python 实现简单的KNN算法

from numpy import *
import operator

def createDataSet():
    group = array([[3,104],[2,100],[1,81],[101,10],[99,5],[98,2]])
    labels = ['爱情片','爱情片','爱情片','动作片','动作片','动作片']
    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.items(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]

group,labels = createDataSet()
print(classify0([500,90],group,labels,3))

 使用错误率来检验算法 

from numpy import *

import matplotlib
import matplotlib.pyplot as plt 
import operator

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))
    # print(shape(dataSet))
    # print(normDataSet)
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals,(m,1))
    normDataSet = normDataSet / tile(ranges,(m,1))
    return normDataSet, ranges, minVals


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.items(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]


def datingClassTest():
    hoRatio = 0.10
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    # print(m)
    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)))
datingClassTest()

 数据集下载：https://i.cnblogs.com/Files.aspx  

datingTestSet2.rar