- 缺点
时间复杂度高
但这是最简单的机器学习了,基本上有编程能力的,看一眼伪代码就可以写出来
- 伪代码
- 计算已知类别数据集中的点与点之间的距离
- 按照距离递增次序排列
- 选取与当前距离最小的k个点
- 确定前k个点所在类别的出现频率
- 返回前k个点出现频率最高的类别作为预测分类
- python代码实现
def autoNorm(dataSet): #用于归一化
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)) #element wise divide
return normDataSet, ranges, minVals
def file2matrix(filename): #用于将txt文件内的数据转换成矩阵
fr = open(filename)
numberOfLines = len(fr.readlines()) #获得文件的行数
returnMat = zeros((numberOfLines,3)) #准备要返回的numpy矩阵
classLabelVector = [] #准备labels
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
returnMat[index,:] = listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat,classLabelVector
def classify0(inX, dataSet, labels, k): #用于分类 [ 分类的向量,训练集,labels标签,k表示选择邻居的数目 ]
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize,1)) - dataSet
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5 #距离计算 ,欧式距离
sortedDistIndicies = distances.argsort()
classCount={}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1 #选择距离最小的k个点
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
- 数据集样例
14488 7.153469 1.673904 smallDoses
26052 1.441871 0.805124 didntLike
75136 13.147394 0.428964 didntLike