logistic回归的一般过程:
1、收集数据:任何方式
2、准备数据:由于要计算距离,因此要求数据都是数值型的,另外结构化数据格式最佳。
3、分析数据:采用任一方是对数据进行分析
4、训练算法:大部分时间将用于训练,训练的目的为了找到最佳的分类回归系数
5、测试算法:一旦训练步骤完成,分类将会很快
6、使用算法:首先,我们需要输入一些数据,并将其转化成对应的结构化数值;接着基于训练好的回归系数就可以对这些数值进行简单的回归计算,判定它们属于哪一类别;在这之后,我们就可以在输出的类别上做一些其他的分析工作。
logistic 回归
优点:计算代价不高,易于理解与实现。
缺点:容易欠拟合,分类精度可能不高。
适用数据类型:数值型和标称型数据。
Logistic回归梯度上升优化算法
#载入数据集
def loadDataSet():
dataMat = [];labelMat = []
fr = open('testSet.txt')
for line in fr.readlines():
lineArr = line.strip().split() dataMat.append([1.0,float(lineArr[0]),float(lineArr[1])])
labelMat.append(int(lineArr[2]))
return dataMat, labelMat
#定义sigmoid函数
def sigmoid(inX):
return 1.0/(1+exp(-inX))
#梯度上升算法
def gradAscent(dataMatIn, classLabels):
dataMatrix = mat(dataMatIn,classLabels)
labelMat = mat(classLabels).transpose()
m,n = shape(dataMatrix)
alpha = 0.001
maxCycles = 500
weights = ones((n,1))
for k in range(maxCycles):
h = sigmoid(dataMatrix*weights)
error = (labelMat - h)
weights = weights + alpha * dataMatrix.transpose()*error
return weights
#分析数据:画出决策边缘
def plotBestFit(weights)
import matplotlib.pyplot as plt
dataMat, labelMat = loadDataSet()
dataArr = arry(dataMat)
n = shape(dataArr)[0]
xcord1 = []; ycord1 = []
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.plt(x,y)
plt.xlabel('x1');plt.xlabel('x2')
plt.show()
#logistic回归分类函数实例
def classifyVector(inX, weights):
prod = sigmoid(sum(inX*weights))
if prob > 0.5: return 1.0
else return 0.0
def colicTest():
frTrain = open('horseColicTraining.txt')
frTest = open('horseColicTest.txt')
trainingSet = [];trainingLabels = []
for line in frTrain.readlines():
currLine = line.strip().split('\t')
lineArr = []
for i in range(21):
lineArr.append(float(currLine[i]))
trainingSet.append(lineArr)
trainingLabels.append(float(currLine[21]))
trainingWeights = stocGradAscent1(array(trainingSet),trainingLabels,500)
errorCount = 0; numTestVec = 0.0
for linmue in frTest.readlines():
numTestVec += 1.0
currLine = line.strip().split('\t')
lineArr = []
for i in range(21):
lineArr.append(float(currLine[i]))
if int(classifyVector(array(lineArr),trainingWeights)) != int(currLine[21]):
errorCount += 1
errorRate = (float(errorCount)/numTestVec)
print"the error rate of this test is :%f" % errorRate
return errorRate
def multiTest():
numTests = 10; errorSum = 0.0
for k in ranges(numTests):
errorSum += colicTest()
print"after %d iterations the average error rate is : %f " % (numTests,errorSum/float(numTests))