diff options
Diffstat (limited to 'analysis/days.R')
| -rw-r--r-- | analysis/days.R | 78 |
1 files changed, 41 insertions, 37 deletions
diff --git a/analysis/days.R b/analysis/days.R index 1ba131d..7d26aef 100644 --- a/analysis/days.R +++ b/analysis/days.R @@ -3,6 +3,7 @@ library("class") library("rpart") library("rpart.plot") library("viridis") +library("MLmetrics") ## Simulation Parameters: ## simkey {baseline,extended,hint,hintandextended} @@ -40,8 +41,8 @@ generate_accuracy_for=function(ignore_hint=FALSE,seed_max=200,attempts_max=2,wrl ## 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$wireless]) + cur_data_seed=data_seed%>%filter(wakeupfor==wuf,wireless==wrl) + data_ml=cur_data_seed%>%select(-efficiency)%>%mutate(wireless=wireless_map[cur_data_seed$wireless]) if(ignore_hint){ data_ml=data_ml%>%filter(simkey!="hint") } @@ -49,12 +50,15 @@ generate_accuracy_for=function(ignore_hint=FALSE,seed_max=200,attempts_max=2,wrl 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$simkey,k=10) + knn_predictions=knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=min(10,NROW(train_set))) ## KNN analysis knn_cont_table=table(knn_predictions,test_set$simkey) knn_accuracy=round((sum(diag(knn_cont_table)/sum(rowSums(knn_cont_table))))*100) knn_prop_table=round(prop.table(knn_cont_table),digits=2) - + knn_f1_score=F1_Score(test_set$simkey,knn_predictions) + knn_recall=Recall(test_set$simkey,knn_predictions) + knn_precision=Precision(test_set$simkey,knn_predictions) + ## Decision tree tree=rpart( simkey ~ wireless + wakeupfor + energy + coverage, @@ -66,7 +70,10 @@ generate_accuracy_for=function(ignore_hint=FALSE,seed_max=200,attempts_max=2,wrl tree_cont_table=table(tree_predictions,test_set$simkey) tree_accuracy=round((sum(diag(tree_cont_table)/sum(rowSums(tree_cont_table))))*100) tree_prop_table=round(prop.table(tree_cont_table),digits=2) - list(tibble(seed_max=seed_max,knn_accuracy=knn_accuracy,tree_accuracy=tree_accuracy)) + tree_f1_score=F1_Score(test_set$simkey,tree_predictions) + tree_recall=Recall(test_set$simkey,tree_predictions) + tree_precision=Precision(test_set$simkey,tree_predictions) + list(tibble(seed_max=seed_max,model=c("knn","tree"),accuracy=c(knn_accuracy,tree_accuracy),f1_score=c(knn_f1_score,tree_f1_score),recall=c(knn_recall,tree_recall),precision=c(knn_precision,tree_precision))) }) ## Prints results=do.call("rbind",results) @@ -74,52 +81,49 @@ generate_accuracy_for=function(ignore_hint=FALSE,seed_max=200,attempts_max=2,wrl } -generate_accuracy = function(wireless,wakeupfor,steps=20, accuracy=10){ +generate_accuracy = function(wireless,wakeupfor,steps=2, accuracy=20,ignore_hint=TRUE){ + npolicies=4 + if(ignore_hint){npolicies=npolicies-1} ## 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) + 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*3) # Since 3 policies (since ignore_hint=TRUE) + result%>%mutate(days=seed_max*npolicies,months=days/30) # Since 3 policies (since ignore_hint=TRUE) } -## Generate accuracy for each wireless and uptime +# 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_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_score=mean(f1_score),sd_f1_score=sd(f1_score),min_f1_score=min(f1_score),max_f1_score=max(f1_score), + mean_recall=mean(recall),sd_recall=sd(recall),min_recall=min(recall),max_recall=max(recall), + mean_precision=mean(precision),sd_precision=sd(precision),min_precision=min(precision),max_precision=max(precision)) ## 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)) +metrics_peak=result_summary%>%group_by(wireless,wakeupfor,model)%>% + summarize(max_accuracy=max(mean_accuracy), + max_f1_score=max(mean_f1_score), + max_recall=max(mean_recall), + max_precision=max(mean_precision)) ## 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") +sapply(c("knn","tree"),function(grp){ + ggplot(result_summary%>%filter(model==grp),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)+xlab("Number of training months")+ylab(paste("Mean",grp,"accuracy"))+ggtitle(paste(grp,"accuracy"))+ +# ylim(c(0,100))+ + 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)) + ggsave(paste0("figures/months_",grp,".pdf")) +}) |