2.1.2(kNN分类算法)

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0] #1
    diffMat = tile(inX, (dataSetSize,1)) - dataSet#2
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1) #3
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort() #4
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True) #5
    return sortedClassCount[0][0]

1 dataSetSize = dataSet.shape[0] #返回向量的行数

>>> dataSet=array([[1,2],[2,3],[3,4]])
>>> dataSet.shape
(3L, 2L)
>>> dataSet.shape[0]
3L

2 tile(inX, (dataSetSize,1))

>>>inX
[5,6]
>>> tile(inX,(dataSet.shape[0],1))
array([[5, 6],
       [5, 6],
       [5, 6]])
>>> tile(inX,(dataSet.shape[0],3))
array([[5, 6, 5, 6, 5, 6],
       [5, 6, 5, 6, 5, 6],
       [5, 6, 5, 6, 5, 6]])

3 sqDiffMat.sum(axis=1)

>>> sqDiffMat
array([[0.25, 0.36],
       [0.25, 0.25],
       [0.25, 0.25],
       [0.25, 0.16]])
>>> sqDistances=sqDiffMat.sum(axis=1)
>>> sqDistances
array([0.61, 0.5 , 0.5 , 0.41])

4 distances.argsort()

>>> dataSet.argsort()
array([0, 4, 3, 1, 2], dtype=int64)
>>> dataSet=array([2,6,8,4,3])
>>> dataSet.argsort()
array([0, 4, 3, 1, 2], dtype=int64)
>>> dataSet[dataSet.argsort()]
array([2, 3, 4, 6, 8])

5 sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)

https://blog.csdn.net/vivian_ll/article/details/78647979