[Machine :Learning] kNN近邻算法

from numpy import *
import operator

def createDataSet() :
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 1.1]])
    labels = [‘A‘, ‘A‘, ‘B‘, ‘B‘]
    return group, labels


‘‘‘
    tile(array, (intR, intC): 对矩阵进行组合，纵向复制intR次， 横向复制intC次
    比如 : tile([1,2,3], (3, 2))
    输出
    [
        [1, 2, 3, 1, 2, 3],
        [1, 2, 3, 1, 2, 3],
        [1, 2, 3, 1, 2, 3]
    ]
    array减法， 两个 行列数相等的矩阵，对应位置做减法

    argsort(array, axis) 对矩阵进行排序，axis=0 按列排序， axis=1 按行排序  输出的是排序的索引。比如输出[0,2,1], 排序结果结果为 array[0],array[2].array[1]

    aorted(iteratorItems, key, reverse)  对可迭代的对象进行排序

‘‘‘
def classify0(intX, dataSet, labels, k) :    # 假设输入 intX = [0, 0], dataSet = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 1.1]]), labels = [‘A‘, ‘A‘, ‘B‘, ‘B‘], k = 3
    dataSetSize = dataSet.shape[0];    # 行数 dataSetSize = 4
    diffMat = tile(intX, (dataSetSize, 1)) - dataSet    # 矩阵差  diffMat = array([[-1.0, -1.1], [-1.0, -1.0], [0, 0], [0, -1.1]])
    sqDiffMat = diffMat ** 2    # 平方   sqDiffMat = array([[1, 1.21], [1, 1], [0, 0], [0, 1.21]])
    sqDistances = sqDiffMat.sum(axis=1)    # 行和，axis=0时输出纵和  sqDistances = array([2.21, 2, 0, 1.21])
    distances = sqDistances ** 0.5    # 开平方 distances = array([1.41, 1.48, 0, 1.1])
    sortedDistIndicies = distances.argsort()    # 排序 sortedDistIndicies = array([2, 3, 0, 1])
    classCount = {}
    for i in range(k) :
        voteIlabel = labels[sortedDistIndicies[i]]   
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1    # {label:count}， 取距离最小的三个， 统计label出现的次数，最终 classCount = {‘B‘: 2, ‘A‘: 1}
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)    # 对dict按照v值（distance）进行倒序排序 sortedClassCount = [(‘B‘, 2), (‘A‘, 1)]
    return sortedClassCount[0][0]  # 返回第一个tuple的第一个值，也就是出现次数最高的label， 这里返回‘B’


if __name__ == "__main__":
    group, labels = createDataSet()
    classify0([0, 0], group, labels, 3)