1.k-近鄰算法
# coding=utf-8
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):
# 數(shù)組長(zhǎng)度
dataSetSize = dataSet.shape[0]
# （A-0）（B-0）
diffMat = tile(inX, (dataSetSize, 1)) - dataSet
# （A-0）*2 （B-0）*2
sqDiffMat = diffMat ** 2
# （A - 0）*2 +（B - 0）*2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances ** 0.5
# 得到距離從小到大的索引
sortedDistIndicies = distances.argsort()
classCount = {}
for i in range(k):
# 獲取從小到大的值的標(biāo)簽
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]
group, labels = createDataSet()
classify0([0, 0], group, labels, 3)
