K-近邻算法:
有点:精度高, 对异常值不敏感,无数据输入假定。
缺点:计算复杂度高,空间复杂度高。
使用范围:数值型和标称型。
python代码:
from numpy import *
def createDataSet():
group = array([[1.0, 1.1], [1.0, 1.0], [0.0, 0.0], [0.0, 0.1]])
labels = ['A', 'A', 'B', 'B']
return group, labels
def classify0(inX, dataSet, labels, k):
dataSize = dataSet.shape[0]
diffMat = tile(inX, (dataSize, 1)) - dataSet
sqDiffMat = diffMat ** 2
sqDistance = sqDiffMat.sum(axis=1)
distance = sqDistance ** 0.5
sortedDistIndicies = distance.argsort()
classCount = {}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
sortedClassSort = sorted(classCount.iteritems(), key=lambda x:x[1], reverse=True)
return sortedClassSort[0][0]