import numpy as np
def classify0(inX,dataSet,labels,k):
#shape[0]表示行数
dataSetSize = dataSet.shape[0]#表示数据集的行数
# tile(a,x): x是控制a重复几次的,结果是一个一维数组
# tile(a,(x,y)): 结果是一个二维矩阵,其中行数为x,列数是一维数组a的长度和y的乘积
# tile(a,(x,y,z)): 结果是一个三维矩阵,其中矩阵的行数为x,
# 矩阵的列数为y,而z表示矩阵每个单元格里a重复的次数。
# (三维矩阵可以看成一个二维矩阵,每个矩阵的单元格里存者一个一维矩阵a)
diffMat=tile(inX,(dataSetSize,1))-dataSet
sqDiffMat=diffMat**2
# a=np.array([[1,2],[3,4],[5,6]]) b=a.sum(axis=0) ---[ 9 12]对行进行计算
# a=np.array([[1,2],[3,4],[5,6]]) b=a.sum(axis=1) ---[ 3 7 11]对列进行计算
sqDistances=sqDiffMat.sum(axis=1)#计算距离,相当于(x-x0)**2+(y-y0)**2
distances=sqDistances**0.5
#print(distances)--->[6.32455532 4.12310563 3.60555128 5.]
# argsort()函数是将x中的元素从小到大排列,提取其对应的index(索引号)g=np.array([1,7,3,8])
#h=g.argsort()----->h=[0 2 1 3]
sortedDistIndicies=distances.argsort()#[2 1 3 0]
classCount={}
for i in range(k):
voteIlabel=labels[sortedDistIndicies[i]]
#classCount.get(voteIlabel,0),这个0表示如果字典里面没有想要的关键词,就返回0,如果有就返回相应的关键词。
classCount[voteIlabel]=classCount.get(voteIlabel,0)+1#刚开始classCount为空的,返回0,加上1之后变为1
pass
print(classCount.items())
#classCount.items()将字典以列表的形式返回,[('c', 1), ('b', 1), ('d', 1), ('a', 1)],
#key=operator.itemgetter(1)按值即value,若operator.itemgetter(0)则按key排序,reverse=True降序
sortedClassCount=sorted(classCount.items(),
key=operator.itemgetter(1),reverse=True)
return sortedClassCount[0][0]
dataset=array([[1,3],[4,5],[6,7],[8,9]])
X=array([3,9])
labels=['a','b','c','d']
classify0(X,dataset,labels,4)
_______________________________________
out:
dict_items([('c', 1), ('b', 1), ('d', 1), ('a', 1)])
'c'
python中函数测试
附加代码,可忽略
'''
kNN: k Nearest Neighbors
Input: inX: vector to compare to existing dataset (1xN)
dataSet: size m data set of known vectors (NxM)
labels: data set labels (1xM vector)
k: number of neighbors to use for comparison (should be an odd number)
Output: the most popular class label
'''
from numpy import *
import operator
from os import listdir
def classify0(inX, dataSet, labels, k):
dataSetSize = dataSet.shape[0]
diffMat = tile(inX, (dataSetSize,1)) - dataSet
sqDiffMat = diffMat**2
sqDistances = sqDiffMat.sum(axis=1)
distances = sqDistances**0.5
sortedDistIndicies = distances.argsort()
classCount={}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
def createDataSet():
group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
labels = ['A','A','B','B']
return group, labels
def file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines()) #get the number of lines in the file
returnMat = zeros((numberOfLines,3)) #prepare matrix to return
classLabelVector = [] #prepare labels return
index = 0
for line in fr.readlines():
line = line.strip()#去掉回车符
listFromLine = line.split('\t')#将有tab键的地方分割,变为列表
returnMat[index,:] = listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat,classLabelVector
def autoNorm(dataSet):
minVals = dataSet.min(0)
maxVals = dataSet.max(0)
ranges = maxVals - minVals
normDataSet = zeros(shape(dataSet))
m = dataSet.shape[0]
normDataSet = dataSet - tile(minVals, (m,1))
normDataSet = normDataSet/tile(ranges, (m,1)) #element wise divide
return normDataSet, ranges, minVals
def datingClassTest():
hoRatio = 0.50 #hold out 10%
datingDataMat,datingLabels = file2matrix('datingTestSet2.txt') #load data setfrom file
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3)
print ("the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i]))
if (classifierResult != datingLabels[i]): errorCount += 1.0
print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))
print (errorCount)
def img2vector(filename):
returnVect = zeros((1,1024))
fr = open(filename)
for i in range(32):
lineStr = fr.readline()
for j in range(32):
returnVect[0,32*i+j] = int(lineStr[j])
return returnVect
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('trainingDigits') #load the training set
m = len(trainingFileList)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
testFileList = listdir('testDigits') #iterate through the test set
errorCount = 0.0
mTest = len(testFileList)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0] #take off .txt
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
print ("the classifier came back with: %d, the real answer is: %d" % (classifierResult, classNumStr))
if (classifierResult != classNumStr): errorCount += 1.0
print ("\nthe total number of errors is: %d" % errorCount)
print ("\nthe total error rate is: %f" % (errorCount/float(mTest)))
```