---
title: "DataPreparationAndCleaning"
author: "Write your name here"
date: "`r Sys.Date()`"
output: 
  pdf_document:
    highlight: tango
header-includes:
   - \usepackage{fvextra}
   - \DefineVerbatimEnvironment{Highlighting}{Verbatim}{commandchars=\\\{\},breaklines}
---

# 1. Preparations

## 1.1 Load the libraries

```{r}
library(dplyr)
library(tidyr)
library(ez)
```

## 1.2 Load the data

```{r}
load("CHC9012_DataImportedFromPCIbex.RData")
```


## 1.3 Check the data

```{r}
str(data)
```


# 2. Prepare the dataset

## 2.1 Remove unnecessary colum

```{r}
data$Controller.name <- NULL
data$Inner.element.number <- NULL
data$Latin.Square.Group <- NULL
data$Comments <- NULL
```

## 2.2 Rename columns

```{r}
names(data)

names(data)[1] <- "ID_1_TimeReceived"
names(data)[2] <- "ID_2_IP"
```


## 2.3 Select the rows you need

```{r}
data2 <- data %>%
  filter(Label == "Experiment")

data2 <- data2 %>%
  filter(Parameter != "_Header_")
```

## 2.4 Add a "Reaction time" column

```{r}
##Calculate reaction time
RT_Prep1 <- data2 %>%
  filter(Parameter == "Choice" | Value == "Start")

RT_Prep1$Index <- ifelse(RT_Prep1$Value == "Start",
                         "Start",
                         "Choice")

RT_Prep1$PennElementType <- NULL
RT_Prep1$PennElementName <- NULL
RT_Prep1$Parameter <- NULL
RT_Prep1$Value <- NULL

RT_Prep2 <- spread(data = RT_Prep1, Index, EventTime)

RT_Prep2$Choice <- as.numeric(RT_Prep2$Choice)
RT_Prep2$Start <- as.numeric(RT_Prep2$Start)
RT_Prep2$RT <- RT_Prep2$Choice - RT_Prep2$Start

data3 <- data2 %>%
  filter(Parameter %in% "Choice")

data3 <- data3 %>%
  left_join(RT_Prep2 %>% select(ID_1_TimeReceived, ID_2_IP, ItemNo, RT), 
            by = c("ID_1_TimeReceived", "ID_2_IP", "ItemNo"))
```


## 2.5 Change the nature of the variables

```{r}
## Transform to "factors" (or "groups")
data3$ID_1_TimeReceived <- as.factor(data3$ID_1_TimeReceived)
data3$ID_2_IP <- as.factor(data3$ID_2_IP)
data3$ItemNo <- as.factor(data3$ItemNo)
data3$Condition <- as.factor(data3$Condition)
data3$Group <- as.factor(data3$Group)
data3$UserDegree <- as.factor(data3$UserDegree)

## Transform to numeric
data3$Order.number.of.item <- as.numeric(data3$Order.number.of.item)
data3$Value <- as.numeric(data3$Value)
data3$UserAge <- as.numeric(data3$UserAge)
data3$RT <- as.numeric(data3$RT)
```

## 2.6 Final removal of unnecessary columns

```{r}
str(data3)

data3$Label <- NULL
data3$PennElementType <- NULL
data3$PennElementName <- NULL
data3$Parameter <- NULL
data3$EventTime <- NULL

str(data3)
```

## 2.7 Add information (The actual sentences)

```{r}
material <- read.csv("~/Documents/CHC9012_Spring2026/PreprocessingAnalysesR/material.csv")
material$ItemNo <- as.factor(material$ItemNo)

data3 <- data3 %>%
  left_join(material %>% select(ItemNo, Sentence), 
            by = "ItemNo")
```


# 3. Check that everything is in order

```{r}
# Same number of item per condition for each participant? (should be '15')
ezDesign(data3, ID_1_TimeReceived, Condition)

# Which participants share the same IP? (hint that this could be the same participant filling the questionnaire twice)
ezDesign(data3, ID_1_TimeReceived, ID_2_IP)

# Number of times an item appeared by participant (should be '1')
ezDesign(data3, ID_1_TimeReceived, ItemNo)

# Were the items well dispatched in the two lists?
ezDesign(data3, ItemNo, Group)

# Were the participants well dispatched in the two lists? (should be '30')
ezDesign(data3, ID_1_TimeReceived, Group)
```

# 4. Save the prepared dataset

```{r}
save(data3,
     file = "CHC9012_PCIbexDataPrepared.RData")
```