最近在自学机器学习,应导师要求,先把《Machine Learning with R》动手刷了一遍,感觉R真不能算是一门计算机语言,感觉也就是一个功能复杂的计算器。所以这次就决定使用经典教材《Machine Learning in action》。因为开学得换work station ,怕到时候代码又丢了,所以就索性开个博客,把代码上传上来。
因为书上的原代码有很多错误,并且网上的许多博客的代码也是没有改正的,这次我把修正过的代码po上来
version:python3.5
talk is cheap show me the code
函数定义代码
#coding=utf-8
from numpy import *
def loadDataSet():
dataMat = []
labelMat = []
fr = open("testSet.txt")
lines = fr.readlines()
for line in lines :
lineArr = line.strip().split()
#第一个特征为固定为 1
dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
labelMat.append(int(lineArr[2]))
return dataMat, labelMat
def sigmoid(inX):
sig = 1.0/(1 + exp(-inX))
return sig
def gradAscent(dataMatIn , classMatIn):
dataMatrix = mat(dataMatIn)
labelMat = mat(classMatIn).transpose()
m, n = shape(dataMatrix)
alpha = 0.01
maxCycle = 500
weights = ones((n, 1))
for k in range(maxCycle):
h = sigmoid(dataMatrix * weights)
error = (labelMat - h)
weights = weights + alpha * dataMatrix.transpose() * error
return weights
def plotBestFit(wei):
import matplotlib.pyplot as plt
weights = wei
#weights = wei.getA()
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)
#最佳拟合直线
y = (-weights[0] - weights[1] * x )/weights[2]
ax.plot(x, y)
plt.xlabel("X1"); plt.ylabel("X2")
plt.show()
def stocGradAscent0(dataMatrix, classLabels):
m, n = shape(dataMatrix)
alpha = 0.01
weights = ones(n)
for i in range(m):
h = sigmoid(sum(dataMatrix[i] * weights))
error = classLabels[i] - h
weights = weights + alpha * error * dataMatrix[i]
return weights
def stocGradAscent1(dataMatrix, classLabels, numIter = 150 ):
m, n = shape(dataMatrix)
weights = ones(n)
for j in range(numIter):
dataIndex = list(range(m))
for i in range(m):
alpha = 4/(10.+i+j) +0.01
randIndex = int(random.uniform(0, len(dataIndex)))
h = sigmoid(sum(dataMatrix[randIndex] * weights))
#print(type(classLabels[randIndex]))
error = float(classLabels[randIndex]) - h
weights = weights + alpha * error * dataMatrix[dataIndex[randIndex]]
del(dataIndex[randIndex])
return weights
def classifyVector(inX ,weights):
prob = 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(currLine[21])
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
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)))
上面代码块只是定义了主要的函数,离运行还差一点。由于书原文中,采用了使用 iPython 命令行的运行方式,但是博主比较懒,所以干脆舍弃掉原来的方式。
废话不多少,直接上代码
实验1
if __name__=="__main__":
dataArr, labelMat = loadDataSet()
#gradAscent(dataArr, labelMat)
print(gradAscent(dataArr, labelMat))
实验2 :
if __name__ == "__main__":
dataArr, labelMat = loadDataSet()
plotBestFit(gradAscent(dataArr, labelMat))
实验3 :
if __name__ == "__main__":
dataArr, labelMat = loadDataSet()
weights = stocGradAscent0(array(dataArr), labelMat)
plotBestFit(weights)
实验4 :
if __name__ == "__main__":
dataArr, labelMat = loadDataSet()
weights = stocGradAscent1(array(dataArr), labelMat)
plotBestFit(weights)
实验5 :
if __name__ == "__main__":
multiTest()
更多请戳github
https://github.com/Edgis/Machine-learning-in-action/blob/master/logRegres.py