K-邻近算法

导入的包

coding=UTF8
from numpy import *
import operator
from os import listdir
import matplotlib
import matplotlib.pyplot as plt

判断数据是哪一个类型

def classify0(inX, dataset, labels, k):

dataSetSize = dataset.shape[0]
diffMat = tile(inX, (dataSetSize, 1)) - dataset
sqDiffMat = diffMat ** 2
sqDistance = sqDiffMat.sum(axis=1)
distance = sqDistance ** 0.5
sortedDistIndicies = distance.argsort()
classCount = {}

for i in range(k):
    voteIlabel = labels[sortedDistIndicies[i]]
    classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]

数据预处理

def file2matrix(filename):
fr = open(filename)
arrayOLines=fr.readlines()
numberOfLines = len(arrayOLines)         #获取 n=样本的行数,1000个样本
returnMat = zeros((numberOfLines,4))        #创建一个2维矩阵用于存放训练样本数据，一共有n行，每一行存放3个数据
classLabelVector = []                       #创建一个1维数组用于存放训练样本标签。
classLabelVectortou = []
index = 0
for line in arrayOLines:
    # 把回车符号给去掉,头尾空白去掉
    line = line.strip()
    # 把每一行数据用\t分割
    listFromLine = line.split('\t')
    # 把分割好的数据放至数据集，其中index是该样本数据的下标，就是放到第几行
    returnMat[index,:] = listFromLine[1:5]
    # 把该样本对应的标签放至标签集，顺序与样本集对应。
    classLabelVector.append(int(listFromLine[-1]))#每行的最后一个下标位置数据是类型
    classLabelVectortou.append(int(listFromLine[0]))
    index += 1
return returnMat,classLabelVector

测试数据预处理

def file3matrix(filename):
"""
从文件中读入训练数据，并存储为矩阵
"""
fr = open(filename)
arrayOLines=fr.readlines()
numberOfLines = len(arrayOLines)         #获取 n=样本的行数,1000个样本
returnMat = zeros((numberOfLines,4))        #创建一个2维矩阵用于存放训练样本数据，一共有n行，每一行存放3个数据
classLabelVector = []                       #创建一个1维数组用于存放训练样本标签。
classLabelVectortou = []
index = 0
for line in arrayOLines:
    # 把回车符号给去掉,头尾空白去掉
    line = line.strip()
    # 把每一行数据用\t分割
    listFromLine = line.split('\t')
    # 把分割好的数据放至数据集，其中index是该样本数据的下标，就是放到第几行
    returnMat[index,:] = listFromLine[1:5]
    # 把该样本对应的标签放至标签集，顺序与样本集对应。
    classLabelVector.append(int(listFromLine[-1]))#每行的最后一个下标位置数据是类型
    classLabelVectortou.append(int(listFromLine[0]))
    index += 1
return returnMat

数据显示图像

def pictureshow(datingDataMat):
datingDataMat1=[]
datingDataMat1=datingDataMat
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1], datingDataMat[:,2],30.0*array(datingLabels), 15.0*array(datingLabels))
ax.axis([-2,25,-0.2,2.0])
plt.xlabel('Percentage of Time Spent Playing Video Games')
plt.ylabel('Liters of Ice Cream Consumed Per Week')
plt.show()

数据归一化

def autoNorm(dataSet):
minVals = dataSet.min(0)
maxVals = dataSet.max(0)
ranges = maxVals - minVals
normDataSet = zeros(shape(dataSet))
m = dataSet.shape[0]
normDataSet = dataSet - tile(minVals, (m,1))
normDataSet = normDataSet/tile(ranges, (m,1))
return normDataSet, ranges, minVals

计算错误率

def datingClassTest():
# 将数据集中10%的数据留作测试用，其余的90%用于训练
hoRatio = 0.8
datingDataMat,datingLabels = file2matrix('D:\MachingLearning\KNN\machingKNN1.0\draining1.txt')       #load data setfrom file
print datingDataMat
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
errorCount = 0.0
#print normMat[0],normMat[0,:],normMat[0,:1],normMat[0,:2]
#normMat[0]代表list中的下标0，normMat[0,:]代表嵌套list的外部下标0，normMat[0,:1]代表嵌套list下标0的同时，截取下标1前面的数
for i in range(numTestVecs):
    classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],4)
    #print "the classifier came back with: %d, the real answer is: %d, result is :%s" % (classifierResult, datingLabels[i],classifierResult==datingLabels[i])
    if (classifierResult != datingLabels[i]):
        errorCount += 1.0
print numTestVecs
print "the total error rate is: %f" % (1-errorCount/float(numTestVecs))
print errorCount

判断输入数据

def classifyPerson():
a=0
b=0
c=0
resultList=['not','pai','pay']
datingDataMat,datingLabels=file2matrix('D:\MachingLearning\KNN\machingKNN1.0\draining1.txt')
print datingDataMat
normMat,ranges,minVals=autoNorm(datingDataMat)
datingDataMat1=file3matrix('D:\MachingLearning\KNN\machingKNN1.0\dest1.txt')
normMat1,ranges1,minVals1=autoNorm(datingDataMat1)
print len(normMat1)
for i in range(len(normMat1)):
    classifierResult=classify0((normMat1[i]-minVals)/ranges,normMat,datingLabels,5)
    #print "result:",resultList[classifierResult-1]
    if resultList[classifierResult-1]=='pai':
        a+=1
    if resultList[classifierResult-1]=='pay':
        b+=1
    if resultList[classifierResult-1]=='not':
        c+=1
print 'pai=',a
print 'pay=',b
print 'not=',c
#return resultList[classifierResult-1]
return a

函数调用

if __name__=="__main__":
datingDataMat,datingLabels=file2matrix('D:\MachingLearning\KNN\machingKNN1.0\draining.txt')
pictureshow(datingDataMat)
#autoNorm(datingDataMat)
#datingClassTest()
classifyPerson()