Clean repo and debug setup.sh

1 files changed, 0 insertions, 254 deletions

diff --git a/analysis/days.R b/analysis/days.R
deleted file mode 100644
index 93d478e..0000000
--- a/analysis/days.R
+++ /dev/null
@@ -1,254 +0,0 @@
-########## INFORMATIONS ##########
-# This file is made to study online classification
-# So, each pair (wireless,wakeupfor) has its classification models (knn and decision tree)
-# Note that is the following error appears: object 'accuracy' not found
-# it means you should toggle the boolean in the if condition in the code to generate the accuracy onbject
-##################################
-
-library("tidyverse")
-options(dplyr.summarise.inform = FALSE)
-library("class")
-library("rpart")
-library("rpart.plot")
-library("viridis")
-library("MLmetrics")
-library("latex2exp")
-
-## 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 and prepare the 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_Score of multiclass vectors
-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)
-}
-
-## Down scale data
-reduce_days=function(data,every=6){data%>%filter(((days/4) %% every) == 0)}
-
-## GGPlot Theme
-th = function(option="D") {list(theme_bw(),
-                                theme(legend.box.background = element_rect(fill = "white", color = "black",size=0.9),
-                                      strip.background =element_rect(fill="#F5F5F5")),
-                     scale_color_viridis(discrete=TRUE,option=option,end=0.95),
-                     scale_fill_viridis(discrete=TRUE,option=option,end=0.95))}
-
-## Train models
-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$wireless])
-        if(ignore_hint){
-            data_ml=data_ml%>%filter(simkey!="hint")
-        }
-        train_set=data_ml%>%filter(seed<=seed_max)%>%select(-seed)     # train data on seed_max*3 days
-        test_set=data_ml%>%select(-seed)                               # build test_sed
-        #print(paste0("Test set ",NROW(test_set)))
-        #print(paste0("Train set ",NROW(train_set)))
-        ## KNN training
-        knn_predictions=knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=min(10,NROW(train_set)))
-        ## KNN analysis
-        knn_cont_table=table(knn_predictions,test_set$simkey)
-        knn_accuracy=(sum(diag(knn_cont_table)/sum(rowSums(knn_cont_table))))
-        #print(knn_accuracy)
-        knn_prop_table=round(prop.table(knn_cont_table),digits=2)
-        knn_f1_score=F1_Score2(test_set$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_energy = function(wireless,wakeupfor,steps=1, accuracy=10,ignore_hint=FALSE){
-    ## Setup variables
-    npolicies=4
-    data_seed_for_energy=data_seed%>%ungroup()
-    if(ignore_hint){npolicies=npolicies-1;data_seed_for_energy=data_seed%>%filter(simkey!="hint")}
-    data_seed_for_energy=data_seed_for_energy%>%filter(wireless==!!wireless,wakeupfor==!!wakeupfor)
-
-    ## Generate inputs
-    result=tibble()
-    result_energy=tibble()
-    for(i in seq(1,160,by=steps)){ # We stop at 80% of the data (this way test set is at least 20%)
-        print(paste("Step",i))
-        acc=generate_accuracy_for(ignore_hint=ignore_hint,seed=i,attempts_max=accuracy,wrl=wireless,wuf=wakeupfor)
-        result_energy=rbind(result_energy,data_seed_for_energy%>%filter(seed<=i)%>%summarize(energy=sum(energy),seed_max=i,days=i*npolicies,setup=paste0(!!wireless," ",!!wakeupfor,"s"),wireless=!!wireless,wakeupfor=!!wakeupfor))
-        result=rbind(result,acc)
-    }
-   list(accuracy=result%>%mutate(days=seed_max*npolicies), # Since 3 policies (since ignore_hint=TRUE)
-        energy=result_energy)
-}
-
-
-########## Generate accuracy, energy, F1-Score and coverage data ##########
-if(F){ # Toggle to train
-    lora180=generate_accuracy_energy("lora",180)
-    lora60=generate_accuracy_energy("lora",60)
-    nbiot60=generate_accuracy_energy("nbiot",60)
-    nbiot180=generate_accuracy_energy("nbiot",180)
-    accuracy=rbind(lora60$accuracy,lora180$accuracy,nbiot60$accuracy,nbiot180$accuracy)
-    coverage=data_seed%>%group_by(wireless,wakeupfor,seed)%>%summarize(coverage=sum(coverage))%>%mutate(days=seed*4)%>%filter(days %in% !!lora60$energy$days)%>%select(-seed)
-    energy=rbind(lora60$energy,
-                 lora180$energy,
-                 nbiot60$energy,
-                 nbiot180$energy)%>%left_join(coverage,by=c("wireless","wakeupfor","days"))
-}
-
-
-########## Build learning curve (Accuracy+F1_Scores) ##########
-learning_curves=accuracy%>%group_by(wireless,wakeupfor,days,model)%>%
-    summarize(
-        ## Accuracy
-        mean_accuracy=mean(accuracy),sd_accuracy=sd(accuracy),
-        min_accuracy=min(accuracy),max_accuracy=max(accuracy),
-        ## F1-Score Baseline
-        mean_f1_baseline=mean(f1_baseline),sd_f1_baseline=sd(f1_baseline),
-        min_f1_baseline=min(f1_baseline),max_f1_baseline=max(f1_baseline),
-        ## F1-Score Hint
-        mean_f1_hint=mean(f1_hint),sd_f1_hint=sd(f1_hint),min_f1_hint=min(f1_hint),
-        max_f1_hint=max(f1_hint),
-        ## F1-Score Extended
-        mean_f1_extended=mean(f1_extended),sd_f1_extended=sd(f1_extended),
-        min_f1_extended=min(f1_extended),max_f1_extended=max(f1_extended),
-        ## F1-Score HintAndExtended
-        mean_f1_hintandextended=mean(f1_hintandextended),sd_f1_hintandextended=sd(f1_hintandextended),
-        min_f1_hintandextended=min(f1_hintandextended),max_f1_hintandextended=max(f1_hintandextended))
-
-
-ggplot(data=learning_curves%>%mutate(model=ifelse(model=="knn","KNN","DT")),aes(linetype=model))+
-    geom_line(aes(days/30,mean_f1_baseline,color="Baseline"),size=1.2)+
-    geom_line(aes(days/30,mean_f1_extended,color="Extended"),size=1.2)+
-    geom_line(aes(days/30,mean_f1_hint,color="Hint"),size=1.2)+
-    geom_line(aes(days/30,mean_f1_hintandextended,color="Hintandextended"),size=1.2)+labs(color="Classes colors",linetype="Model")+
-    facet_wrap(~wireless+wakeupfor)+
-    scale_x_continuous(breaks = seq(0, max(learning_curves$days/30)))+
-    scale_y_continuous(breaks = seq(0, 1, by = 0.1))+
-    th()+
-    theme(panel.grid.minor = element_blank(),
-          legend.position = c(0.9,0.72),
-          legend.margin = margin(2,4,2,4),
-          legend.spacing=unit(-0.2,"cm"),
-          legend.box.margin=margin(1,1,1,1))+
-    xlab("Training duration (months)")+ylab("Classes F1-Score")
-ggsave("figures/months_f1-score.pdf",width=8.5,height=6)
-
-
-## Plot Merge Accuracy
-ggplot(data=learning_curves%>%mutate(model=ifelse(model=="knn","KNN","DT")),
-       aes(days/30,mean_accuracy))+
-    geom_line(aes(linetype=model),size=1.2)+xlab("Training duration (months)")+ylab("Model overall accuracy (OAcc)")+labs(linetype="Models")+
-    scale_x_continuous(breaks = seq(0, max(learning_curves$days/30)))+
-    scale_y_continuous(breaks = seq(0, 1, by = 0.1))+
-    facet_wrap(~wireless+wakeupfor)+expand_limits(x = 0, y = 0)+
-    th()+
-    theme(panel.grid.minor = element_blank(),
-          legend.position = c(0.38,0.68))
-ggsave("figures/months_accuracy.pdf",width=8.5,height=6)
-
-
-########## Energy and delta with raw policies ##########
-npolicies=4
-## First we extended the number of seed to cover the entire duration of the training
-data_seed_energy=rbind(data_seed,
-                           data_seed%>%mutate(seed=seed+200),
-                           data_seed%>%mutate(seed=seed+400),
-                           data_seed%>%mutate(seed=seed+600)) # Almost same as if each experiment run 4 times more seed seed
-## Compute the cumulative energy of each policies in each configuration accross the $npolicies*200 days
-data_seed_energy=data_seed_energy%>%group_by(wireless,wakeupfor,simkey)%>%mutate(energy=cumsum(energy),setup=paste0(wireless," ",wakeupfor,"s"),days=seed)
-## Now sum coverage of each $npolicies days (like in the energy data frame)
-data_seed_energy=data_seed_energy%>%group_by(wireless,wakeupfor,simkey)%>%mutate(grp=ceiling(days/npolicies))%>%group_by(wireless,wakeupfor,simkey,grp)%>%mutate(coverage=cumsum(coverage))%>%filter(days%%npolicies==0)
-## Now filter the data
-data_seed_energy=data_seed_energy%>%filter(days %in% !!energy$days)
-## Compute the delta data
-energy_coverage_delta=data_seed_energy%>%
-    full_join(energy,by=c("days","wireless","wakeupfor"),suffix=c("","_training"))
-energy_coverage_delta=energy_coverage_delta%>%group_by(wireless,wakeupfor)%>%summarize(delta_energy=energy-energy_training,simkey=simkey,days=days,delta_coverage=(coverage-coverage_training)/npolicies,coverage=coverage/npolicies,coverage_training=coverage_training/npolicies) # delta_coverage divide by $npolicies because we want the average per day (coverage is measure every $npolicies days (round-robin of $npolicies policies))
-
-
-write("wireless,wakeupfor,policy,slope,intercept,delta_coverage,coverage,coverage_training,latex","figures/delta_energy_coverage.csv")
-energy_coverage_delta%>%group_by(wireless,wakeupfor,simkey)%>%group_walk(function(data,grp){
-    grp=as.list(grp)
-    reg=lm(delta_energy ~ days,data)
-    slope=round(as.numeric(reg$coefficients["days"]),digits=0)
-    intercept=round(as.numeric(reg$coefficients[1]),digits=0)
-    mean_delta_coverage=round(mean(data$delta_coverage),digits=1)
-    mean_coverage=round(mean(data$coverage),digits=1)
-    mean_coverage_training=round(mean(data$coverage_training),digits=1)
-    print(paste0("Wireless=",grp$wireless," Wakeupfor=",grp$wakeupfor," Policy=",grp$simkey," Slope=",slope," Intercept=",intercept," Delta Coverage=",mean_delta_coverage))
-    write(paste(grp$wireless,grp$wakeupfor,grp$simkey,slope,intercept,mean_delta_coverage,mean_coverage,mean_coverage_training,paste0(r"("$\mathbf{s=)",slope,",c_p=",mean_coverage,",c_t=",mean_coverage_training,r"(}$")"),sep=","),"figures/delta_energy_coverage.csv",append=T)
-})
-
-ggplot(energy_coverage_delta,aes(days/30,delta_energy/1e3,color=simkey,shape=simkey))+
-    geom_line(size=1.2)+ylab(TeX("Delta in $E_{total}$ (kJ)"))+xlab("Training duration (months)")+
-    facet_wrap(~wireless+wakeupfor,scale="free")+
-    th()+theme(legend.position=c(0.61,0.97))+labs(color="Classes colors")
-ggsave("figures/delta_energy_training.pdf",height=6,width=10)
-
-ggplot(energy_coverage_delta,aes(days/30,delta_coverage,color=simkey))+
-    geom_line(size=1.2)+ylab("Delta in network coverage")+xlab("Training duration (months)")+
-    facet_wrap(~wireless+wakeupfor,scale="free")+
-    th()+theme(legend.position="top")+labs(color="Classes colors")
-ggsave("figures/delta_coverage_training.pdf",width=9)
-
-## ggplot(data=energy,aes(days/30,energy/1e6,group=setup,fill=setup))+
-##     geom_bar(stat="identity",position="dodge")+
-##     labs(fill="Wireless and Uptime")+
-##     scale_x_continuous(breaks = seq(0, max(energy$days/30)))+
-##     xlab("Training duration (months)")+ylab("Energy consumption (MJ)")+
-##     th()+theme(legend.position=c(0.12,0.75))
-## ggsave("figures/days_energy.pdf",width=8.5,height=4)
-
-
-