採用python3.7,需要安裝Numpy庫
算法的邏輯如下:
1.計算已知分類數據集中的點與輸入點之間的距離
2.根據距離遞增排序
3 選擇與輸入點距離最小的k個點
4 確認前k個點所在分類的出現頻率
5 返回前k個點出現頻率最高的分類作爲輸入點的預測分類
數據集:
[[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]]
['A','A','B','B']
輸入:[1.2,0]
輸出:A
輸入:[1.5,1]
輸出:A
輸入:[0,0.5]
輸出:B
下面是源碼:
from numpy import *
import operator
'''
KNN分類算法
出現問題
AttributeError: 'dict' object has no attribute 'iteritems'
Python3.5中:iteritems變爲items
'''
def createDataSet():
#創建數據集
group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
labels = ['A','A','B','B']
return group,labels
#print(group)
#print(labels)
def classify0(intX,dataSet,labels,k):
#距離計算
dataSetSize = dataSet.shape[0]
diffMat = tile(intX,(dataSetSize,1))-dataSet
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
sortedDistIndicies = distances.argsort()
#選擇距離最小的K個點
classCount = {}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel,0)+1
#排序
sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
return sortedClassCount[0][0]
group,labels = createDataSet()
print("輸入:[1.2,0]")
print("輸出:"+classify0([1.2,0],group,labels,3))
print("輸入:[1.5,1]")
print("輸出:"+classify0([1.5,1],group,labels,3))
print("輸入:[0,0.5]")
print("輸出:"+classify0([0,0.5],group,labels,3))