SVM
1.概述
SVM全稱Support_Vector_Machine,即支持向量機,是機器學習中的一種監督學習分類算法,一般用於二分類問題。對於線性可分的二分類問題,SVM可以直接求解,對於非線性可分問題,其也可以通過核函數將低維映射到高維空間從而轉變爲線性可分。對於多分類問題,SVM經過適當的轉換,也能加以解決。相對於傳統的分類算法如logistic迴歸,k近鄰法,決策樹,感知機,高斯判別分析法(GDA)等,SVM尤其獨到的優勢。相對於神經網絡複雜的訓練計算量,SVM在訓練方面較少計算量的同時也能得到很好的訓練效果。
2.問題的提出
考慮一個線性可分的二分類問題
m個訓練樣本
x 是特徵向量,y 是目標變量{x(i),y(i)},x(i)∈Rn,y(i)∈{1,−1},i=1,2,⋯,m
決策函數:hw,b(x)=g(wTx+b),g(z)={1,ifx>00,ifx<0
直線代表wTx+b=0 首先定義一些符號
functional margin(函數邊界)
r^=min{r^(i)},i=1,2,⋯,m;r^(i)=y(i)∗(wTx(i)+b) geometrical margin(幾何邊界)
r=min{r(i)},i=1,2,⋯,m;r(i)=y(i)∗(wTx(i)+b)∥w∥ 符號解釋:
- 函數邊界:由於
y(i) 只能取1,−1 ,所以當wT∗x(i)+b>>0 時,y=1 和y=−1 分別表示點分佈在距離超平面wTx+b=0 兩邊很遠的地方,注意如果加倍w 與x ,函數邊界是會加倍的
- 函數邊界:由於
目標:幾何邊界最大,即
max{r}
3.問題的轉化
依次轉化:
max{r} max{min{r(i)=y(i)∗(wTx(i)+b)∥w∥};i=1,2,⋯,m} ⎧⎩⎨max{r}s.t.y(i)∗(wTx(i)+b)∥w∥≥r {max{r^∥w∥}s.t.y(i)∗(wTx(i)+b)≥r^ - 注意函數邊界的改變不影響優化問題的求解結果
letr^=1
問題轉化爲:
{max{1∥w∥}s.t.y(i)∗(wTx(i)+b)≥1
最終轉化爲optimization problem,而且目標函數是convex的,即凸函數
{min{12w2}s.t.y(i)∗(wTx(i)+b)≥1最終得到優化問題(1)
4.問題求解
(1)可以用通常的QP(二次規劃)方法求解,matlab或lingo都有相應工具箱。
(2)既然本文叫SVM,當然會用到不同的解法,而且SVM的解法在訓練集很大的時候,比一般的QP解法效率高。
廣義拉格朗日數乘法
對於3中得到的優化問題(1)有:
{L(w,b,α)=12w2−∑mi=1α(i)[y(i)∗(wTx(i)+b)−1]α(i)≥0 - 滿足約束條件
y(i)∗(wTx(i)+b)≥1 下有:
max{L(w,b,α)}=1w2=f(w)
- 滿足約束條件
優化問題變爲:
⎧⎩⎨⎪⎪minw,b{maxα{L(w,b,α)}}s.t.y(i)∗(wTx(i)+b)≥1α(i)≥0 在滿足KKT條件下有(對偶優化問題)
minw,b{maxα{L(w,b,α)}}=maxα{minw,b{L(w,b,α)}}
通常對偶問題(dual problem)
max{min{f(w,α)}} 比原始問題(primal problem)min{max{f(w,α)}} 更容易求解,尤其是在訓練樣本數量很大的情況下,KKT條件又稱爲互補鬆弛條件∇w,bL(w¯,b¯,α¯)=0; w¯,b¯是primaloptimal;α¯是dualoptimal α¯(i)gi(w¯,b¯)=0 ,y(i)∗(wTx(i)+b)=1 時,通常有α≠0 ,這些點稱爲Support Vector,即支持向量y(i)∗(wTx(i)+b)>1 時,有α=0 ,通常大多數α 爲0,減少了計算量
解決
minw,b{L(w,b,α)} 求偏導令爲0可得
{w=∑mi=1α(i)y(i)x(i)∑mi=1α(i)y(i)=0 帶入原式:
⎧⎩⎨⎪⎪maxα{∑mi=1α(i)−12∑mi,j=1y(i)y(j)α(i)α(j)<x(i),x(j)>}α(i)≥0∑mi=1α(i)y(i)=0 - 求得
α 則可得到w,b - 目標表示爲
wTx+b=∑mi=1α(i)y(i)<x(i),x>+b kernel(x,y)=<xT,y> 稱爲核函數,能較少高維空間計算量,通常知道了核函數,計算量相對於找對應的x,y 向量小得多,而且若x,y 是無限維向量,也可通過核函數映射。常用的核函數有:
- 高斯核
K(x,z)=exp(−∥z−x∥2σ2) - 多項式核
K(x,z)=(x−z)a
- 高斯核
- 求得
5.問題的優化
4中推導出了求
α 使得最大化的問題。但其存在一定問題。
當訓練集如右圖分佈在超平面兩側時,結果並不好,因此我們可以給
r^=1 添加鬆弛條件,允許少數點小於1,甚至分類到錯誤的一面我們修改限制條件,並修改目標函數
⎧⎩⎨⎪⎪min{12w2+csummi=1ξi}y(i)∗(wTx(i)+b)≥1−ξiξi≥0 通過類似的對偶問題的求解,我們得到
⎧⎩⎨⎪⎪⎪⎪⎪⎪⎪⎪W=maxα{∑mi=1α(i)−12∑mi,j=1y(i)y(j)α(i)α(j)<x(i),x(j)>}0≤α≤c∑mi=1α(i)y(i)=0
6.優化後問題的求解
- 座標上升法求解最大值
#僞代碼
loop {
for i in range(m):
alpha(i):=alpha(i) which let {w} maximum
}
座標上升與梯度上升的對比圖
SMO
#僞代碼
L<=alpha<=H
loop {
for i,j in range(m):
alpha(i):=min{ (alpha(i) or L or H ) which let {w} maximum }
alpha(j):=min{ (alpha(j) or L or H ) which let {w} maximum }
}
7.實戰
- trainsets 總共90組
-0.017612 14.0530640
-1.395634 4.6625411
-0.752157 6.5386200
-1.322371 7.1528530
…………………………
-1.076637 -3.1818881
1.821096 10.2839900
3.010150 8.4017661
-1.099458 1.6882741
-0.834872 -1.7338691
-0.846637 3.8490751
1.400102 12.6287810
1.752842 5.4681661
0.078557 0.0597361 testsets 總共10組
0.089392 -0.7153001
1.825662 12.6938080
0.197445 9.7446380
0.126117 0.9223111
-0.679797 1.2205301
0.677983 2.5566661
0.761349 10.6938620
-2.168791 0.1436321
1.388610 9.3419970
0.317029 14.7390250logistic迴歸效果
- 權值
weight=[[11.93391219][1.12324688][−1.60965531]] - 原始測試文件真值
y=[1.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0] - logistic迴歸預測值:
y1=[1.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0] - 正確率還是蠻高的
- 附上代碼:
- 權值
#!/usr/bin/env
#coding:utf-8
import numpy
import sys
from matplotlib import pyplot
import random
def makedata(filename):
try:
f = open(filename,"r")
lines = f.readlines()
datalist = []
datalist = [i.split() for i in lines ]
datalist = [ [ float(i) for i in line] for line in datalist ]
for i in range(len(datalist)):
datalist[i].insert(0,1.0)
except:
return
finally:
return datalist
f.close()
def makedat(filename):
try:
f = open(filename,"r")
lines = f.readlines()
datalist = []
datalist = [i.split() for i in lines ]
datalist = [ [ float(i) for i in line] for line in datalist ]
x = [ line[0:len(line)-1] for line in datalist ]
y = [ line[-1] for line in datalist ]
except:
return
finally:
return x,y
f.close()
def sigma(z):
return 1.0/(1+numpy.exp(-z))
#batch regression
def logisticFunc(dataset,itertimes,alpha):
weight = numpy.ones((len(dataset[0])-1,1))
value = [ int(i[-1]) for i in dataset ]
value = numpy.mat(value).transpose()
params = [ i[0:-1] for i in dataset ]
params = numpy.mat(params)
for i in range(int(itertimes)):
error = value-sigma(params*weight)
weight = weight+alpha*params.transpose()*error
return weight
#random grad ascend regression
def randLogisticFunc(dataset,itertimes,alpha):
weight = numpy.ones((len(dataset[0])-1,1))
value = [ int(i[-1]) for i in dataset ]
value = numpy.mat(value).transpose()
params = [ i[0:-1] for i in dataset ]
params = numpy.mat(params)
for i in range(int(itertimes)):
randid = random.randint(0,len(dataset)-1)
error = value[randid]-sigma(params[randid]*weight)
weight = weight+alpha*params[randid].transpose()*error
return weight
def plot(data,weight):
x1 = []
x2 = []
y1 = []
y2 = []
for i in data:
if i[-1] == 1:
x1.append(i[1])
y1.append(i[2])
else:
x2.append(i[1])
y2.append(i[2])
x = numpy.linspace(-3,3,1000)
weight = numpy.array(weight)
y = (-weight[0][0]-weight[1][0]*x)/weight[2][0]
fg = pyplot.figure()
sp = fg.add_subplot(111)
sp.scatter(x1,y1,s=30,c="red")
sp.scatter(x2,y2,s=30,c="blue")
sp.plot(x,y)
pyplot.show()
def predict(weight,x1):
yi = []
for i in x1:
if weight[0][0]+i[0]*weight[1][0]+i[1]*weight[2][0]>=0:
yi.append(1)
else:
yi.append(0)
print yi
def main():
trainfile = sys.argv[1]
itertimes = int(sys.argv[2])
alpha = float(sys.argv[3])
testfile = sys.argv[4]
data = makedata(trainfile)
testx,testy = makedat(testfile)
weight = logisticFunc(data,itertimes,alpha)
print weight
predict(weight,testx)
print testy
#weight = randLogisticFunc(data,itertimes,alpha)
#print weight
plot(data,weight)
if __name__=='__main__':
main()
- SVM效果(採用高斯核,使用sklearn庫)
- 原始測試文件真值
y=[1.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0] - svm預測值:
y1=array([1.,0.,0.,1.,1.,1.,0.,1.,0.,0.]) - 正確率也挺高的
- 附上代碼:
- 原始測試文件真值
#!/usr/bin/env python
#coding:utf-8
from sklearn import svm
import sys
def makedata(filename):
try:
f = open(filename,"r")
lines = f.readlines()
datalist = []
datalist = [i.split() for i in lines ]
datalist = [ [ float(i) for i in line] for line in datalist ]
x = [ line[0:len(line)-1] for line in datalist ]
y = [ line[-1] for line in datalist ]
except:
return
finally:
return x,y
f.close()
def learn(x,y):
clf = svm.SVC()
clf.fit(x,y)
return clf
def predict(x1,y1,clf):
print "svm fit results",clf.predict(x1)
print "original test file results",y1
if __name__=="__main__":
inputfile = sys.argv[1]
testfile = sys.argv[2]
x,y = makedata(inputfile)
x1,y1 = makedata(testfile)
clf = learn(x,y)
predict(x1, y1, clf)