Clean repo and debug setup.sh

6 files changed, 21 insertions, 12 deletions

diff --git a/README.md b/README.md
index 52a99f5..7e02742 100644
--- a/README.md
+++ b/README.md
@@ -1,10 +1,13 @@
 # loosely-policies-analytics
 
 ## Analysis folder
-- learning.R: contains two major functions:
+- offline.R: contains two major functions:
   - build_models: To generate K-fold cross-validation results (note that hyper-parameters for decisions tree is fixed (no validation set))
   - generate_inputs: generate the inputs for the simulations experiments + the decision tree plots
-- days.R: Implement the in-situ learning approach
+- in-situ.R: Implement the in-situ learning approach (Figure 4a 4b and 4c)
+    - For figure 4a and 4b we train the model with increasing amount of data from previous results as if we were using one policy per day (see section IV.A)
+    - For figure 4c, delta is generated by comparing using each policies in round-robin (one per days to perform the training)
+        to each previous paper results with single policy only (see paper section IV.A)
 
 Todo: remove minbucket=1 (does not impact the results)
 
diff --git a/analysis/days.R b/analysis/in-situ.R
index 93d478e..2d57666 100644
--- a/analysis/days.R
+++ b/analysis/in-situ.R
@@ -27,6 +27,8 @@ library("latex2exp")
 ## energy         [0,+inf)
 ## nDataRcv       [0,+inf)
 
+## WARNING: Goto line 138 first and set the boolean to T (populate the R environment with accuracy results) afterwhich you can set it to FALSE (save time)
+
 nseed=200
 nwakeupfor=2
 nwireless=2
@@ -75,7 +77,7 @@ generate_accuracy_for=function(ignore_hint=FALSE,seed_max=200,attempts_max=2,wrl
             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
+        test_set=data_ml%>%select(-seed)                               # build test_set
         #print(paste0("Test set ",NROW(test_set)))
         #print(paste0("Train set ",NROW(train_set)))
         ## KNN training
@@ -86,7 +88,7 @@ generate_accuracy_for=function(ignore_hint=FALSE,seed_max=200,attempts_max=2,wrl
         #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,
@@ -111,23 +113,24 @@ generate_accuracy_for=function(ignore_hint=FALSE,seed_max=200,attempts_max=2,wrl
 
 }
 
+########## Train models from seed 0 to seed 160 (this code assumes that each day, a given policy is used)
 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)
+    data_seed_for_energy=data_seed_for_energy%>%filter(wireless==!!wireless,wakeupfor==!!wakeupfor) # Note !! do unquote, here we select the proper scenario
 
     ## 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%)
+    for(i in seq(1,160,by=steps)){ # We stop at 80% of the data (this way test set is at least 20%) here 160 over 200 seeds
         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_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)) # days=i*npolicies since 1 policy only per day is used (see paper section IV.A)
         result=rbind(result,acc)
     }
-   list(accuracy=result%>%mutate(days=seed_max*npolicies), # Since 3 policies (since ignore_hint=TRUE)
+   list(accuracy=result%>%mutate(days=seed_max*npolicies), # Since 1 policy per days see L130
         energy=result_energy)
 }
 
diff --git a/analysis/learning.R b/analysis/offline.R
index da444d8..da444d8 100644
--- a/analysis/learning.R
+++ b/analysis/offline.R
diff --git a/simulations/.gitignore b/simulations/.gitignore
index a5fd42a..89d1606 100644
--- a/simulations/.gitignore
+++ b/simulations/.gitignore
@@ -1,6 +1,7 @@
 simulator
 libs/simgrid
 libs/rapidjson
+libs/*.tar*
 compile_commands.json
 platform.xml
 scenarios
diff --git a/simulations/Makefile b/simulations/Makefile
index 3ed792d..8702e66 100644
--- a/simulations/Makefile
+++ b/simulations/Makefile
@@ -7,7 +7,7 @@ CC := g++ $(addprefix -L , $(LIBS)) $(addprefix -I , $(INCLUDES))
 all: $(EXEC) $(basename $(notdir $(SCENARIOS)))
 
 $(EXEC): $(filter-out $(SCENARIOS), $(wildcard src/*))
-	$(CC) -lsimgrid $^ -o $@
+	$(CC) $^ -lsimgrid -o $@
 
 $(basename $(notdir $(SCENARIOS))): $(SCENARIOS)
 	$(CC) $^ -o $@
@@ -16,4 +16,4 @@ run: $(EXEC)
 	export LD_LIBRARY_PATH=$(addprefix :, $(LIBS)) && ./$(EXEC) 10 --cfg=network/bandwidth-factor:1.05 --cfg=network/model:CM02 -–cfg=network/crosstraffic:0
 
 clean:
-	-rm $(EXEC) $(basename $(notdir $(SCENARIOS)))
\ No newline at end of file
+	-rm $(EXEC) $(basename $(notdir $(SCENARIOS)))
diff --git a/simulations/libs/setup.sh b/simulations/libs/setup.sh
index 395a11e..14705f6 100755
--- a/simulations/libs/setup.sh
+++ b/simulations/libs/setup.sh
@@ -2,8 +2,10 @@
 
 set -e
 
-[ ! -e "simgrid" ] && git clone https://framagit.org/simgrid/simgrid
-[ ! -e "rapidjson"] && git clone https://github.com/Tencent/rapidjson
+[ ! -e "simgrid-v3.35.tar.bz2" ] && wget "https://framagit.org/simgrid/simgrid/-/archive/v3.35/simgrid-v3.35.tar.bz2?ref_type=tags" -O "simgrid-v3.35.tar.bz2"
+[ ! -e "simgrid" ] && tar -xf "simgrid-v3.35.tar.bz2" && mv "simgrid-v3.35" simgrid
+
+[ ! -e "rapidjson" ] && git clone --depth 1 https://github.com/Tencent/rapidjson
 
 cd simgrid
 mkdir -p build