knn算法

import numpy as np def CreateDateSet(): group = np.array([[1.0, 2.0], [1.2, 0.1], [0.1, 1.4], [0.3, 3.5]]) labels = ['A','A','B','B'] return group,labels

coding:utf-8

from numpy import * import operator

##給出訓練數據以及對應的類別 def createDataSet(): group = array([[1.0, 2.0], [1.2, 0.1], [0.1, 1.4], [0.3, 3.5],[0.2,1.5]]) labels = ['A', 'A', 'B', 'B','B'] return group, labels

###經過KNN進行分類 def classify(input, dataSet, label, k): dataSize = dataSet.shape[0] ####計算歐式距離 diff = tile(input, (dataSize, 1)) - dataSet sqdiff = diff ** 2

squareDist = sum(sqdiff, axis=1)  ###行向量分別相加，從而獲得新的一個行向量
dist = squareDist ** 0.5

##對距離進行排序
sortedDistIndex = argsort(dist)  ##argsort()根據元素的值從大到小對元素進行排序，返回下標
print(sortedDistIndex )
classCount = {}
for i in range(k):
    voteLabel = label[sortedDistIndex[i]]
    ###對選取的K個樣本所屬的類別個數進行統計
    classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
    print(classCount)
###選取出現的類別次數最多的類別
maxCount = 0
for key, value in classCount.items():
    if value > maxCount:
        maxCount = value
        classes = key

return classes

def main(): input = array([1.1, 0.3]) dataSet, labels = createDataSet() K = 3 classify(input,dataSet,labels,K)

main()