knn 简介

简介

思想就是计算数据集中数据对应的向量和分类向量的欧式距离,最近的k个

优缺点

优点:精度高,对异常数据不敏感
缺点:计算和空间复杂度高

代码来自机器学习实战

from numpy import *
import operator


def classify(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 createDataSet():
    group = array([[1, 1.1], [1, 1], [0, 0], [0, 0.1]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels