【读书笔记】机器学习实战-2.3节

机器学习实战

#!/usr/bin/python
# -*- coding: utf-8 -*-
from numpy import *
import operator
from os import listdir
import matplotlib
import matplotlib.pyplot as plt

def createDataSet():
group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
labels = ['A','A','B','B']
return group ,labels

def classify0( inX,dataSet,labels,k ):                 # 待判定输入，训练样本，样本标签，kNN中k的取值
dataSetSize = dataSet.shape[0]                      # shape 返回矩阵的维度
diffMat = tile(inX, (dataSetSize, 1)) - dataSet     # tile(a,b)：将a重复b次
saDiffMat = diffMat**2                              # 运算符模块：** 平方
sqDistances = saDiffMat.sum(axis=1)                 # axis=1： array按行求和   axis=0：array按列求和
distances = sqDistances**0.5
sortedDistIndicies = distances.argsort()            # 返回数组值从大到小的索引值
classCount = {}
for i in range(k):
voteIlabel  = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1   # dic.get()  访问不存在的键时，自动添加并设值为默认值
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)  # dic.iteritems() :迭代器函数  operator.itemgetter()：获取对象的指定域的值  key:进行比较的关键字
return sortedClassCount[0][0]

def file2matrix(filename):
fr = open(filename)
arrayOLines = fr.readlines()                        # 将文件全部读入字符串列表,每个字符串为一行
numberOfLines = len(arrayOLines)
returnMat = zeros((numberOfLines,3))                # numpy.zeros() 创建零矩阵
classLabelVector = []
index = 0
for line in arrayOLines:
line = line.strip()                             # 除去两边的空格
listFromLine = line.split('\t')                 # '\t' = Tab  split:拆解字符串
returnMat[index ,:] = listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))  # 列表添加元素
index += 1
return returnMat, classLabelVector

def autoNorm(dataSet):
minVals = dataSet.min(0)    # numpy.array.min(0) 返回每列的最小值
maxVals = dataSet.max(0)    # numpy.array.max(0) 返回每列的最大值
ranges = maxVals - minVals
# normDataSet = zeros(dataSet.shape)  # 利用shape属性，建同样大小的矩阵
m = dataSet.shape[0]
normDataSet = dataSet - tile(minVals, (m, 1))   # array全部减去最小值
normDataSet = normDataSet/tile(ranges, (m, 1))  # array全部除去范围值
return normDataSet, ranges, minVals

def datingClassTest():
hoRatio = 0.1                 # 测试样例比例
datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)  # 测试数据集
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = classify0(normMat[i,:], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m],3)
print "the classifier came back with: %d,the real answer is:%d" %(classifierResult, datingLabels[i])
if(classifierResult != datingLabels[i]):
errorCount += 1.0
print "the total error rate is :%f" %(errorCount/float(numTestVecs))

def classifyPerson():
resultList = ['not at all ','in small doses ','in large doses ']
percetTates = float(raw_input('percent of time spent playing video game?'))
ffMiles = float(raw_input('frequent flier miles earned per year?'))
iceCream = float(raw_input('liters of ice cream consumed per year?'))
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = array([ffMiles,percetTates,iceCream]) # 构建分类目标array
inArr = (inArr-minVals)/ranges
classifierResult = classify0(inArr, normMat,datingLabels,3)
print 'you will like this person:',resultList[classifierResult-1]

def img2vector(filename):
returnVect = zeros(1024)
fr = open(filename)
for i in range(32):
lineStr = fr.readline()
for j in range(32):
returnVect[32*i+j] = int(lineStr[j])  # 字符转数字
return returnVect

def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('trainingDigits')  # 获取训练目录文件内容
m = len(trainingFileList)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList[i]         # 当前解析文件
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])  # 获取真实标签
hwLabels.append(classNumStr)
trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('testDigits')          # 获取测试数据样本
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0]     #take off .txt
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
print "the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr)
if (classifierResult != classNumStr): errorCount += 1.0
print "\nthe total number of errors is: %d" % errorCount
print "\nthe total error rate is: %f" % (errorCount/float(mTest))

handwritingClassTest()
# classifyPerson()
# datingClassTest()

# datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')

# normMat,ranges,minVals = autoNorm(datingDataMat)

# fig = plt.figure()
# ax = fig.add_subplot(111)
# ax.scatter(datingDataMat[:, 0], datingDataMat[:, 1], 15.0*array(datingLabels),15.0*array(datingLabels))  # 利用标签属性标记
# fig.show() 显示后自动退出
# plt.show()  #显示不退出

#group,labels = createDataSet()
#result = classify0([0,0],group,labels,3)
#pass