diff options
Diffstat (limited to 'analysis/learning.R')
| -rw-r--r-- | analysis/learning.R | 103 |
1 files changed, 92 insertions, 11 deletions
diff --git a/analysis/learning.R b/analysis/learning.R index d21b8cd..ff31d33 100644 --- a/analysis/learning.R +++ b/analysis/learning.R @@ -1,8 +1,10 @@ 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} @@ -24,16 +26,95 @@ 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=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) +} + +build_models=function(ignore_hint=TRUE){ + ## 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$wireless]) + if(ignore_hint){ + data_ml=data_ml%>%filter(simkey!="hint") + } + train_set=data_ml%>%sample_frac(0.8) # 80% of the data + test_set=data_ml%>%suppressMessages(anti_join(train_set)) # 20% of the data + + ## KNN predict function + knn_fn=function(inputs){ + as.vector(knn(train=train_set%>%select(-simkey),test=inputs%>%select(-simkey),cl=train_set$simkey,k=10)) + } + + ## Decision tree + tree=rpart( + simkey ~ wireless + wakeupfor + energy + coverage, + data=train_set, + method="class", + minsplit=60, + minbucket=1) + ## Tree predict function + tree_fn=function(inputs){ + as.vector(predict(tree,newdata=inputs%>%select(-simkey),type="class")) + } + + ## Build models + models=list(predict_knn=knn_fn,predict_tree=tree_fn) + + ## Computer performances + perfs=sapply(seq(1,20),function(i){ + ## 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$wireless]) + if(ignore_hint){ + data_ml=data_ml%>%filter(simkey!="hint") + } + train_set=data_ml%>%sample_frac(0.8) # 80% of the data + test_set=data_ml%>%suppressMessages(anti_join(train_set)) # 20% of the data + + ## KNN + knn_predictions=as.vector(knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=10)) + ## Decision tree + tree=rpart( + simkey ~ wireless + wakeupfor + energy + coverage, + data=train_set, + method="class", + minsplit=60, + minbucket=1) + tree_predictions=as.vector(predict(tree,newdata=test_set%>%select(-simkey),type="class")) + + ## Prefs + f1_knn=F1_Score2(test_set$simkey,knn_predictions) + f1_tree=F1_Score2(test_set$simkey,tree_predictions) + list(cbind(tibble(model=c("knn","tree")),rbind(f1_knn,f1_tree))) + }) + perfs=do.call("rbind",perfs)%>%mutate_if(is.numeric, ~round(.,digits=2)) + perfs=perfs%>%group_by(model)%>%summarize( + f1_baseline=mean(f1_baseline), + f1_hint=mean(f1_hint), + f1_extended=mean(f1_extended), + f1_hintandextended=mean(f1_hintandextended)) + write.csv(perfs,"figures/f1_scores_offline.csv",quote=FALSE,row.names=FALSE) + + ## Return models + models +} + generate_inputs=function(ignore_hint=FALSE) { ## Prepare data for traning set.seed(1) # Reproducibility @@ -61,7 +142,7 @@ generate_inputs=function(ignore_hint=FALSE) { minbucket=1) tree_predictions=predict(tree,newdata=test_set%>%select(-simkey),type="class") tree_cont_table=table(tree_predictions,test_set$simkey) - tree_accuracy=round((sum(diag(tree_cont_table)/sum(rowSums(tree_cont_table))))*100) + tree_accuracy=(sum(diag(tree_cont_table)/sum(rowSums(tree_cont_table)))) tree_prop_table=round(prop.table(tree_cont_table),digits=2) ## Elbow plot @@ -69,12 +150,12 @@ generate_inputs=function(ignore_hint=FALSE) { knn_predictions=knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$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_accuracy=(sum(diag(knn_cont_table)/sum(rowSums(knn_cont_table)))) 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))) + ggplot(data=elbow_data,aes(k,accuracy))+geom_point()+geom_line()+ggtitle(paste("K-elbow for with NoHint to",as.character(ignore_hint)))+ylim(c(0,1)) ggsave(paste0("figures/knn_elbow_NoHintIs",as.character(ignore_hint),".pdf")) ## Prints @@ -126,5 +207,5 @@ generate_inputs=function(ignore_hint=FALSE) { } ## Generate inputs -generate_inputs(FALSE) -generate_inputs(TRUE) +#generate_inputs(FALSE) +#generate_inputs(TRUE) |