diff options
Diffstat (limited to 'analysis/days.R')
| -rw-r--r-- | analysis/days.R | 125 |
1 files changed, 125 insertions, 0 deletions
diff --git a/analysis/days.R b/analysis/days.R new file mode 100644 index 0000000..1ba131d --- /dev/null +++ b/analysis/days.R @@ -0,0 +1,125 @@ +library("tidyverse") +library("class") +library("rpart") +library("rpart.plot") +library("viridis") + +## 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=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 +tmp_data_coverage=data%>%group_by(simkey,wireless,wakeupfor,seed)%>%mutate(coverage=sum(nDataRcv))%>%ungroup()%>%filter(isSender==1)%>%select(simkey,wireless,wakeupfor,seed,coverage) +data_seed_isSender=data%>%group_by(simkey,wireless,wakeupfor,seed,isSender)%>%summarize(energy_mean=mean(energy))%>% + left_join(tmp_data_coverage,by=c("simkey","wireless","wakeupfor","seed"))%>% + mutate(efficiency=energy_mean/coverage)%>% + ungroup() +data_seed=data%>%group_by(simkey,wireless,wakeupfor,seed)%>%summarize(energy=sum(energy),coverage=sum(nDataRcv))%>% + mutate(efficiency=energy/coverage)%>% + ungroup() + +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) + data_seed=data_seed%>%filter(wakeupfor==wuf,wireless==wrl) + data_ml=data_seed%>%select(-efficiency)%>%mutate(wireless=wireless_map[data_seed$wireless]) + if(ignore_hint){ + data_ml=data_ml%>%filter(simkey!="hint") + } + train_set=data_ml%>%filter(seed<=seed_max)%>%select(-seed) # train data on seed_max*3 days + test_set=data_ml%>%anti_join(train_set)%>%select(-seed) # build test_sed excluding training set + + ## KNN training + knn_predictions=knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=10) + ## KNN analysis + knn_cont_table=table(knn_predictions,test_set$simkey) + knn_accuracy=round((sum(diag(knn_cont_table)/sum(rowSums(knn_cont_table))))*100) + knn_prop_table=round(prop.table(knn_cont_table),digits=2) + + ## Decision tree + tree=rpart( + simkey ~ wireless + wakeupfor + energy + coverage, + data=train_set, + method="class", + minsplit=60, + minbucket=1) + tree_predictions=predict(tree,newdata=test_set%>%select(-simkey),type="class") + tree_cont_table=table(tree_predictions,test_set$simkey) + tree_accuracy=round((sum(diag(tree_cont_table)/sum(rowSums(tree_cont_table))))*100) + tree_prop_table=round(prop.table(tree_cont_table),digits=2) + list(tibble(seed_max=seed_max,knn_accuracy=knn_accuracy,tree_accuracy=tree_accuracy)) + }) + ## 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=20, accuracy=10){ + ## Generate inputs + result=tibble() + for(i in seq(1,200,by=steps)){ + acc=generate_accuracy_for(ignore_hint=TRUE,seed=i,attempts_max=accuracy,wrl=wireless,wuf=wakeupfor) + result=rbind(result,acc) + } + result%>%mutate(days=seed_max*3) # 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,seed_max)%>%summarize(attempts_max=mean(attempts_max),days=mean(days),mean_knn_accuracy=mean(knn_accuracy),sd_knn_accuracy=sd(knn_accuracy),min_knn_accuracy=min(knn_accuracy),max_knn_accuracy=max(knn_accuracy),mean_tree_accuracy=mean(tree_accuracy),sd_tree_accuracy=sd(tree_accuracy),min_tree_accuracy=min(tree_accuracy),max_tree_accuracy=max(tree_accuracy)) + +## Result max +result_max=result_summary%>%group_by(wireless,wakeupfor)%>%summarize(max_knn_mean=max(mean_knn_accuracy),max_tree_mean=max(mean_tree_accuracy)) + +## Plot +ggplot(result_summary,aes(days,mean_knn_accuracy))+ + geom_errorbar(aes(ymin=min_knn_accuracy,ymax=max_knn_accuracy),width=5)+ + geom_boxplot(aes(ymin=min_knn_accuracy,ymax=max_knn_accuracy, + middle=mean_knn_accuracy, + upper=mean_knn_accuracy+sd_knn_accuracy, + lower=mean_knn_accuracy-sd_knn_accuracy,group=days),stat="identity",fill="grey")+ + geom_line(size=1.1)+geom_point(size=3,pch=15)+xlab("Number of training days")+ylab("Mean KNN accuracy")+ggtitle("KNN Accuracy")+ + ylim(c(0,100))+ + facet_wrap(~wireless+wakeupfor)+ + geom_hline(data=result_max,aes(yintercept=max_knn_mean),color="red",size=1)+ + geom_text(data=result_max, geom="text",x=0,aes(y=max_knn_mean,label = max_knn_mean,vjust=-1),color="red") +ggsave("figures/days_knn.pdf") + +ggplot(result_summary,aes(days,mean_tree_accuracy))+ + geom_errorbar(aes(ymin=min_tree_accuracy,ymax=max_tree_accuracy),width=5)+ + geom_boxplot(aes(ymin=min_tree_accuracy,ymax=max_tree_accuracy, + middle=mean_tree_accuracy, + upper=mean_tree_accuracy+sd_tree_accuracy, + lower=mean_tree_accuracy-sd_tree_accuracy,group=days),stat="identity",fill="grey")+ + geom_line(size=1.1)+geom_point(size=3,pch=15)+xlab("Number of training days")+ylab("Mean tree accuracy")+ggtitle("TREE Accuracy")+ + ylim(c(0,100))+ + facet_wrap(~wireless+wakeupfor)+ + geom_hline(data=result_max,aes(yintercept=max_tree_mean),color="red",size=1)+ + geom_text(data=result_max, geom="text",x=0,aes(y=max_tree_mean,label = max_tree_mean,vjust=-1),color="red") +ggsave("figures/days_tree.pdf") + |