[Python] 实施kNN算法

1 from numpy import *
2 import operator
3 
4 #运算符模块   创建数据集和标签
5 def createDataSet():
6     group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
7     labels = [‘A‘, ‘A‘, ‘B‘, ‘B‘]
8     return group, labels

 1 from numpy import *
 2 import operator
 3 
 4 #运算符模块
 5 def createDataSet():
 6     group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
 7     labels = [‘A‘, ‘A‘, ‘B‘, ‘B‘]
 8     return group, labels
 9 
10 #k-近邻算法  此模块需要使用运算符模块的group/labels
11 def classify0(inX, dataSet, labels, k):
12     dataSetSize = dataSet.shape[0]
13     diffMat = tile(inX, (dataSetSize, 1)) - dataSet
14     sqDiffMat = diffMat ** 2
15     sqDistances = sqDiffMat.sum(axis=1)
16     distances = sqDistances ** 0.5
17     sortedDistIndicies = distances.argsort()
18     classCount = {}
19     for i in range(k):
20         voteIlabel = labels[sortedDistIndicies[i]]
21         classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
22 
23     sortedClassCount = sorted(classCount.iteritems(),
24                               key=operator.itemgetter(1),
25                               reverse=True)
26     return sortedClassCount[0][0]