1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
########## INFORMATIONS ##########
# This file is made to study online classification
# So, each pair (wireless,wakeupfor) has its classification models (knn and decision tree)
##################################
library("tidyverse")
options(dplyr.summarise.inform = FALSE)
library("class")
library("rpart")
library("rpart.plot")
library("viridis")
library("MLmetrics")
## Simulation Parameters:
## simkey {baseline,extended,hint,hintandextended}
## wireless {lora,nbiot}
## wakeupfor {60s,180s}
## seed [1,200]
## node on[0,12]
## isSender {0,1}
## dataSize {1MB}
## Metrics:
## energy [0,+inf)
## nDataRcv [0,+inf)
nseed=200
nwakeupfor=2
nwireless=2
nsimkey=4
nsimulations=nseed*nwakeupfor*nwireless*nsimkey # Must be 3200
## Load data
data=suppressMessages(read_csv("../CCGRID2022.csv"))%>%distinct() # Note that in the data experiment wireless=="lora",seed==1,wakeupfor==60,simkey=="baseline" is present 2 times in the CSV file
data_seed=data%>%group_by(simkey,wireless,wakeupfor,seed)%>%summarize(energy=sum(energy),coverage=sum(nDataRcv))%>%
mutate(efficiency=energy/coverage)%>%
ungroup()
F1_Score2=function(truth, pred){
result=sapply(c("baseline","extended","hint","hintandextended"),function(c){
cur_truth=truth[truth==c]
cur_pred=pred[truth==c]
col=paste0("f1_",c)
score=F1_Score(cur_truth,cur_pred)
if(is.nan(score)){score=0}
list(tibble(!!col:=score))
})
do.call("cbind",result)
}
generate_accuracy_for=function(ignore_hint=FALSE,seed_max=200,attempts_max=2,wrl="lora",wuf=180) {
attempts=seq(1,attempts_max)
results=sapply(attempts,function(attempt){
## Prepare data for traning
set.seed(1+attempt) # Reproducibility
wireless_map=c("lora"=1,"nbiot"=2)
cur_data_seed=data_seed%>%filter(wakeupfor==wuf,wireless==wrl)
data_ml=cur_data_seed%>%select(-efficiency)%>%mutate(wireless=wireless_map[cur_data_seed$wireless])
if(ignore_hint){
data_ml=data_ml%>%filter(simkey!="hint")
}
train_set=data_ml%>%filter(seed<=seed_max)%>%select(-seed) # train data on seed_max*3 days
test_set=data_ml%>%suppressMessages(anti_join(train_set))%>%select(-seed) # build test_sed excluding training set
## KNN training
knn_predictions=knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=min(10,NROW(train_set)))
## KNN analysis
knn_cont_table=table(knn_predictions,test_set$simkey)
knn_accuracy=(sum(diag(knn_cont_table)/sum(rowSums(knn_cont_table))))
knn_prop_table=round(prop.table(knn_cont_table),digits=2)
knn_f1_score=F1_Score2(test_set$simkey,knn_predictions)
## Decision tree
tree=rpart(
simkey ~ wireless + wakeupfor + energy + coverage,
data=train_set,
method="class",
minsplit=60,
minbucket=1)
tree_predictions=predict(tree,newdata=test_set%>%select(-simkey),type="class")
tree_cont_table=table(tree_predictions,test_set$simkey)
tree_accuracy=(sum(diag(tree_cont_table)/sum(rowSums(tree_cont_table))))
tree_prop_table=round(prop.table(tree_cont_table),digits=2)
tree_f1_score=F1_Score2(test_set$simkey,tree_predictions)
## Format data
result_data=tibble(seed_max=seed_max,model=c("knn","tree"),accuracy=c(knn_accuracy,tree_accuracy))
result_data=cbind(result_data,rbind(knn_f1_score,tree_f1_score))
list(result_data)
})
## Prints
results=do.call("rbind",results)
results%>%mutate(seed_max=seed_max,attempts_max=attempts_max,wireless=wrl,wakeupfor=wuf)
}
generate_accuracy = function(wireless,wakeupfor,steps=10, accuracy=10,ignore_hint=TRUE){
npolicies=4
if(ignore_hint){npolicies=npolicies-1}
## Generate inputs
result=tibble()
for(i in seq(1,160,by=steps)){ # We stop at 80% of the data (this way test set is at least 20%)
acc=generate_accuracy_for(ignore_hint=ignore_hint,seed=i,attempts_max=accuracy,wrl=wireless,wuf=wakeupfor)
result=rbind(result,acc)
}
result%>%mutate(days=seed_max*npolicies,months=days/30) # Since 3 policies (since ignore_hint=TRUE)
}
# Generate accuracy for each wireless and uptime
#accuracy=rbind(generate_accuracy("lora",60),
# generate_accuracy("lora",180),
# generate_accuracy("nbiot",60),
# generate_accuracy("nbiot",180))
## Summarize
result_summary=accuracy%>%group_by(wireless,wakeupfor,months,model)%>%
summarize(
mean_accuracy=mean(accuracy),sd_accuracy=sd(accuracy),min_accuracy=min(accuracy),max_accuracy=max(accuracy),
mean_f1_baseline=mean(f1_baseline),sd_f1_baseline=sd(f1_baseline),min_f1_baseline=min(f1_baseline),max_f1_baseline=max(f1_baseline),
mean_f1_hint=mean(f1_hint),sd_f1_hint=sd(f1_hint),min_f1_hint=min(f1_hint),max_f1_hint=max(f1_hint),
mean_f1_extended=mean(f1_extended),sd_f1_extended=sd(f1_extended),min_f1_extended=min(f1_extended),max_f1_extended=max(f1_extended),
mean_f1_hintandextended=mean(f1_hintandextended),sd_f1_hintandextended=sd(f1_hintandextended),min_f1_hintandextended=min(f1_hintandextended),max_f1_hintandextended=max(f1_hintandextended))
## Result max
metrics_peak=result_summary%>%group_by(wireless,wakeupfor,model)%>%
summarize(max_accuracy=max(mean_accuracy))
## Plot
sapply(c("knn","tree"),function(grp){
data=result_summary%>%filter(model==grp)
plot=ggplot(data,aes(months,mean_accuracy))+
geom_ribbon(aes(ymin=mean_accuracy-sd_accuracy,ymax=mean_accuracy+sd_accuracy),alpha=0.2,color=NA)+
geom_line(size=1.1)+geom_point(size=3)+
geom_point(data=data%>%drop_na(mean_f1_baseline),aes(months,mean_f1_baseline,color="baseline"))+geom_line(data=data%>%drop_na(mean_f1_baseline),aes(months,mean_f1_baseline,color="baseline"))+
geom_point(data=data%>%drop_na(mean_f1_extended),aes(months,mean_f1_extended,color="extended"))+geom_line(data=data%>%drop_na(mean_f1_extended),aes(months,mean_f1_extended,color="extended"))+
geom_point(data=data%>%drop_na(mean_f1_hintandextended),aes(months,mean_f1_hintandextended,color="hintandextended"))+geom_line(data=data%>%drop_na(mean_f1_hintandextended),aes(months,mean_f1_hintandextended,color="hintandextended"))
if(any(!is.na(data$mean_f1_hint))){
plot=plot+geom_point(data=data%>%drop_na(mean_f1_hint),aes(months,mean_f1_hint,color="hint"))+geom_line(data=data%>%drop_na(mean_f1_hint),aes(months,mean_f1_hint,color="hint"))
}
plot=plot+xlab("Number of training months")+ylab(paste("Mean",grp,"accuracy"))+ggtitle(paste(grp,"accuracy"))+
# geom_hline(data=metrics_peak%>%filter(model==grp),aes(yintercept=max_accuracy),color="red",size=1)+
# geom_text(data=metrics_peak%>%filter(model==grp),x=0,aes(y=max_accuracy,label = round(max_accuracy,digits=1),vjust=-1),color="red")+
facet_wrap(~wireless+wakeupfor)+scale_x_continuous(breaks = seq(0, max(result_summary$months), by = 1))+ylim(c(0,1))+labs(color="F1 Score")
ggsave(paste0("figures/months_",grp,".pdf"),width=20,height=15)
print(plot)
})
|
