完成了最基本的Logistic算法的测试,手写了最简单的随机梯度上升的算法。
并基于写好的算法,利用疝气病症预测了病马的死亡率(即能否存活)
这章的代码比较短,但是由于5.1假期太浪,回来之后才补完。
# -*- coding: utf-8 -*-
"""
照葫芦画瓢完成于2017.5.2 20:30
算法名称 : Logistic回归
算法整体思路:
利用凸优化中的随机梯度上升法来对回归系数进行调优,基于迭代完毕之后的系数,通过sigmoid函数进行分类
然后和实际的分类结果进行比较,可以观察出错误率等相关的东西
注意梯度的数值计算方法的求解
注意随机梯度上升的批处理思想---->实际上就是分块
作者:
zzt941006
"""
from numpy import *
def loadDataSet():
dataMat = []
labelMat = []
fr = open('testSet.txt')
for line in fr.readlines():
lineArr = line.strip().split() #获取测试集中的元素的每一行,并形成一个list
#print lineArr
dataMat.append([1.0,float(lineArr[0]),float(lineArr[1])])#将前2个值单独取出,并在前面均加上1.0这个属性,构成数据矩阵
labelMat.append(int(lineArr[2]))#将最后一列的元素单独取出,构成标签矩阵
return dataMat,labelMat
#sigmoid函数的计算
#原型为 1 / (1 + e ^ -z)
def sigmoid(inX):
return 1.0/(1+exp(-inX))
#Logistic回归梯度上升优化算法
#注意要遍历整个数据集,数据集十分大的时候效率会非常慢
def gradAscent(dataMatIn,classLabels):
dataMatrix = mat(dataMatIn)#将list类型转化为numpy类型,矩阵维度为 100 * 3
labelMat = mat(classLabels).transpose()#同样转化,并转置,变成 100 * 1的格式
m,n = shape(dataMatrix)#获取矩阵行和列
alpha = 0.001#向目标移动的步长
maxCycles = 500#迭代次数
weights = ones((n,1))#初始化权重(回归)矩阵,维度为 3 * 1 并且所有元素都是 1,因为 sigmoid函数中的 z = x * w
#print shape(dataMatrix * weights)
for k in range(maxCycles):
h = sigmoid(dataMatrix * weights) #得到一个100 * 1 维的向量
error = (labelMat - h)#计算标准分类和其进行sigmoid操作后的差
weights = weights + alpha * dataMatrix.transpose() * error # 注意这里 dataMatrix.transpose() * error 实际上计算的就是基于当前
# weight的梯度,只不过这是数值计算梯度的方法
return weights
#画出数据集和Logistic回归最佳拟合直线的函数
def plotBestFit(weights):
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()
#随机梯度上升,一次仅用一个样本点来更新整体的回归系数
#随机梯度上升是一个在线学习的算法,一次处理所有数据称为批处理
#即分块来做更新
def stocGradAscent0(dataMatrix,classLabels):
m,n = shape(dataMatrix)
weights = ones(n)
alpha = 0.01
for i in range(m):
h = sigmoid(sum(dataMatrix[i] * weights))#取每一行的属性来做sigmoid操作,并更新weights
error = classLabels[i] - h
weights = weights + alpha * error * dataMatrix[i]
return weights
#改进的随机梯度上升,通过设置numIter来迭代alpha的值,来进行调优
def stocGradAscent1(dataMatrix,classLabels,numIter = 150):
m,n = shape(dataMatrix)
weights = ones(n)
for j in range(numIter):
dataIndex = range(m)
for i in range(m):
alpha = 4 /(1.0 + j + i) + 0.01#加一个常数,防止alpha降低到0
randIndex = int(random.uniform(0,len(dataIndex)))#随机选取某个样本进行更新,减少周期性波动
h = sigmoid(sum(dataMatrix[randIndex] * weights))
error = classLabels[randIndex] - h
weights = weights + alpha * error * dataMatrix[randIndex]
del(dataIndex[randIndex])
return weights
#分类函数,通过sigmoid计算,一旦大于0.5就阶跃到1,反之被分类为0
def classifyVector(inX,weights):
prob = sigmoid(sum(inX * weights))
if prob > 0.5:
return 1.0
else:
return 0.0
#疝气检测
def colicTest():
frTrain = open('horseColicTraining.txt')
frTest = open('horseColicTest.txt')
trainingSet = []
trainingLabels = []
for line in frTrain.readlines():
currLine = line.strip().split('\t')
# print currLine
lineArr = []
for i in range(21):
lineArr.append(float(currLine[i]))
trainingSet.append(lineArr)
trainingLabels.append(float(currLine[21]))#第22列为实际标签
trainWeights = stocGradAscent1(array(trainingSet), trainingLabels, 500)
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
errorRate = (float(errorCount)/numTestVec)
print "the error rate of this test is: %f" % errorRate
return errorRate
#多次试验求平均值
def multiTest():
numTests = 20
errorSum = 0.0
for k in range(numTests):
errorSum += colicTest()
print "after %d iterations the average error rate is: %f" % (numTests,errorSum/(float(numTests)))