第1关:SMO高效优化算法
import numpy as np
import random
def calcEk(oS, k):
"""
计算误差
Parameters:
oS - 数据结构
k - 标号为k的数据
Returns:
Ek - 标号为k的数据误差
"""
fXk = float(np.multiply(oS.alphas,oS.labelMat).T*(oS.X*oS.X[k,:].T) + oS.b)
Ek = fXk - float(oS.labelMat[k])
return Ek
def loadDataSet(fileName):
"""
读取数据
Parameters:
fileName - 文件名
Returns:
dataMat - 数据矩阵
labelMat - 数据标签
"""
dataMat = []; labelMat = []
fr = open(fileName)
for line in fr.readlines():
lineArr = line.strip().split('\t')
dataMat.append([float(lineArr[0]), float(lineArr[1])])
labelMat.append(float(lineArr[2]))
return dataMat,labelMat
def selectJrand(i, m):
"""
函数说明:随机选择alpha_j的索引值
Parameters:
i - alpha_i的索引值
m - alpha参数个数
Returns:
j - alpha_j的索引值
"""
j = i
while (j == i):
j = int(random.uniform(0, m))
return j
def selectJ(i, oS, Ei):
"""
内循环启发方式2
Parameters:
i - 标号为i的数据的索引值
oS - 数据结构
Ei - 标号为i的数据误差
Returns:
j, maxK - 标号为j或maxK的数据的索引值
Ej - 标号为j的数据误差
"""
maxK = -1; maxDeltaE = 0; Ej = 0
oS.eCache[i] = [1,Ei]
validEcacheList = np.nonzero(oS.eCache[:,0].A)[0]
if (len(validEcacheList)) > 1:
for k in validEcacheList:
if k == i: continue
Ek = calcEk(oS, k)
deltaE = abs(Ei - Ek)
if (deltaE > maxDeltaE):
maxK = k; maxDeltaE = deltaE; Ej = Ek
return maxK, Ej
else:
j = selectJrand(i, oS.m)
Ej = calcEk(oS, j)
return j, Ej
def updateEk(oS, k):
"""
计算Ek,并更新误差缓存
Parameters:
oS - 数据结构
k - 标号为k的数据的索引值
Returns:
无
"""
Ek = calcEk(oS, k)
oS.eCache[k] = [1,Ek]
def clipAlpha(aj,H,L):
"""
修剪alpha_j
Parameters:
aj - alpha_j的值
H - alpha上限
L - alpha下限
Returns:
aj - 修剪后的alpah_j的值
"""
if aj > H:
aj = H
if L > aj:
aj = L
return aj
class optStruct:
"""
数据结构,维护所有需要操作的值
Parameters:
dataMatIn - 数据矩阵
classLabels - 数据标签
C - 松弛变量
toler - 容错率
"""
def __init__(self, dataMatIn, classLabels, C, toler):
self.X = dataMatIn
self.labelMat = classLabels
self.C = C
self.tol = toler
self.m = np.shape(dataMatIn)[0]
self.alphas = np.mat(np.zeros((self.m,1)))
self.b = 0
self.eCache = np.mat(np.zeros((self.m,2)))
def smoP(dataMatIn, classLabels, C, toler, maxIter):
dataMatrix = np.mat(dataMatIn); labelMat = np.mat(classLabels).transpose()
b = 0; m,n = np.shape(dataMatrix)
alphas = np.mat(np.zeros((m,1)))
iter_num = 0
while (iter_num < maxIter):
alphaPairsChanged = 0
for i in range(m):
fXi = float(np.multiply(alphas,labelMat).T*(dataMatrix*dataMatrix[i,:].T)) + b
Ei = fXi - float(labelMat[i])
if ((labelMat[i]*Ei < -toler) and (alphas[i] < C)) or ((labelMat[i]*Ei > toler) and (alphas[i] > 0)):
j = selectJrand(i,m)
fXj = float(np.multiply(alphas,labelMat).T*(dataMatrix*dataMatrix[j,:].T)) + b
Ej = fXj - float(labelMat[j])
alphaIold = alphas[i].copy(); alphaJold = alphas[j].copy();
if (labelMat[i] != labelMat[j]):
L = max(0, alphas[j] - alphas[i])
H = min(C, C + alphas[j] - alphas[i])
else:
L = max(0, alphas[j] + alphas[i] - C)
H = min(C, alphas[j] + alphas[i])
if L==H: print("L==H"); continue
eta = 2.0 * dataMatrix[i,:]*dataMatrix[j,:].T - dataMatrix[i,:]*dataMatrix[i,:].T - dataMatrix[j,:]*dataMatrix[j,:].T
if eta >= 0: print("eta>=0"); continue
alphas[j] -= labelMat[j]*(Ei - Ej)/eta
alphas[j] = clipAlpha(alphas[j],H,L)
if (abs(alphas[j] - alphaJold) < 0.00001): print("alpha_j变化太小"); continue
alphas[i] += labelMat[j]*labelMat[i]*(alphaJold - alphas[j])
b1 = b - Ei- labelMat[i]*(alphas[i]-alphaIold)*dataMatrix[i,:]*dataMatrix[i,:].T - labelMat[j]*(alphas[j]-alphaJold)*dataMatrix[i,:]*dataMatrix[j,:].T
b2 = b - Ej- labelMat[i]*(alphas[i]-alphaIold)*dataMatrix[i,:]*dataMatrix[j,:].T - labelMat[j]*(alphas[j]-alphaJold)*dataMatrix[j,:]*dataMatrix[j,:].T
if (0 < alphas[i]) and (C > alphas[i]): b = b1
elif (0 < alphas[j]) and (C > alphas[j]): b = b2
else: b = (b1 + b2)/2.0
alphaPairsChanged += 1
if (alphaPairsChanged == 0): iter_num += 1
else: iter_num = 0
print("迭代次数: %d" % iter_num)
return b,alphas
def calcWs(alphas,dataArr,classLabels):
"""
计算w
Parameters:
dataArr - 数据矩阵
classLabels - 数据标签
alphas - alphas值
Returns:
w - 计算得到的w
"""
X = np.mat(dataArr); labelMat = np.mat(classLabels).transpose()
m,n = np.shape(X)
w = np.zeros((n,1))
for i in range(m):
w += np.multiply(alphas[i]*labelMat[i],X[i,:].T)
return w
if __name__ == '__main__':
dataArr, classLabels = loadDataSet('./src/step2/testSet.txt')
b, alphas = smoP(dataArr, classLabels, 0.6, 0.001, 40)
w = calcWs(alphas,dataArr, classLabels)