diff --git a/ccn2019.rev3.Rmd b/ccn2019.rev3.Rmd
index d286a1c..9f38d9b 100644
--- a/ccn2019.rev3.Rmd
+++ b/ccn2019.rev3.Rmd
@@ -1,11 +1,11 @@
 ```{r setup, message=FALSE, include=FALSE, paged.print=FALSE}
+#! ===============================================
+#! load required packages
+
 library(ggplot2)
 library(tidyverse)
 library(stringi)
 library(pls)
-#library(plsRglm)
-#library(plsdof)
-library(pls)
 library(caret)
 library(here)
 library(tsibble)
@@ -18,9 +18,13 @@
 
 ```{r preprocessing}
 
+#! ===============================================
+#! load data set and set running window size
 load(here('notebooks/data/CL2015.RData'))
 window_size <- 8
 
+#! ===============================================
+#! A function to mark lures in a sequence
 with_lures <- function(stimulus, stimulus_type, n) {
   sapply(1:length(stimulus), function(i) {
     lures <- c(as.character(stimulus[i-n-1]), as.character(stimulus[i-n+1]))
@@ -31,6 +35,9 @@
   })
 }
 
+#! ===============================================
+#! Preprocess data set to add t,tl,l,ll,u,ul,s,sl,a,al
+#! a and al are respectively accuracy and recent accuracy
 seqs <- NB %>%
   group_by(participant, block, condition) %>%
   mutate(n = ifelse(condition=='2-back',2,3)) %>%
@@ -55,25 +62,30 @@
   ungroup() %>%
   select(-participant,-block,-condition)
 
+#! ===============================================
+#! visualize correlations
 inspect_cor(seqs %>% unnest(local_stats), show_plot = T)
-#inspect_cor(NB,show_plot = T)
 ```
 
 ```{r models}
+#! ===============================================
+#! prepare data for modeling (remove na, etc)
+#! it also restructures "correct" column to avoid caret errors. C stands for "CORRECT", and I is "INCORRECT"
 data <- seqs %>% 
   unnest(local_stats) %>%
-  # restructure correct column to avoid caret errors
-  # C stands for "CORRECT", and I is "INCORRECT"
   mutate(correct=factor(as.numeric(correct),labels=c("C","I"))) %>%
   filter(!is.na(correct), !is.na(rt))
 
+#! ===============================================
+#! Prepare train and test partials
 shuff <- sample(nrow(data))
 split <- nrow(data) * 0.8
 
-
 train_data <- data[1:split,]
 test_data <- data[(split+1):nrow(data),]
 
+#! ===============================================
+#! training parameters for the PLS models
 plsTrControl <- trainControl(
     method = "cv",
     number = 5
@@ -93,7 +105,7 @@
 plot(model_pls_accuracy)
 
 # PLS variable importance
-varImp(model_pls_accuracy)
+plot(varImp(model_pls_accuracy), main="Accuracy - Variable Importance")
 
 
 #==================================================#
@@ -113,13 +125,12 @@
 plot(model_pls_rt)
 
 # PLS variable importance
-varImp(model_pls_rt)
-
+plot(varImp(model_pls_rt), main="RT - Variable Importance")
 
 predicted_rt_data <- predict(model_pls_rt, test_data)
 
+#FIXME
 confusionMatrix(predicted_rt_data,test_data$rt)
-
 colAUC(predicted_rt_data,test_data$rt, plotROC=T)
 
 #==================================================#
@@ -140,11 +151,13 @@
 )
 
 model_glm_correct
+varImp(model_glm_correct)
+
 
 predicted_correct_data <- predict(model_glm_correct, test_data, type="prob")
 
-confusionMatrix(test_data$correct, predicted_correct_data)
-
+#FIXME
+confusionMatrix(predicted_correct_data, test_data$correct)
 colAUC(predicted_correct_data, test_data$correct, plotROC=T)
 
 #==================================================#
@@ -161,7 +174,7 @@
 
 predicted_old_correct_data <- predict(model_glm_correct_old, test_data, type="prob")
 
+#FIXME
 confusionMatrix(test_data$correct, predicted_old_correct_data)
-
 colAUC(predicted_old_correct_data,test_data$correct, plotROC=T)
 ```