『机器学习实战』使用 k-近邻算法改进约会网站的配对效果

算法：

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)
	
	print 'sorted class count: ', sortedClassCount
	
	return sortedClassCount[0][0]
	
	
def file2matrix(filename):
	fr = open(filename)
	arrayOLines = fr.readlines()
	numberOfLines = len(arrayOLines)
	returnMat = zeros((numberOfLines, 3))
	classLabelVector = []
	index = 0
	for line in arrayOLines:
		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))
	
	return normDataSet, ranges, minVals
	
	
def datingClassTest():
	hoRatio = 0.10
	datingDataMat, datingLabels = file2matrix("datingTestSet2.txt")
	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))

		
def classifyPerson():
	resultList = ['not at all', 'in samall doses', 'in large doses']
	percentTats = float(raw_input(\
				"percentage 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]

运行代码：

import kNN_L

group, labels = kNN_L.createDataSet()
print group
print labels

print kNN_L.classify0([0, 0], group, labels, 3)


datingDataMat, datingLabels = kNN_L.file2matrix('datingTestSet2.txt')
print datingDataMat
print datingLabels[0: 20]


import matplotlib
import matplotlib.pyplot as plt

fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2])
plt.show()


normMat, ranges, minVals = kNN_L.autoNorm(datingDataMat)
print normMat

print ranges

print minVals

kNN_L.datingClassTest()

kNN_L.classifyPerson()