:',b1)
print('更新的权重w2:',w2)
print('更新的偏置b2:',b2)
print("The loss after iteration is ：",loss)
#保存训练结束后的参数，用于测试
np.save("w1.npy",w1)
np.save("b1.npy",b1)
np.save("w2.npy",w2)
np.save("b2.npy",b2)
#库的导入
import numpy as np
import pandas as pd
#激活函数tanh
def tanh(x):
return (np.exp(x)-np.exp(-x))/(np.exp(x)+np.exp(-x))
#测试数据数量
testnum = 24
#隐含层节点数量
hiddenunitnum = 8
#输入数据的导入，用于测试数据的归一化与返归一化
df = pd.read_csv("train.csv")
df.columns = ["Co", "Cr", "Mg", "Pb", "Ti"]
Co = df["Co"]
Co = np.array(Co)
Cr = df["Cr"]
Cr = np.array(Cr)
Mg=df["Mg"]
Mg=np.array(Mg)
Pb = df["Pb"]
Pb =np.array(Pb)
Ti = df["Ti"]
Ti = np.array(Ti)
samplein = np.mat([Co,Cr,Mg,Pb])
sampleinminmax = np.array([samplein.min(axis=1).T.tolist()[0],samplein.max(axis=1).T.tolist()[0]]).transpose()#对应最大值最小值
sampleout = np.mat([Ti])
sampleoutminmax = np.array([sampleout.min(axis=1).T.tolist()[0],sampleout.max(axis=1).T.tolist()[0]]).transpose()#对应最大值最小值
#导入训练的参数
w1=np.load('w1.npy')
w2=np.load('w2.npy')
b1=np.load('b1.npy')
b2=np.load('b2.npy')
w1 = np.mat(w1)
w2 = np.mat(w2)
b1 = np.mat(b1)
b2 = np.mat(b2)
#测试数据的导入
df = pd.read_csv("test.csv")
df.columns = ["Co", "Cr", "Mg", "Pb", "Ti"]
Co = df["Co"]
Co = np.array(Co)
Cr = df["Cr"]
Cr = np.array(Cr)
Mg=df["Mg"]
Mg=np.array(Mg)
Pb = df["Pb"]
Pb =np.array(Pb)
Ti = df["Ti"]
Ti = np.array(Ti)
input=np.mat([Co,Cr,Mg,Pb])
#测试数据中输入数据的归一化
inputnorm=(np.array(input.T)-sampleinminmax.transpose()[0])/(sampleinminmax.transpose()[1]-sampleinminmax.transpose()[0])
#hidden_out2用于保持隐含层输出
hidden_out2 = np.mat(np.zeros((testnum,hiddenunitnum)))
#计算隐含层输出
for a in range(testnum):
for j in range(hiddenunitnum):
d = (inputnorm[a, :] - w1[j, :]) * (inputnorm[a, :] - w1[j, :]).T
c = 2 * b1[j, :] * b1[j, :].T
hidden_out2[a, j] = np.exp((-1.0) * (d / c))
#计算输出层输出
output = tanh(hidden_out2 * w2 + b2)
#对输出结果进行反归一化
diff = sampleoutminmax[:,1]-sampleoutminmax[:,0]
networkout2 = output*diff+sampleoutminmax[0][0]
networkout2 = np.array(networkout2).transpose()
output1=networkout2.flatten()#降成一维数组
output1=output1.tolist()
for i in range(testnum):
output1[i] = float('%.2f'%output1[i])
print("the prediction is:",output1)
#将输出结果与真实值进行对比，计算误差
output=Ti
err = output1 - output
rmse = (np.sum(np.square(output-output1))/len(output)) ** 0.5
mae = np.sum(np.abs(output-output1))/len(output)
average_loss1=np.sum(np.abs((output-output1)/output))/len(output)
mape="%.2f%%"%(average_loss1*100)
f1 = 0
for m in range(testnum):
f1 = f1 + np.abs(output[m]-output1[m])/((np.abs(output[m])+np.abs(output1[m]))/2)
f2 = f1 / testnum
smape="%.2f%%"%(f2*100)
print("the MAE is :",mae)
print("the RMSE is :",rmse)
print("the MAPE is :",mape)
print("the SMAPE is :",smape)
#计算预测值与真实值误差与真实值之比的分布
A=0
B=0
C=0
D=0
E=0
for m in range(testnum):
y1 = np.abs(output[m]-output1[m])/np.abs(output[m])
if y1 <= 0.1:
A = A + 1
elif y1 > 0.1 and y1 <= 0.2:
B = B + 1
elif y1 > 0.2 and y1 <= 0.3:
C = C + 1
elif y1 > 0.3 and y1 <= 0.4:
D = D + 1
else:
E = E + 1
print("Ratio <= 0.1 :",A)
print("0.1< Ratio <= 0.2 :",B)
print("0.2< Ratio <= 0.3 :",C)
print("0.3< Ratio <= 0.4 :",D)
print("Ratio > 0.4 :",E)
按照以上代码形式写成两部分代码，分开编写
这段代码利用numpy的ones()函数生成了一个与X数组在前两维形状相同的三维数组，所有元素均为1，第三维大小为1。
扫一扫
2223
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
