机器学习-从kNN开始

import numpy as np

import operator

def createDataSet():
#数据集
    group = np.array([[1.0,1.1],
                    [1.0,1.0],
                    [0,0],
                    [0,0.1]])
    #标签
    labels = ['A','A','B','B']
    return group, labels

def classify0(inX, dataSet, labels, k):
    #数据集的行数，即数据量
    dataSetSize = dataSet.shape[0]
    #np.tile(a,b):重复a数据b次，eg:np.tile([1,0],3),输出array([1, 0, 1, 0, 1, 0])
    diffMat = np.tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat ** 2
    #.sum(axis):axis =1 是按行相加，axis = 0是按列相加
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances ** 0.5

    #返回distance从小到大的索引值
    sortedDistIndicies = distances.argsort()

    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        #各种类型的个数
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    print(classCount)
    #dic.items():以列表返回元组数组
    #降序排列(按照第二个元素的次序排列，即按类型的数量排序)，返回排序的列表
  sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse = True)
  print(sortedClassCount)
  return sortedClassCount[0][0]

group,labels = createDataSet()
print(classify0([0,0.2],group,labels,2))