应用KNN算法识别手机传感器数据交通方式

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    #print(sortedDistIndicies)
    #print(len(sortedDistIndicies))
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        voteIlabel=voteIlabel[0]####这一步不做就会报错
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
        #print('step:',i,' voteIlabel:',voteIlabel)
        #print(classCount)
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    #print('result:',sortedClassCount[0][0])
return sortedClassCount[0][0]

def autoNorm(dataSet):
    minVals = dataSet.min(axis=0)
    maxVals = dataSet.max(axis=0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m,1))
    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide
return normDataSet, ranges, minVals

def TrafficClassTest():   
    normMat, ranges, minVals = autoNorm(data_xnew)
    normMat1, ranges1, minVals1 = autoNorm(Data_xnew)
    numTestVecs = Data_ynew.shape[0]
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat1[i,:],normMat,data_ynew,3)
        print ("the classifier came back with: %d, the real answer is: %d" % (classifierResult,Data_ynew[i]))
        if (classifierResult != Data_ynew[i]): errorCount += 1.0
    print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))

表1 识别率分布图

标签\预测	1：步行	2：自行车	3：公交车	4：小汽车	求和
1：步行	0.9767	0.0021	0.0163	0.0049	1.0000
2：自行车	0.0024	0.9904	0.0072	0.0000	1.0000
3：公交车	0.0230	0.0000	0.9641	0.0129	1.0000
4：小汽车	0.0138	0.0000	0.0453	0.9409	1.0000

附录程序源代码:

#-*- coding=utf-8 -*-
##一次平滑用于预测
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from collections import Counter
import operator


##定义用于将多维list整合成为1维list的函数
def flat(l): 
    for k in l: 
        if not isinstance(k, (list, tuple)): 
            yield k 
        else: 
            yield from flat(k)


SCALE = 60#定义SCALE长度，滚动每段数据实际为2SCALE长度
data_x=[]
data_y=[]#训练集

Data_x=[]
Data_y=[]#测试集
##定义文件读入函数
def choose_file(filenumber):
    traindata = pd.read_excel('train%s.xlsx'%filenumber)
    tempspeed=[]
    tempfirstplant=[]
    tempmeans=[]
    tempspeed.append(list(traindata['speed']))
    tempmeans.append(list(traindata['means']))
    tempfirstplant.append(list(traindata['firstplant']))
    tempspeed = list(flat(tempspeed))
    tempmeans = list(flat(tempmeans))
    tempfirstplant=list(flat(tempfirstplant))
    for i in range(SCALE):#每个文件前SCALE个数据的读入
        speed=np.array(tempspeed[0 : i+SCALE])
        speed_in=tempspeed[i]
        firstplant=tempfirstplant[i]
        mean_speed=speed.mean()
        max_speed=speed.max()
        std_speed=speed.std()
        data_x.append(list([speed_in,firstplant,mean_speed,max_speed,std_speed]))
        data_y.append(list([tempmeans[i]]))
    for i in range(SCALE,(len(tempspeed)-SCALE)):#每个文件可以正常选择SCALE的数据的读入
        speed = np.array(tempspeed[i-SCALE : i+SCALE])
        speed_in=tempspeed[i]
        firstplant=tempfirstplant[i]
        mean_speed=speed.mean()
        max_speed=speed.max()
        std_speed=speed.std()
        data_x.append(list([speed_in,firstplant,mean_speed,max_speed,std_speed]))
        data_y.append(list([tempmeans[i]]))
    for i in range((len(tempspeed)-SCALE),len(tempspeed)):#每个文件尾部的SCALE个数据的读入
        speed=np.array(tempspeed[i-SCALE:(len(tempspeed))])
        speed_in=tempspeed[i]
        firstplant=tempfirstplant[i]
        mean_speed=speed.mean()
        max_speed=speed.max()
        std_speed=speed.std()
        data_x.append(list([speed_in,firstplant,mean_speed,max_speed,std_speed]))
        data_y.append(list([tempmeans[i]]))
    return data_x,data_y#返回用于训练模型的x和y

##读入5个出行个体的训练文件
l=[1,2,3,4,5,6]
for i in l:
    choose_file(i)
data_y=np.array(data_y)

import  random
a=range((len(data_x)))
b=random.sample(a,int(0.8*len(data_x)))
c=list(set(a).difference(set(b))) 
data_xnew=[]
data_ynew=[]
Data_xnew=[]
Data_ynew=[]
for i in b:
        data_xnew.append(data_x[i])
        data_ynew.append(data_y[i])
for i in c:
        Data_xnew.append(data_x[i])
        Data_ynew.append(data_y[i])


data_xnew=np.array(data_xnew)
data_ynew=np.array(data_ynew)
Data_xnew=np.array(Data_xnew)
Data_ynew=np.array(Data_ynew)


def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = np.tile(inX, (dataSetSize,1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()
    #print(sortedDistIndicies)
    #print(len(sortedDistIndicies))
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        voteIlabel=voteIlabel[0]####这一步不做就会报错
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
        #print('step:',i,' voteIlabel:',voteIlabel)
        #print(classCount)
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    #print('result:',sortedClassCount[0][0])
    return sortedClassCount[0][0]

def autoNorm(dataSet):
    minVals = dataSet.min(axis=0)
    maxVals = dataSet.max(axis=0)
    ranges = maxVals - minVals
    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVals, (m,1))
    normDataSet = normDataSet/np.tile(ranges, (m,1))   #element wise divide
    return normDataSet, ranges, minVals
CLASSFIERRESULT=[]
def TrafficClassTest():   
    normMat, ranges, minVals = autoNorm(data_xnew)
    normMat1, ranges1, minVals1 = autoNorm(Data_xnew)
    numTestVecs = Data_ynew.shape[0]
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat1[i,:],normMat,data_ynew,3)
        CLASSFIERRESULT.append(classifierResult)
        #print ("the classifier came back with: %d, the real answer is: %d" % (classifierResult, Data_ynew[i]))
        if (classifierResult != Data_ynew[i]): errorCount += 1.0
    print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))
    print(errorCount,numTestVecs)
TrafficClassTest()
CLASSFIERRESULT = np.array(CLASSFIERRESULT)
#Data_ynew标签（真实）true；CLASSFIERRESULT预测pre
count1,count2,count3,count4=0,0,0,0
true_walk = Data_ynew[Data_ynew==1].shape[0]
true_walk_index = np.argwhere(Data_ynew==1)[:,0]
for o in true_walk_index:
    if CLASSFIERRESULT[o]==1:
        count1+=1
    elif CLASSFIERRESULT[o]==2:
        count2+=1
    elif CLASSFIERRESULT[o]==3:
        count3+=1
    elif CLASSFIERRESULT[o]==4:
        count4+=1
    else:pass  
w_w,w_b,w_s,w_c=count1/true_walk,count2/true_walk,count3/true_walk,count4/true_walk


count1,count2,count3,count4=0,0,0,0
true_bike = Data_ynew[Data_ynew==2].shape[0]
true_bike_index = np.argwhere(Data_ynew==2)[:,0]
for o in true_bike_index:
    if CLASSFIERRESULT[o]==1:
        count1+=1
    elif CLASSFIERRESULT[o]==2:
        count2+=1
    elif CLASSFIERRESULT[o]==3:
        count3+=1
    elif CLASSFIERRESULT[o]==4:
        count4+=1
    else:pass
b_w,b_b,b_s,b_c=count1/true_bike,count2/true_bike,count3/true_bike,count4/true_bike


count1,count2,count3,count4=0,0,0,0
true_bus = Data_ynew[Data_ynew==3].shape[0]
true_bus_index = np.argwhere(Data_ynew==3)[:,0]
for o in true_bus_index:
    if CLASSFIERRESULT[o]==1:
        count1+=1
    elif CLASSFIERRESULT[o]==2:
        count2+=1
    elif CLASSFIERRESULT[o]==3:
        count3+=1
    elif CLASSFIERRESULT[o]==4:
        count4+=1
    else:pass
s_w,s_b,s_s,s_c=count1/true_bus,count2/true_bus,count3/true_bus,count4/true_bus


count1,count2,count3,count4=0,0,0,0
true_car = Data_ynew[Data_ynew==4].shape[0]
true_car_index = np.argwhere(Data_ynew==4)[:,0]
for o in true_car_index:
    if CLASSFIERRESULT[o]==1:
        count1+=1
    elif CLASSFIERRESULT[o]==2:
        count2+=1
    elif CLASSFIERRESULT[o]==3:
        count3+=1
    elif CLASSFIERRESULT[o]==4:
        count4+=1
    else:pass
c_w,c_b,c_s,c_c=count1/true_car,count2/true_car,count3/true_car,count4/true_car
print('line1',w_w,w_b,w_s,w_c)
print('line2',b_w,b_b,b_s,b_c)
print('line3',s_w,s_b,s_s,s_c)
print('line4',c_w,c_b,c_s,c_c)