《机器学习实战》-支持向量机源码运行

SVM源码（smoSimple）

'''
文件名：svmSimple.py
Chapter 5 source file for Machine Learing in Action
@author: Peter
画图函数showClassifer参考链接为：
https://blog.csdn.net/qq_51307413/article/details/122130025
'''
from numpy import *
from time import sleep
import numpy as np
import matplotlib.pyplot as plt
import operator
import time

def loadDataSet(fileName):
    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):
    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):
    if aj > H: 
        aj = H
    if L > aj:
        aj = L
    return aj

def smoSimple(dataMatIn, classLabels, C, toler, maxIter):
    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

def showClassifer(dataMat,labelMat, alphas, w, b):
	#绘制样本点
	data_plus = []                                  #正样本
	data_minus = []                                 #负样本
	for i in range(len(dataMat)):
		if labelMat[i] > 0:
			data_plus.append(dataMat[i])
		else:
			data_minus.append(dataMat[i])
	data_plus_np = np.array(data_plus)              #转换为numpy矩阵
	data_minus_np = np.array(data_minus)            #转换为numpy矩阵
	plt.scatter(np.transpose(data_plus_np)[0], np.transpose(data_plus_np)[1], s=30, alpha=0.7)   #正样本散点图
	plt.scatter(np.transpose(data_minus_np)[0], np.transpose(data_minus_np)[1], s=30, alpha=0.7) #负样本散点图
	#绘制直线
	x1 = max(dataMat)[0]
	x2 = min(dataMat)[0]
	a1, a2 = w
	b = float(b)
	a1 = float(a1[0])
	a2 = float(a2[0])
	y1, y2 = (-b- a1*x1)/a2, (-b - a1*x2)/a2
	plt.plot([x1, x2], [y1, y2])
	#找出支持向量点
	for i, alpha in enumerate(alphas):
		if abs(alpha) > 0:
			x, y = dataMat[i]
			plt.scatter([x], [y], s=150, c='none', alpha=0.7, linewidth=1.5, edgecolor='red')
	plt.show()
	
def get_w(dataMat, labelMat, alphas):
    alphas, dataMat, labelMat = np.array(alphas), np.array(dataMat), np.array(labelMat)
    w = np.dot((np.tile(labelMat.reshape(1, -1).T, (1, 2)) * dataMat).T, alphas)
    return w.tolist()

if __name__ == '__main__':
	dataMat, labelMat = loadDataSet('testSet.txt')
	start = time.time()
	b,alphas = smoSimple(dataMat, labelMat, 0.6, 0.001, 40)
	w = get_w(dataMat, labelMat, alphas)
	end = time.time()
	print('finish all in %s' % str(end - start))
	showClassifer(dataMat,labelMat, alphas, w, b)

单独运行svmSimple.py即可。

也可用下面的python文件引用。

'''
文件名：test.py
Created on May 1, 2022
SVM
'''
import svmSimple
import time

dataMat, labelMat = svmSimple.loadDataSet('testSet.txt')
start = time.time()
b,alphas = svmSimple.smoSimple(dataMat, labelMat, 0.6, 0.001, 40)
w = svmSimple.get_w(dataMat, labelMat, alphas)
end = time.time()
print('finish all in %s' % str(end - start))
svmSimple.showClassifer(dataMat,labelMat, alphas, w, b)