机器学习 k-近邻算法
2016-09-11 20:34
417 查看
简单的按照例子实现的一个demo,慢慢学习吧!
from numpy import *
import operator
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):
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize,1)) - dataSet
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
sortedDistIndicies = distances.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]
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):
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)) #element wise divide
return normDataSet, ranges, minVals
def datingClassTest():
hoRatio = 0.50 #hold out 10%
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt') #load data setfrom file
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
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))
print errorCount
def classifyPerson():
resultList=['not at all','in small doses','in large doses']
percentTats = float(raw_input(\
"precentage of time spent playing video games?"))
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,percentTats,iceCream])
classifierResult =classify0((inArr-\
minVals)/ranges,normMat,datingLabels,3)
print "You will probably like this person : ",\
resultList[classifierResult-1]
from numpy import *
import operator
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):
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize,1)) - dataSet
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
sortedDistIndicies = distances.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]
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):
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)) #element wise divide
return normDataSet, ranges, minVals
def datingClassTest():
hoRatio = 0.50 #hold out 10%
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt') #load data setfrom file
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
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))
print errorCount
def classifyPerson():
resultList=['not at all','in small doses','in large doses']
percentTats = float(raw_input(\
"precentage of time spent playing video games?"))
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,percentTats,iceCream])
classifierResult =classify0((inArr-\
minVals)/ranges,normMat,datingLabels,3)
print "You will probably like this person : ",\
resultList[classifierResult-1]
相关文章推荐
- 机器学习之K-近邻算法(kNN算法)
- 机器学习实战 - K-近邻算法
- 机器学习实战之k-近邻算法(7)---算法总结
- 机器学习实战--最简单算法--KNN算法(k-近邻算法)
- 机器学习实战之近邻算法kNN
- Python 学习笔记(Machine Learning In Action)K-近邻算法(KNN)机器学习实战
- 机器学习实战之k-近邻算法(4)--- 如何归一化数据
- 机器学习实战之k-近邻算法(3)---如何可视化数据
- 机器学习实战 k-近邻算法
- 机器学习实战——使用K-近邻算法进行约会配对
- 机器学习笔记--K-近邻算法(二)
- 机器学习实战学习笔记 一 k-近邻算法
- 机器学习实战之k-近邻算法(5)--- 完整版约会网站数据分类
- 机器学习实战笔记之二(k-近邻算法)
- 机器学习实战——使用K-近邻算法识别手写数字
- 机器学习实战(第2章 k-近邻算法)
- 机器学习实战——K-近邻算法【2:改进约会网站配对效果】
- 机器学习实战-第2章(k-近邻算法)
- 机器学习实战之k-近邻算法(2)---python简单版
- 机器学习实战2.2示例: 使用k-近邻算法改进约会网站的配对效果