Machine Learning in Action_CH2_1_kNN

最新推荐文章于 2021-03-27 12:12:29 发布

Eminem1147

最新推荐文章于 2021-03-27 12:12:29 发布

阅读量259

点赞数 1

分类专栏：机器学习

本文链接：https://blog.csdn.net/qq_33765907/article/details/70245563

版权

机器学习专栏收录该内容

8 篇文章 0 订阅

订阅专栏

from numpy import *
import operator

def createDataBase():
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]]) # numpy向量
    labels = ['A', 'A', 'B', 'B'] # 列表
    return group, labels

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0] # 获得向量第一维长度
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet # 纵向扩大dataSetSize倍
    sqDiffMat = diffMat ** 2
    sqDistances = sqDiffMat.sum(axis = 1) # 按行求和
    distances = sqDistances ** 0.5
    sortedDistIndicies = distances.argsort() # 从小到大排序，返回的是索引值的列表
    classCount = {} # python字典
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1 # 数频度，每次加1
    # 对字典进行排序
    # Python 2 才能使用classCount.iteritems()
    sortedClassCount = sorted(classCount.items(), key = operator.itemgetter(1), reverse = True)
    return sortedClassCount[0][0]

if __name__ == '__main__':
    # arr = array([[1, 2, 3, 4], [5, 6, 7, 8]])
    # print(arr.shape)
    # matrix = mat(arr)
    # print(matrix.shape)

    # print(array([[1, 2],[3, 4]]))
    # print(array([(1, 2), (3, 4)]))
    # a = array([1, 2])
    # print(a.dtype)

    # a = [1, 2, 3, 4]
    # print(tile(a, 2))

    group, labels = createDataBase()
    print(classify0([0, 0], group, labels, 3)) # 输出B