mirror of
https://github.com/apachecn/ailearning.git
synced 2026-02-11 14:26:04 +08:00
118 lines
4.4 KiB
Python
118 lines
4.4 KiB
Python
"""
|
|
Created on Nov 4, 2010
|
|
Update on 2017-03-21
|
|
Chapter 5 source file for Machine Learing in Action
|
|
@author: Peter/geekidentity
|
|
"""
|
|
from numpy import *
|
|
from time import sleep
|
|
|
|
def loadDataSet(fileName):
|
|
"""
|
|
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: testSet.txt
|
|
|
|
Returns:
|
|
数据矩阵, 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=i #we want to select any J not equal to i
|
|
while (j==i):
|
|
j = int(random.uniform(0,m))
|
|
return j
|
|
|
|
def clipAlpha(aj,H,L):
|
|
"""
|
|
用于调整大于H或小于L的alpha值
|
|
Args:
|
|
aj:
|
|
H:
|
|
L:
|
|
|
|
Returns:
|
|
|
|
"""
|
|
if aj > H:
|
|
aj = H
|
|
if L > aj:
|
|
aj = L
|
|
return aj
|
|
|
|
def smoSimple(dataMatIn, classLabels, C, toler, maxIter):
|
|
"""
|
|
SVM SMO算法的简单实现:
|
|
创建一个alpha向量并将其初始化为0向量
|
|
当迭代次数据小于最大迭代次数时(外循环)
|
|
对数据集中的每个数据向量(内循环):
|
|
如果该数据向量可以被优化:
|
|
随机选择另外一个数据向量
|
|
同时优化这两个向量
|
|
如果两个向量都不能被优化，退出内循环
|
|
如果所有向量都没有被优化，增加迭代数目，继续下一次循环
|
|
Args:
|
|
dataMatIn: 数据集
|
|
classLabels: 类别标签
|
|
C: 常数C
|
|
toler: 容错率
|
|
maxIter: 退出前最大的循环次数
|
|
|
|
Returns:
|
|
|
|
"""
|
|
dataMatrix = mat(dataMatIn); labelMat = mat(classLabels).transpose()
|
|
b = 0; m,n = shape(dataMatrix)
|
|
alphas = mat(zeros((m,1)))
|
|
iter = 0
|
|
while (iter < maxIter):
|
|
alphaPairsChanged = 0
|
|
for i in range(m):
|
|
fXi = float(multiply(alphas,labelMat).T*(dataMatrix*dataMatrix[i,:].T)) + b
|
|
Ei = fXi - float(labelMat[i])#if checks if an example violates KKT conditions
|
|
if ((labelMat[i]*Ei < -toler) and (alphas[i] < C)) or ((labelMat[i]*Ei > toler) and (alphas[i] > 0)):
|
|
j = selectJrand(i,m)
|
|
fXj = float(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("j not moving enough"); continue
|
|
alphas[i] += labelMat[j]*labelMat[i]*(alphaJold - alphas[j])#update i by the same amount as j
|
|
#the update is in the oppostie direction
|
|
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
|
|
print("iter: %d i:%d, pairs changed %d" % (iter,i,alphaPairsChanged))
|
|
if (alphaPairsChanged == 0): iter += 1
|
|
else: iter = 0
|
|
print("iteration number: %d" % iter)
|
|
return b,alphas |