mirror of
https://github.com/apachecn/ailearning.git
synced 2026-02-13 07:15:26 +08:00
260 lines
8.1 KiB
Python
260 lines
8.1 KiB
Python
#!/usr/bin/python
|
||
# coding:utf8
|
||
|
||
"""
|
||
Created on Nov 4, 2010
|
||
Update on 2017-03-21
|
||
Chapter 5 source file for Machine Learing in Action
|
||
@author: Peter/geekidentity/片刻
|
||
"""
|
||
from numpy import *
|
||
import matplotlib.pyplot as plt
|
||
|
||
|
||
def loadDataSet(fileName):
|
||
"""loadDataSet（对文件进行逐行解析，从而得到第行的类标签和整个数据矩阵）
|
||
|
||
Args:
|
||
fileName 文件名
|
||
Returns:
|
||
dataMat 数据矩阵
|
||
labelMat 类标签
|
||
"""
|
||
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):
|
||
"""
|
||
随机选择一个整数
|
||
Args:
|
||
i 第一个alpha的下标
|
||
m 所有alpha的数目
|
||
Returns:
|
||
j 返回一个不为i的随机数，在0~m之间的整数值
|
||
"""
|
||
j = i
|
||
while j == i:
|
||
j = int(random.uniform(0, m))
|
||
return j
|
||
|
||
|
||
def clipAlpha(aj, H, L):
|
||
"""clipAlpha(调整aj的值，使aj处于 L<=aj<=H)
|
||
Args:
|
||
aj 目标值
|
||
H 最大值
|
||
L 最小值
|
||
Returns:
|
||
aj 目标值
|
||
"""
|
||
if aj > H:
|
||
aj = H
|
||
if L > aj:
|
||
aj = L
|
||
return aj
|
||
|
||
|
||
def calcWs(alphas, dataArr, classLabels):
|
||
"""
|
||
基于alpha计算w值
|
||
Args:
|
||
alphas 拉格朗日乘子
|
||
dataArr feature数据集
|
||
classLabels 目标变量数据集
|
||
|
||
Returns:
|
||
wc 回归系数
|
||
"""
|
||
X = mat(dataArr)
|
||
labelMat = mat(classLabels).transpose()
|
||
m, n = shape(X)
|
||
w = zeros((n, 1))
|
||
for i in range(m):
|
||
w += multiply(alphas[i] * labelMat[i], X[i, :].T)
|
||
return w
|
||
|
||
|
||
'''
|
||
#######********************************
|
||
Non-Kernel VErsions below
|
||
#######********************************
|
||
'''
|
||
|
||
class optStruct:
|
||
def __init__(self, dataMatIn, classLabels, C, toler): # Initialize the structure with the parameters
|
||
self.X = dataMatIn
|
||
self.labelMat = classLabels
|
||
self.C = C
|
||
self.tol = toler
|
||
self.m = shape(dataMatIn)[0]
|
||
self.alphas = mat(zeros((self.m, 1)))
|
||
self.b = 0
|
||
self.eCache = mat(zeros((self.m, 2))) # first column is valid flag
|
||
|
||
|
||
def calcEk(oS, k):
|
||
fXk = float(multiply(oS.alphas, oS.labelMat).T * (oS.X * oS.X[k, :].T)) + oS.b
|
||
Ek = fXk - float(oS.labelMat[k])
|
||
return Ek
|
||
|
||
|
||
def selectJ(i, oS, Ei): # this is the second choice -heurstic, and calcs Ej
|
||
maxK = -1
|
||
maxDeltaE = 0
|
||
Ej = 0
|
||
oS.eCache[i] = [1, Ei] # set valid #choose the alpha that gives the maximum delta E
|
||
validEcacheList = nonzero(oS.eCache[:, 0].A)[0]
|
||
if (len(validEcacheList)) > 1:
|
||
for k in validEcacheList: # loop through valid Ecache values and find the one that maximizes delta E
|
||
if k == i: continue # don't calc for i, waste of time
|
||
Ek = calcEk(oS, k)
|
||
deltaE = abs(Ei - Ek)
|
||
if (deltaE > maxDeltaE):
|
||
maxK = k
|
||
maxDeltaE = deltaE
|
||
Ej = Ek
|
||
return maxK, Ej
|
||
else: # in this case (first time around) we don't have any valid eCache values
|
||
j = selectJrand(i, oS.m)
|
||
Ej = calcEk(oS, j)
|
||
return j, Ej
|
||
|
||
|
||
def updateEk(oS, k): # after any alpha has changed update the new value in the cache
|
||
Ek = calcEk(oS, k)
|
||
oS.eCache[k] = [1, Ek]
|
||
|
||
|
||
def innerL(i, oS):
|
||
Ei = calcEk(oS, i)
|
||
if ((oS.labelMat[i] * Ei < -oS.tol) and (oS.alphas[i] < oS.C)) or (
|
||
(oS.labelMat[i] * Ei > oS.tol) and (oS.alphas[i] > 0)):
|
||
j, Ej = selectJ(i, oS, Ei) # this has been changed from selectJrand
|
||
alphaIold = oS.alphas[i].copy()
|
||
alphaJold = oS.alphas[j].copy()
|
||
if (oS.labelMat[i] != oS.labelMat[j]):
|
||
L = max(0, oS.alphas[j] - oS.alphas[i])
|
||
H = min(oS.C, oS.C + oS.alphas[j] - oS.alphas[i])
|
||
else:
|
||
L = max(0, oS.alphas[j] + oS.alphas[i] - oS.C)
|
||
H = min(oS.C, oS.alphas[j] + oS.alphas[i])
|
||
if L == H:
|
||
print("L==H")
|
||
return 0
|
||
eta = 2.0 * oS.X[i, :] * oS.X[j, :].T - oS.X[i, :] * oS.X[i, :].T - oS.X[j, :] * oS.X[j, :].T
|
||
if eta >= 0:
|
||
print("eta>=0")
|
||
return 0
|
||
oS.alphas[j] -= oS.labelMat[j] * (Ei - Ej) / eta
|
||
oS.alphas[j] = clipAlpha(oS.alphas[j], H, L)
|
||
updateEk(oS, j) # added this for the Ecache
|
||
if (abs(oS.alphas[j] - alphaJold) < 0.00001):
|
||
print("j not moving enough")
|
||
return 0
|
||
oS.alphas[i] += oS.labelMat[j] * oS.labelMat[i] * (alphaJold - oS.alphas[j]) # update i by the same amount as j
|
||
updateEk(oS, i) # added this for the Ecache #the update is in the oppostie direction
|
||
b1 = oS.b - Ei - oS.labelMat[i] * (oS.alphas[i] - alphaIold) * oS.X[i, :] * oS.X[i, :].T - oS.labelMat[j] * (
|
||
oS.alphas[j] - alphaJold) * oS.X[i, :] * oS.X[j, :].T
|
||
b2 = oS.b - Ej - oS.labelMat[i] * (oS.alphas[i] - alphaIold) * oS.X[i, :] * oS.X[j, :].T - oS.labelMat[j] * (
|
||
oS.alphas[j] - alphaJold) * oS.X[j, :] * oS.X[j, :].T
|
||
if (0 < oS.alphas[i]) and (oS.C > oS.alphas[i]):
|
||
oS.b = b1
|
||
elif (0 < oS.alphas[j]) and (oS.C > oS.alphas[j]):
|
||
oS.b = b2
|
||
else:
|
||
oS.b = (b1 + b2) / 2.0
|
||
return 1
|
||
else:
|
||
return 0
|
||
|
||
|
||
def smoP(dataMatIn, classLabels, C, toler, maxIter): # full Platt SMO
|
||
oS = optStruct(mat(dataMatIn), mat(classLabels).transpose(), C, toler)
|
||
iter = 0
|
||
entireSet = True
|
||
alphaPairsChanged = 0
|
||
while (iter < maxIter) and ((alphaPairsChanged > 0) or (entireSet)):
|
||
alphaPairsChanged = 0
|
||
if entireSet: # go over all
|
||
for i in range(oS.m):
|
||
alphaPairsChanged += innerL(i, oS)
|
||
print("fullSet, iter: %d i:%d, pairs changed %d" % (iter, i, alphaPairsChanged))
|
||
iter += 1
|
||
else: # go over non-bound (railed) alphas
|
||
nonBoundIs = nonzero((oS.alphas.A > 0) * (oS.alphas.A < C))[0]
|
||
for i in nonBoundIs:
|
||
alphaPairsChanged += innerL(i, oS)
|
||
print("non-bound, iter: %d i:%d, pairs changed %d" % (iter, i, alphaPairsChanged))
|
||
iter += 1
|
||
if entireSet:
|
||
entireSet = False # toggle entire set loop
|
||
elif (alphaPairsChanged == 0):
|
||
entireSet = True
|
||
print("iteration number: %d" % iter)
|
||
return oS.b, oS.alphas
|
||
|
||
|
||
def plotfig_SVM(xArr, yArr, ws, b, alphas):
|
||
"""
|
||
参考地址：
|
||
http://blog.csdn.net/maoersong/article/details/24315633
|
||
http://www.cnblogs.com/JustForCS/p/5283489.html
|
||
http://blog.csdn.net/kkxgx/article/details/6951959
|
||
"""
|
||
|
||
xMat = mat(xArr)
|
||
yMat = mat(yArr)
|
||
|
||
# b原来是矩阵，先转为数组类型后其数组大小为（1,1），所以后面加[0]，变为(1,)
|
||
b = array(b)[0]
|
||
fig = plt.figure()
|
||
ax = fig.add_subplot(111)
|
||
|
||
# 注意flatten的用法
|
||
ax.scatter(xMat[:, 0].flatten().A[0], xMat[:, 1].flatten().A[0])
|
||
|
||
# x最大值，最小值根据原数据集dataArr[:, 0]的大小而定
|
||
x = arange(-1.0, 10.0, 0.1)
|
||
|
||
# 根据x.w + b = 0 得到，其式子展开为w0.x1 + w1.x2 + b = 0, x2就是y值
|
||
y = (-b-ws[0, 0]*x)/ws[1, 0]
|
||
ax.plot(x, y)
|
||
|
||
for i in range(shape(yMat[0, :])[1]):
|
||
if yMat[0, i] > 0:
|
||
ax.plot(xMat[i, 0], xMat[i, 1], 'cx')
|
||
else:
|
||
ax.plot(xMat[i, 0], xMat[i, 1], 'kp')
|
||
|
||
# 找到支持向量，并在图中标红
|
||
for i in range(100):
|
||
if alphas[i] > 0.0:
|
||
ax.plot(xMat[i, 0], xMat[i, 1], 'ro')
|
||
plt.show()
|
||
|
||
|
||
if __name__ == "__main__":
|
||
# 获取特征和目标变量
|
||
dataArr, labelArr = loadDataSet('input/6.SVM/testSet.txt')
|
||
# print labelArr
|
||
|
||
# b是常量值， alphas是拉格朗日乘子
|
||
b, alphas = smoP(dataArr, labelArr, 0.6, 0.001, 40)
|
||
print '/n/n/n'
|
||
print 'b=', b
|
||
print 'alphas[alphas>0]=', alphas[alphas > 0]
|
||
print 'shape(alphas[alphas > 0])=', shape(alphas[alphas > 0])
|
||
for i in range(100):
|
||
if alphas[i] > 0:
|
||
print dataArr[i], labelArr[i]
|
||
# 画图
|
||
ws = calcWs(alphas, dataArr, labelArr)
|
||
plotfig_SVM(dataArr, labelArr, ws, b, alphas)
|