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_inputs=function(ignore_hint=FALSE) {
    ## Prepare data for traning
    set.seed(1) # Reproducibility
    wireless_map=c("lora"=1,"nbiot"=2)
    data_ml=data_seed%>%select(-efficiency,-seed)%>%mutate(wireless=wireless_map[data_seed$wireless])
    if(ignore_hint){
        data_ml=data_ml%>%filter(simkey!="hint")
    }
    train_set=data_ml%>%sample_frac(0.8)     # 80% of the data
    test_set=data_ml%>%anti_join(train_set)  # 20% of the data

    ## 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)

    ## Elbow plot
    elbow_data=lapply(seq(1,10),function(kvalue){
        knn_predictions=knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=kvalue)
        ## KNN analysis
        knn_cont_table=table(knn_predictions,test_set$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)
        tibble(k=kvalue,accuracy=knn_accuracy)
    })
    elbow_data=do.call("rbind",elbow_data)
    ggplot(data=elbow_data,aes(k,accuracy))+geom_point()+geom_line()+ggtitle(paste("K-elbow for with NoHint to",as.character(ignore_hint)))
    ggsave(paste0("figures/knn_elbow_NoHintIs",as.character(ignore_hint),".pdf"))
    
    ## Prints
    print(paste0("Accuracy: KNN=",knn_accuracy,"% CART=",tree_accuracy,"%"))
    pdf(paste0("figures/tree_",as.character(ignore_hint),".pdf"))
    tree_plot=rpart.plot(tree,box.palette=as.list(viridis::viridis(4,begin=0.48)))
    silent_call=dev.off()
    ## Notes: KNN accuracy jump to 76% and CART to 80% accuracy without the hint policy

    ## Generate simulation inputs
    inputs=tibble(
        wakeupfor = c(60,180,60,180),
        wireless  = c("lora", "lora", "nbiot", "nbiot"))
    constraints=apply(inputs,1,function(row){
        wi=row["wireless"]
        wa=as.numeric(row["wakeupfor"])
        ## First extract energy/coverage boundaries
        min_energy=min((data_seed%>%filter(wireless==wi,wakeupfor==wa))$energy)
        max_energy=max((data_seed%>%filter(wireless==wi,wakeupfor==wa))$energy)
        min_coverage=min((data_seed%>%filter(wireless==wi,wakeupfor==wa))$coverage)
        max_coverage=max((data_seed%>%filter(wireless==wi,wakeupfor==wa))$coverage)
        ## Generate random points (10 per scenarios)
        n=100
        current_inputs=tibble(
            wireless=rep(wi,n),
            wakeupfor=rep(wa,n),
            energy_constraint=runif(n,min_energy,max_energy),
            coverage_constraint=round(runif(n,min_coverage,max_coverage)))
        predictions_knn=knn(train=train_set%>%select(-simkey),test=current_inputs%>%
                                                                  rename(energy=energy_constraint,coverage=coverage_constraint)%>%
                                                                  mutate(wireless=wireless_map[wireless]),cl=train_set$simkey,k=10)
        predictions_tree=predict(tree,newdata=current_inputs%>%
                                          rename(energy=energy_constraint,coverage=coverage_constraint)%>%
                                          mutate(wireless=wireless_map[wireless]),type="class")
        knn_final=tibble(cbind(current_inputs,tibble(simkey=predictions_knn,model="knn")))
        tree_final=tibble(cbind(current_inputs,tibble(simkey=predictions_tree,model="tree")))
        rbind(knn_final,tree_final)
    })
    inputs=do.call("rbind",constraints)%>%distinct()
    ## Dimension Energy/Coverage
    ggplot(data_seed%>%mutate(wakeupfor=as.character(wakeupfor)),
           aes(coverage,energy,color=simkey))+geom_point()+
        geom_point(data=inputs%>%mutate(wakeupfor=as.character(wakeupfor)),aes(coverage_constraint,energy_constraint),size=3,pch=5)+
        ggtitle("Dimension Energy/Coverage")+xlab("Coverage")+ylab("Sum of nodes energy consumption (J)")+
        facet_wrap(~wakeupfor+wireless,scale="free")
    ggsave(paste0("figures/random_inputs_NoHintIs",as.character(ignore_hint),".pdf"),width=15)
    write.csv(inputs,paste0("../inputs_NoHintIs",as.character(ignore_hint),".csv"),row.names=FALSE, quote=FALSE)

}

## Generate inputs
generate_inputs(FALSE)
generate_inputs(TRUE)