程序清单2-5,
本笔记将主要注意力放在理解代码上,所以大家看代码中的注释即可
伪代码
def classifyPerson():
resultList = ['not at all','in small doses','in large doses']
percentTats = float(input(\
"percentage of time spent playing video games?"))
ffMiles = float(input(\
"frequent flier miles earned per year? "))
iceCream = float(input(\
"liters of ice cream consumed per year?"))
datingDataMat,datingLabels = file2matrix('datingTestSet.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = array([ffMiles, percentTats, iceCream])
clssifierResult = classify0((inArr-minVals)/ranges,\
normMat,datingLabels,3)
print("You will probably like this person:",\
resultList[clssifierResult-1])
完整
#批量注释、批量取消注释 Ctrl+/
# from __future__ import print_function
from numpy import *
import operator#运算符模块
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
group,labels=createDataSet()
def classify0(inX, dataSet, labels, k): #inX: 待测试数据 ; dataSet: 训练样本集;labels: 样本集的标签;k近邻
dataSetSize = dataSet.shape[0] #to get the rows of the matrix
# to get the Xi-Yi of the dataSet
diffMat = tile(inX, (dataSetSize,1)) - dataSet #a=[1 2],b=[2 3];tile(a,b) to generate 2*3 matrix when
#the element all is a [1 2]
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1) #使每行的元素相加,得到测试样本与各训练样本distance**2
#axis=0,按列相加;axis=1,按行相加;
distances = sqDistances**0.5
sortedDistIndicies = distances.argsort() #将distance中的元素从小到大排列,
# 提取其对应的index(索引),然后输出到 sortedDistIndicies
#声明一个dict:{key:value1,key2:value2}
classCount={}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
#classCount= {'B': 2, 'A': 1},初始化后,classCount每得到一个相同的voteIlabel,就+1
classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1 #当我们获取字典里的值的时候,一个是通过
# 键值对,即dict['key'],另一个就是dict.get()方法
# dict.get(voteIlabel,0) = 0, 此处0 to be initiated,
# 之后就没有作用了。
#items方法是可以将字典中的所有项,以列表方式返回。 iteritems方法与items方法相比作用大致相同,只是它的返回值不是列表,而是一个迭代器
#Python3 中没有iteritems函数,需要用values()代替,并用list转为列表
# sortedClassCount = sorted((key_label, value_num), key=operator.itemgetter(1), reverse=True)
#python3中无法使用iteritems,需要对上面这句话改造,我们通过得到两个list,得到出现频率最高的label
key_label=list(classCount.keys())
value_num=list(classCount.values())
#label出现频率由小到大排列,并返回索引index
sortedvalue_num_indicies = argsort(value_num)
#返回频率最大的label
return key_label[len(sortedvalue_num_indicies)-1]
# group,labels = createDataSet()
# a=classify0([0,0], group,labels,3)
# print(a)
#自己根据Python3 改正后的函数
def file2matrix(filename): # 将数据分离为样本数据与标签
#open a file, default: 'r'ead
fr = open(filename)
#一次读取所有行
arrayOLines = fr.readlines()
#得到行数
numberOfLines = len(arrayOLines)
#1000*3 zeros matrix,row-1000, column-3
returnMat = zeros((numberOfLines,3))
#声明
classLabelVector = []
classLabelVector_Value = []
index = 0
#逐行扫描
for line in arrayOLines:
#strip函数会删除头和尾的字符,中间的不会删除
line = line.strip()
#删除‘\t’字符,仅剩下数据,供使用
listFromLine = line.split('\t')
#得到前三列数据,即飞行时间,游戏,冰激凌
returnMat[index, :] = listFromLine[0:3]
#得到largeDoses,smallDoses,didntLike的label
classLabelVector.append(listFromLine[-1]) #无法将largeDoses,smallDoses,didntLike
#转换为int。基于这个思想,我们在这里将得到的行矩阵建立
#一个数值矩阵与之对应,暂时这样处理,不合适再继续修改
if classLabelVector[index] == 'largeDoses':
classLabelVector_Value.append(3)
elif classLabelVector[index] == 'smallDoses':
classLabelVector_Value.append(2)
else:
classLabelVector_Value.append(1)
index += 1
return returnMat, classLabelVector_Value
# def file2matrix(filename):
# fr = open(filename)
# numberOfLines = len(fr.readlines()) #get the number of lines in the file
# returnMat = zeros((numberOfLines,3)) #prepare matrix to return
# classLabelVector = [] #prepare labels return
# fr = open(filename)
# index = 0
# for line in fr.readlines():
# line = line.strip()
# listFromLine = line.split('\t')
# returnMat[index,:] = listFromLine[0:3]
# classLabelVector.append(int(listFromLine[-1]))
# index += 1
# return returnMat,classLabelVector
def autoNorm(dataSet):#得到归一化后的数据样本,最大值最小值之差,与最小值
#得到每一列的max,min
minVals = dataSet.min(0)
maxVals = dataSet.max(0)
ranges = maxVals - minVals
#initiate a zero-matrix like dataSet's shape
normDataSet = zeros(shape(dataSet))
#get the num of row in dataSet
m = dataSet.shape[0]
#init a matrix of minvals that the same rows to the dataSet, 从而使当前数据矩阵中的每个数减去最小值
normDataSet = dataSet - tile(minVals, (m,1)) #tile(matrixlike,A) :init a matrix when the shape is same to A
#meanwhile, if A is a number, the matrix is A*1, if A is (m,n),the matrix
#is m*n matrix
normDataSet = normDataSet/tile(ranges, (m,1)) #element wise divide
return normDataSet, ranges, minVals
def datingClassTest():
#使用10%的数据去测试分类器
hoRatio = 0.10 # hold out 10%
#datingTestSet2.txt中标签全部变为3,2,1,而不是字符串label,所以如果不想改file2matrix()函数,应用datingTestSet.txt
#如果file2matrix()用书中原程序,可用datingTestSet.txt
datingDataMat, datingLabels = file2matrix('datingTestSet.txt') # 将数据分离为样本数据与标签
normMat, ranges, minVals = autoNorm(datingDataMat)#得到归一化后的数据样本,最大值最小值之差,与最小值
#get the num of the row
m = normMat.shape[0]
#get the test num of normMat
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
#数据前numTestVecs个为测试数据,以后为样本训练集
classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :], datingLabels[numTestVecs:m], 3) # inX: 待测试数据 ; dataSet: 训练样本集;labels: 样本集的标签;k近邻
#测试结果与真正结果对照输出
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)))
print(errorCount)
def classifyPerson():
resultList = ['not at all','in small doses','in large doses']
percentTats = float(input(\
"percentage of time spent playing video games?"))
ffMiles = float(input(\
"frequent flier miles earned per year? "))
iceCream = float(input(\
"liters of ice cream consumed per year?"))
datingDataMat,datingLabels = file2matrix('datingTestSet.txt')
normMat, ranges, minVals = autoNorm(datingDataMat)
inArr = array([ffMiles, percentTats, iceCream])
clssifierResult = classify0((inArr-minVals)/ranges,\
normMat,datingLabels,3)
print("You will probably like this person:",\
resultList[clssifierResult-1])
测试
classifyPerson()
完成!