其中是由d维属性描述的样本,其中 xi 是 x 在第 i 个属性上的取值。
线性回归模型:f(x)=wx+b,取合适的w,b值,使得预测值逼近真实标记 y
Logistic Regression的目的 :虽然名字上称之回归,但其本质是一个分类算法。
Logistic Regression的本质:Logistic Regression属于判别式模型。它是在线性回归的基础上使用sigmoid函数将线性模型压缩到[0,1]之间,实其具备概率意义。
Logistic Regression的损失函数:当通过sigmoid函数获得分类预测值后,我们通过损失函数来参与logistic模型的优化。
测试数据是二维的,共100个样本,有2个类
如下:
-0.017612 14.053064 0
-1.395634 4.662541 1
-0.752157 6.538620 0
-1.322371 7.152853 0
0.423363 11.054677 0
0.406704 7.067335 1
0.667394 12.741452 0
-2.460150 6.866805 1
0.569411 9.548755 0
-0.026632 10.427743 0
0.850433 6.920334 1
1.347183 13.175500 0
1.176813 3.167020 1
-1.781871 9.097953 0
-0.566606 5.749003 1
0.931635 1.589505 1
-0.024205 6.151823 1
-0.036453 2.690988 1
-0.196949 0.444165 1
1.014459 5.754399 1
1.985298 3.230619 1
-1.693453 -0.557540 1
-0.576525 11.778922 0
-0.346811 -1.678730 1
-2.124484 2.672471 1
1.217916 9.597015 0
-0.733928 9.098687 0
-3.642001 -1.618087 1
0.315985 3.523953 1
1.416614 9.619232 0
-0.386323 3.989286 1
0.556921 8.294984 1
1.224863 11.587360 0
-1.347803 -2.406051 1
1.196604 4.951851 1
0.275221 9.543647 0
0.470575 9.332488 0
-1.889567 9.542662 0
-1.527893 12.150579 0
-1.185247 11.309318 0
-0.445678 3.297303 1
1.042222 6.105155 1
-0.618787 10.320986 0
1.152083 0.548467 1
0.828534 2.676045 1
-1.237728 10.549033 0
-0.683565 -2.166125 1
0.229456 5.921938 1
-0.959885 11.555336 0
0.492911 10.993324 0
0.184992 8.721488 0
-0.355715 10.325976 0
-0.397822 8.058397 0
0.824839 13.730343 0
1.507278 5.027866 1
0.099671 6.835839 1
-0.344008 10.717485 0
1.785928 7.718645 1
-0.918801 11.560217 0
-0.364009 4.747300 1
-0.841722 4.119083 1
0.490426 1.960539 1
-0.007194 9.075792 0
0.356107 12.447863 0
0.342578 12.281162 0
-0.810823 -1.466018 1
2.530777 6.476801 1
1.296683 11.607559 0
0.475487 12.040035 0
-0.783277 11.009725 0
0.074798 11.023650 0
-1.337472 0.468339 1
-0.102781 13.763651 0
-0.147324 2.874846 1
0.518389 9.887035 0
1.015399 7.571882 0
-1.658086 -0.027255 1
1.319944 2.171228 1
2.056216 5.019981 1
-0.851633 4.375691 1
-1.510047 6.061992 0
-1.076637 -3.181888 1
1.821096 10.283990 0
3.010150 8.401766 1
-1.099458 1.688274 1
-0.834872 -1.733869 1
-0.846637 3.849075 1
1.400102 12.628781 0
1.752842 5.468166 1
0.078557 0.059736 1
0.089392 -0.715300 1
1.825662 12.693808 0
0.197445 9.744638 0
0.126117 0.922311 1
-0.679797 1.220530 1
0.677983 2.556666 1
0.761349 10.693862 0
-2.168791 0.143632 1
1.388610 9.341997 0
0.317029 14.739025 0
def loadDataSet(): #读取数据(这里只有两个特征)
dataMat = []
labelMat = []
fr = open(filename)
for line in fr.readlines():
lineArr = line.strip().split()
dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])]) #前面的1,表示方程的常量。比如两个特征X1,X2,共需要三个参数,W1+W2*X1+W3*X2
labelMat.append(int(lineArr[2]))
return dataMat,labelMat
def sigmoid(inX): #sigmoid函数
return 1.0/(1+exp(-inX))
def gradAscent(dataMat, labelMat): #梯度上升求最优参数
dataMatrix=mat(dataMat) #将读取的数据转换为矩阵
classLabels=mat(labelMat).transpose() #将读取的数据转换为矩阵
m,n = shape(dataMatrix)
alpha = 0.001 #设置梯度的阀值,该值越大梯度上升幅度越大
maxCycles = 500 #设置迭代的次数,一般看实际数据进行设定,有些可能200次就够了
weights = ones((n,1)) #设置初始的参数,并都赋默认值为1。注意这里权重以矩阵形式表示三个参数。
for k in range(maxCycles):
h = sigmoid(dataMatrix*weights)
error = (classLabels - h) #求导后差值
weights = weights + alpha * dataMatrix.transpose()* error #迭代更新权重
return weights
from numpy import *
filename='LogisticRegessionSet.txt' #文件目录
def loadDataSet(): #读取数据(这里只有两个特征)
dataMat = []
labelMat = []
fr = open(filename)
for line in fr.readlines():
lineArr = line.strip().split()
dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])]) #前面的1,表示方程的常量。比如两个特征X1,X2,共需要三个参数,W1+W2*X1+W3*X2
labelMat.append(int(lineArr[2]))
return dataMat,labelMat
def sigmoid(inX): #sigmoid函数
return 1.0/(1+exp(-inX))
def gradAscent(dataMat, labelMat): #梯度上升求最优参数
dataMatrix=mat(dataMat) #将读取的数据转换为矩阵
classLabels=mat(labelMat).transpose() #将读取的数据转换为矩阵
m,n = shape(dataMatrix)
alpha = 0.001 #设置梯度的阀值,该值越大梯度上升幅度越大
maxCycles = 500 #设置迭代的次数,一般看实际数据进行设定,有些可能200次就够了
weights = ones((n,1)) #设置初始的参数,并都赋默认值为1。注意这里权重以矩阵形式表示三个参数。
for k in range(maxCycles):
h = sigmoid(dataMatrix*weights)
error = (classLabels - h) #求导后差值
weights = weights + alpha * dataMatrix.transpose()* error #迭代更新权重
return weights
def plotBestFit(weights): #画出最终分类的图
import matplotlib.pyplot as plt
dataMat,labelMat=loadDataSet()
dataArr = array(dataMat)
n = shape(dataArr)[0]
xcord1 = []; ycord1 = []
xcord2 = []; ycord2 = []
for i in range(n):
if int(labelMat[i])== 1:
xcord1.append(dataArr[i,1])
ycord1.append(dataArr[i,2])
else:
xcord2.append(dataArr[i,1])
ycord2.append(dataArr[i,2])
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')
ax.scatter(xcord2, ycord2, s=30, c='green')
x = arange(-3.0, 3.0, 0.1)
y = (-weights[0]-weights[1]*x)/weights[2]
ax.plot(x, y)
plt.xlabel('X1')
plt.ylabel('X2')
plt.show()
def main():
dataMat, labelMat = loadDataSet()
weights=gradAscent(dataMat, labelMat).getA()
plotBestFit(weights)
if __name__=='__main__':
main()