数据描述:
数据集来源 Horse Colic Data Set
数据预处理:
经过缺失值处理以及数据的类别标签整理后,实际使用的特征为20个,类别标签为存活和未存活 1和0
缺失值特征使用0值填充,原因是下面将要使用逻辑回归分类器,零值特征不影响回归系数训练更新(该特征不改变回归系数)
分类器:
逻辑回归分类
参见博文:逻辑回归(LR)--分类
算法的优点是:
缺点:容易欠拟合,分类精度不高
实现的代码:
分类器:
"""
函数说明:逻辑回归分类
Parameters:
inX - 特征向量
weights - 权值系数(回归系数)
Returns:
-
Author:
heda3
Blog:
https://blog.csdn.net/heda3
Modify:
2019-10-04
"""
def classifyVector(inX, weights):
prob = sigmoid(sum(inX*weights))
if prob > 0.5: return 1.0
else: return 0.0
优化算法:
"""
函数说明:随机梯度上升计算(没有迭代次数的)
在线学习算法
涉及的计算都是numpy数组,而之前的梯度上升涉及的都是向量计算为mat--numpy矩阵
Parameters:
dataMatIn - 数据矩阵
classLabels - 类标签
Returns:
weights - 权值系数W
Author:
heda3
Blog:
https://blog.csdn.net/heda3
Modify:
2019-10-04
"""
def stocGradAscent0(dataMatrix, classLabels):
m,n = shape(dataMatrix)
alpha = 0.01
weights = ones(n) #initialize to all ones
for i in range(m):#样本数
h = sigmoid(sum(dataMatrix[i]*weights))#计算每个样本的梯度
error = classLabels[i] - h
weights = weights + alpha * error * dataMatrix[i]
return weights
"""
函数说明:改进的随机梯度上升计算
#aph1值每次迭代变换
#样本点计算梯度随机选择
#
Parameters:
dataMatIn - 数据矩阵
classLabels - 类标签
numIter - 迭代次数
Returns:
weights - 权值系数W
Author:
heda3
Blog:
https://blog.csdn.net/heda3
Modify:
2019-10-04
"""
def stocGradAscent1(dataMatrix, classLabels, numIter=150):
m,n = shape(dataMatrix)#m:样本数 n:特征数
weights = ones(n) #initialize to all ones(特征数)n*1
for j in list(range(numIter)):#迭代次数
dataIndex = list(range(m))
for i in range(m):#样本数
alpha = 4/(1.0+j+i)+0.0001 #apha decreases with iteration, does not
randIndex = int(random.uniform(0,len(dataIndex)))#随机获取索引go to 0 because of the constant
h = sigmoid(sum(dataMatrix[randIndex]*weights))#z=w0x0+w1x1+w2x2+....+wnxn 等价于Z=WTx (1xn*nx1)
error = classLabels[randIndex]-h #实际值和对数几率的差值
weights = weights + alpha * error * dataMatrix[randIndex]#w*=w+a*deltaf(w)
del(dataIndex[randIndex])#使用此次值,下次迭代时不再使用
return weights
数据加载、优化算法训练(计算回归系数)代入上述的分类器、进行分类、计算错误率
from numpy import *
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
"""
函数说明:导入数据集--数据格式化处理--计算回归系数--分类
Modify:
2019-10-04
"""
def colicTest():
##加载训练数据集
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]))
##三种优化算法
#trainWeights = gradAscent(array(trainingSet), trainingLabels)#梯度上升
#trainWeights = stocGradAscent0(array(trainingSet), trainingLabels)#随机梯度上升
trainWeights = stocGradAscent1(array(trainingSet), trainingLabels, 1000)#随机梯度上升的改进
#plotBestFit(trainWeights)#画出决策边界
##逐个样本的加载测试集---并分类
errorCount = 0; numTestVec = 0.0
for line 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), trainWeights))!= int(currLine[21]):
errorCount += 1#统计分类错误的个数
##计算错误率
errorRate = (float(errorCount)/numTestVec)
print("the error rate of this test is: %f" % errorRate)
return errorRate
"""
函数说明:结果平均值的计算
Modify:
2019-10-04
"""
def multiTest():
numTests = 10; errorSum=0.0
for k in range(numTests):
errorSum += colicTest()
print("after %d iterations the average error rate is: %f" % (numTests, errorSum/float(numTests)))