---
title: "DataExploration"
author: "Aymeric Collart"
date: "`r Sys.Date()`"
output: html_document
---

# 1. Prepare the environment

```{r}
load(file = "CHC9012_PCIbexDataPrepared.RData")
```

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

# 2. First look at the data

## 2.1 Look based on the experimental design

```{r}
plot(data3$Value ~ data3$Condition)
```

```{r}
plot(data3$RT ~ data3$Condition)
plot(data3$RT ~ data3$Condition, outline = FALSE)
```

## 2.2 Look by participant and by item

```{r}
plot(data3$Value ~ data3$ID_1_TimeReceived)
```

```{r}
plot(data3$RT ~ data3$ID_1_TimeReceived)
plot(data3$RT ~ data3$ID_1_TimeReceived, outline = FALSE)
```

```{r}
plot(data3$Value ~ data3$ItemNo)
```

```{r}
plot(data3$RT ~ data3$ItemNo)
plot(data3$RT ~ data3$ItemNo, outline = FALSE)
```

## 2.3 Look at the background of the participants

```{r}
## Number of participants
length(levels(data3$ID_1_TimeReceived))
```

```{r}
## Age of participants
summary(data3$UserAge)
```

```{r}
## Degree of participants
DegreePart <- subset(data3, select = c(ID_1_TimeReceived, UserDegree))
DegreePart <- unique(DegreePart)
table(DegreePart$UserDegree)
```


# 3. Cleaning the dataset

## 3.1 How to identify non-valid participants?

### 3.1.1 Identification by RT

```{r}
plot(data3$RT ~ data3$ID_1_TimeReceived, outline = FALSE)

PartMeanRT <- aggregate(RT ~ ID_1_TimeReceived,
                        data = data3,
                        FUN = mean)

print(PartMeanRT)
```

```{r}
data_QuickPart <- subset(PartMeanRT, RT < 1000)
data_QuickPart_FullData <- subset(data3,
                                  ID_1_TimeReceived %in% data_QuickPart$ID_1_TimeReceived)

plot(data_QuickPart_FullData$RT ~ data_QuickPart_FullData$ID_1_TimeReceived, outline = FALSE)
plot(data_QuickPart_FullData$Value ~ data_QuickPart_FullData$Condition)
```

```{r}
data_OtherPart <- subset(PartMeanRT, RT > 1000)
data_OtherPart_FullData <- droplevels(subset(data3,
                                             ID_1_TimeReceived %in% data_OtherPart$ID_1_TimeReceived))

plot(data_OtherPart_FullData$RT ~ data_OtherPart_FullData$ID_1_TimeReceived, outline = FALSE)
plot(data_OtherPart_FullData$Value ~ data_OtherPart_FullData$Condition)
```

### 3.1.2 Identification by IP

```{r}
ezDesign(data3, ID_1_TimeReceived, ID_2_IP)

ezDesign(data_QuickPart_FullData, ID_1_TimeReceived, ID_2_IP)
ezDesign(data_OtherPart_FullData, ID_1_TimeReceived, ID_2_IP)
```

### 3.1.3 Identification by looking at individual participants

```{r}
IndPart <- subset(data_OtherPart_FullData,
                  ID_1_TimeReceived == levels(data_OtherPart_FullData$ID_1_TimeReceived)[9])

plot(IndPart$Value ~ IndPart$Condition)
```

```{r}
## One participant very different
levels(data_OtherPart_FullData$ID_1_TimeReceived)[3]

IndPart <- subset(data_OtherPart_FullData,
                  ID_1_TimeReceived == levels(data_OtherPart_FullData$ID_1_TimeReceived)[3])
plot(IndPart$Value ~ IndPart$Condition)
plot(IndPart$RT ~ IndPart$ItemNo)
```


## 3.2 How to identify non-valid trials?


### 3.2.1 Absolute values

```{r}
data_OtherPart_CleanAbsolute <- subset(data_OtherPart_FullData, RT > 200 & RT < 20000)
```

### 3.2.2 Relative values

```{r}
# Calculate the mean per Participant and Condition
data_OtherPart_CleanAbsolute$m_rt <- ave(data_OtherPart_CleanAbsolute$RT, 
                                         data_OtherPart_CleanAbsolute$ID_1_TimeReceived, 
                                         data_OtherPart_CleanAbsolute$Condition, 
                                         FUN = mean)

# 2. Calculate the SD per Participant and Condition
data_OtherPart_CleanAbsolute$sd_rt <- ave(data_OtherPart_CleanAbsolute$RT, 
                                          data_OtherPart_CleanAbsolute$ID_1_TimeReceived, 
                                          data_OtherPart_CleanAbsolute$Condition, 
                                          FUN = sd)

# 3. Subset the data to remove outliers
data_OtherPart_CleanAbsoluteRelative <- subset(data_OtherPart_CleanAbsolute, 
                                               RT >= (m_rt - 2.5 * sd_rt) & 
                                                 RT <= (m_rt + 2.5 * sd_rt))
```

### 3.2.3 Calculate the number of trials removed

```{r}
FullData_NbTrials <- nrow(data_OtherPart_FullData)
TrimmedData_NbTrials <- nrow(data_OtherPart_CleanAbsoluteRelative)

# Number of trimmed trials
NbTrimmedTrials <- FullData_NbTrials - TrimmedData_NbTrials
NbTrimmedTrials

# Proportion (%)
NbTrimmedTrials*100/FullData_NbTrials
```


# 4. Exploration of the clean results

## 4.1 Factorial analysis: Based on the experimental design

```{r}
plot(data_OtherPart_CleanAbsoluteRelative$Value ~ data_OtherPart_CleanAbsoluteRelative$Condition)

summarySE(data_OtherPart_CleanAbsoluteRelative,
          measurevar = "Value",
          groupvars = "Condition")

plot(data_OtherPart_CleanAbsoluteRelative$RT ~ data_OtherPart_CleanAbsoluteRelative$Condition, outline = FALSE)

summarySE(data_OtherPart_CleanAbsoluteRelative,
          measurevar = "RT",
          groupvars = "Condition")
```

## 4.2 Exploratory analysis: Look at trials in specific conditions

### 4.2.1 Look at the grammatical condition

```{r}
data_Grammatical <- droplevels(subset(data_OtherPart_CleanAbsoluteRelative,
                                        Condition == "Grammatical"))

plot(data_Grammatical$Value ~ data_Grammatical$ItemNo)
plot(data_Grammatical$RT ~ data_Grammatical$ItemNo)
```

### 4.2.2 Look at the Ungrammatical condition

```{r}
data_Ungrammatical <- droplevels(subset(data_OtherPart_CleanAbsoluteRelative,
                                        Condition == "Ungrammatical"))

plot(data_Ungrammatical$Value ~ data_Ungrammatical$ItemNo)
plot(data_Ungrammatical$RT ~ data_Ungrammatical$ItemNo)
```

```{r}
# Exploration of divergent ungrammatical sentences
data_Ungrammatical_OutlierValue <- subset(data_Ungrammatical, Value > 4)

data_Ungrammatical_OutlierValue_Summary <- droplevels(subset(data_Ungrammatical_OutlierValue,
                                                  select = c(ID_1_TimeReceived,
                                                             ItemNo,
                                                             Sentence)))
data_Ungrammatical_OutlierValue_Summary <- unique(data_Ungrammatical_OutlierValue_Summary)
data_Ungrammatical_OutlierValue_Overview <- table(data_Ungrammatical_OutlierValue_Summary$ItemNo)

data_Ungrammatical_OutlierValue_Overview
```

```{r}
# Identify which ungrammatical sentences
data_Ungrammatical_OutlierValue_Overview <- as.data.frame(data_Ungrammatical_OutlierValue_Overview)
names(data_Ungrammatical_OutlierValue_Overview)[1] <- "ItemNo"

data_Ungrammatical_OutlierValue_Overview <- droplevels(subset(data_Ungrammatical_OutlierValue_Overview, Freq > 2))

data_Ungrammatical_OutlierValue_Overview <- left_join(data_Ungrammatical_OutlierValue_Overview, 
                                                      data_Ungrammatical, 
                                                      by = "ItemNo")
OutlierUngrammaticalSentences <- unique(data_Ungrammatical_OutlierValue_Overview$Sentence)
OutlierUngrammaticalSentences
```