diff --git a/dummy-vars-playground.R b/dummy-vars-playground.R
index 3db3bc1..d956522 100644
--- a/dummy-vars-playground.R
+++ b/dummy-vars-playground.R
@@ -1,24 +1,83 @@
 library(tidyverse)
 library(caret)
 library(here)
-
+library(inspectdf)
+library(glmnet)
+library(ROSE)
 
 rm(seqs)
 load(here("notebooks/data/nback_seqs.Rd"))
 
 set.seed(42)
 
-seqs.dummy <- data.frame(predict(dummyVars(~.,seqs,fullRank = T),seqs)) %>%
-  filter(!is.na(correctTRUE), !is.na(rt))
+# 1. dummy vars
+# INPUTS : seqs
+# OUTPUTS: seqs.dmy
 
-inspect_num(seqs.dummy)
-inspect_na(seqs.dummy,show_plot = T)
+seqs <- seqs %>%
+  filter(!is.na(correct) & !is.na(rt)) %>%
+  mutate(correct = factor(as.numeric(correct), labels=c("NO","YES"))) %>%
+  mutate(stimulus = factor(stimulus)) %>%
+  mutate(stimulus_type = factor(stimulus_type))
 
-#inspect_cor(seqs.dummy,show_plot = T)
 
-cor_matrix <- cor(seqs.dummy)
-cor_high <- findCorrelation(cor_matrix, 0.5)
-high_cor_remove <- row.names(cor_matrix)[cor_high]
-#FIXME remove by column name
-seqs.uncorr <- seqs.dummy %>% select(-high_cor_remove)
-```
\ No newline at end of file
+table(seqs$stimulus)
+
+train.indices <- createDataPartition(seqs$correct, p = .8, list =FALSE)
+
+
+seqs.train.balanced <- seqs[train.indices,]
+seqs.train <- ROSE(correct ~ ., data = seqs.train.balanced)$data
+
+seqs.train.x <- model.matrix(correct ~ stimulus + stimulus_type + n, seqs.train)[,-1]
+seqs.train.y <- seqs.train$correct
+
+seqs.test  <- seqs[-train.indices,]
+seqs.test.x <-  model.matrix(correct ~ stimulus + stimulus_type + n, seqs.test)[,-1]
+seqs.test.observed_y <- seqs.test$correct
+  
+# model <- cv.glmnet(seqs.train.x,
+#                    seqs.train.y,
+#                    alpha = 1,
+#                    nfolds = 5,
+#                    family = "binomial",
+#                    type.measure = "auc")
+# 
+# model$lambda.min
+
+ctrl <- trainControl(method="cv",
+                     number=5, 
+                     classProbs=T,
+                     summaryFunction=twoClassSummary)
+
+# glmnet tune
+tune <- expand.grid(alpha = 0:1, lambda = seq(0, 0.01, length = 100),ncomp=1:10)
+
+# pls tune
+tune <- expand.grid(ncomp=1:10)
+
+model <- train(seqs.train.x,
+               seqs.train.y, 
+               method = "pls",
+               family = "binomial",
+               metric = "ROC",
+               preProc = c("center", "scale"),
+               tuneGrid = tune,
+               trControl = ctrl)
+
+model$bestTune
+plot(model)
+
+seqs.test.y <- model %>% predict(seqs.test.x)
+
+confusionMatrix(seqs.test.y, seqs.test.observed_y)
+
+# RT
+# data.frame(
+#   RMSE = RMSE(y.test, seqs.test$correct),
+#   Rsquare = R2(y.test, seqs.test$correct)
+# )
+
+
+#dmy <- dummyVars(~.-stimulus-stimulus_type,seqs,fullRank = T)
+#dmy.rt <- dummyVars(~correct+stimulus_type,seqs)