---
title: "PLS Training"
output: html_notebook
---

PLS:


```{r}
#detach("package:MASS","plsdof") # to avoid conflict with dplyr::select
library(tidyverse)
library(pls)

## 1. load sample data
#data <- read.csv("http://wiki.q-researchsoftware.com/images/d/db/Stacked_colas.csv")

rm(NB)
load("./data/CL2015.RData")
data <- NB
str(data)

## 2. clean data (remove brand and URLID)
data <- data %>% 
  mutate(n=ifelse(condition=='2-back', 2, 3)) %>%
  select(-condition,
         -stimulus,
         -block,
         -trial)
# %>%
#   rename(
#          ev.participant=participant,
#          ev.n=n,
#          ev.block=block,
#          ev.stimulus_type=stimulus_type,
#          rv.choice=choice,
#          rv.rt=rt,
#          rv.correct=correct
#          )

## 3. use cross validatation to find the optimal number of dimensions
pls.model = plsr(rt ~ ., data = data, validation = "CV")

## 3.1. find the model with lowest cv error
cv <- RMSEP(pls.model)
best_dims <- which.min(cv$val[estimate = "adjCV", , ]) - 1

## 4. rebuild the model
pls.model <- plsr(rt ~ ., data = data, ncomp = best_dims)

## 5. Sort, and visualize top coefficients
coefs <- coef(pls.model)

barplot(sort(coefs[,1,1], decreasing = T)[1:4])
```