Update

2 files changed, 8 insertions, 5 deletions

diff --git a/analysis/figures/f1_scores_offline.csv b/analysis/figures/f1_scores_offline.csv
index 108b671..fa754ff 100644
--- a/analysis/figures/f1_scores_offline.csv
+++ b/analysis/figures/f1_scores_offline.csv
@@ -1,3 +1,3 @@
-model,f1_baseline,f1_hint,f1_extended,f1_hintandextended
-knn,0.88,NA,0.89,0.91
-tree,0.93,NA,0.86,0.92
+model,f1_baseline,f1_hint,f1_extended,f1_hintandextended,accuracy
+knn,0.88,NA,0.89,0.91,0.81
+tree,0.93,NA,0.86,0.92,0.83
diff --git a/analysis/learning.R b/analysis/learning.R
index ff31d33..684dc7b 100644
--- a/analysis/learning.R
+++ b/analysis/learning.R
@@ -101,14 +101,17 @@ build_models=function(ignore_hint=TRUE){
         ## 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)))
+        accuracy_knn=sum(test_set$simkey==knn_predictions)/length(test_set$simkey)
+        accuracy_tree=sum(test_set$simkey==tree_predictions)/length(test_set$simkey)
+        list(cbind(tibble(model=c("knn","tree")),rbind(f1_knn,f1_tree),tibble(accuracy=c(accuracy_knn,accuracy_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))
+        f1_hintandextended=mean(f1_hintandextended),
+        accuracy=mean(accuracy))
     write.csv(perfs,"figures/f1_scores_offline.csv",quote=FALSE,row.names=FALSE)
               
     ## Return models