《机器学习实战》之k-近邻算法

 1 from numpy import *
 2 import operator
 3 
 4 def createDataSet():
 5     group = array([[1.0,1.1], [1.0,1.0], [0,0], [0,0.1]])
 6     labels = [‘A‘, ‘A‘, ‘B‘, ‘B‘]
 7     return group, labels
 8 
 9 def classify0(inX, dataSet, labels, k):
10     dataSetSize = dataSet.shape[0]
11     diffMat = tile(inX, (dataSetSize,1)) - dataSet  #统一矩阵，实现加减
12     sqDiffMat = diffMat**2
13     sqDistances = sqDiffMat.sum(axis=1)  #进行累加，axis=0是按列，axis=1是按行
14     distances = sqDistances**0.5  #开根号
15     sortedDistIndicies = distances.argsort()  #按升序进行排序，返回原下标
16     classCount = {}
17     for i in range(k):
18         voteIlabel = labels[sortedDistIndicies[i]]
19         classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1  #get是字典中的方法，前面是要获得的值，后面是若该值不存在时的默认值
20     sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
　　　　#在python3中没有iteritems，key在这里是按照字典的第二个元素来排序，降序排序
21     return sortedClassCount[0][0]  #获得字典中第一对映射中的第一个值
22 
23 
24 if __name__ == "__main__":
25     dataSet, labels = createDataSet()
26     inX = [0.2, 0.2]
27     print(classify0(inX, dataSet, labels, 2))

1 from numpy import array
2 
3 a = array([[1,1],
4            [2,3]])
5 b = array([[0,1],
6            [3,2]])
7 c = a-b
8 print(c)

1 from numpy import tile
2 
3 a = [1,2,3]
4 b = tile(a,(2,3))
5 print(b)

1 from numpy import argsort
2 
3 a = [4,3,1,2]
4 b = argsort(a)
5 print(b)