Refusal_Test_Graphs.Rmd

---
title: "DataFest"
author: "Derek Nakagawa"
date: "4/29/2022"
output: html_document
---

```{r setup, include=FALSE}
library(stringr)
library(ggplot2)
library(dplyr)
library(tidyverse)
library(stringi)
library(ggrepel)

mydata <- read_csv("logs.csv", guess_max = 2106600)

```

Creating different data tables for analysis

```{r setup, include=FALSE}
otherdata <- read.csv("S5_scores_cleaned.csv")


#-----------------------------------------------------------------------------------------------------
# Data Collecting for different schools
school_id <- mydata %>%
  select(school, player_id) %>%
  distinct()
yay <- merge(school_id, otherdata)

data_week <- yay %>%
  group_by(weeks) %>%
  summarise(
    count = n(),
    mean_val = mean(S5_mean)
     )

data_each_school <- yay %>%
  group_by(weeks, school) %>%
  summarise(
    count = n(),
    mean_val = mean(S5_mean)
     )


#-----------------------------------------------------------------------------------------------------
# Data Collecting for Schools with at least 2 participants
at_least_2_students <- data_each_school %>%
  filter(school == "0647" | school == "1827" | school == "3561" | school == "5340" | school == "7167" | school == "9691")


#-----------------------------------------------------------------------------------------------------
# Data Collecting for Ethnicity
ethnicity_data <- mydata[complete.cases(mydata$avatar_id),]

ethnicity2 <- ethnicity_data %>%
  select(avatar_id, player_id) %>%
  distinct()
merged_ethnicity <- merge(ethnicity2, otherdata)
merged_ethnicity

data_ethnicity <- merged_ethnicity %>%
  group_by(weeks, avatar_id) %>%
  summarise(
    count = n(),
    mean_val = mean(S5_mean)
     )


#------------------------------------------------------------------------------------------
# Data Collecting for Age
age_data <- mydata[complete.cases(mydata$avatar_age),]

age2 <- age_data %>%
  select(avatar_age, player_id) %>%
  distinct()
merged_age <- merge(age2, otherdata)

data_age <- merged_age %>%
  group_by(weeks, avatar_age) %>%
  summarise(
    count = n(),
    mean_val = mean(S5_mean)
     )



#------------------------------------------------------------------------------------------
# Data Collecting for Gender
length(unique(otherdata$player_id))

gender_data <- mydata[complete.cases(mydata$avatar_gender),]

gender2 <- gender_data %>%
  select(avatar_gender, player_id) %>%
  distinct()
merged_gender <- merge(gender2, otherdata)

data_gender <- merged_gender %>%
  group_by(weeks, avatar_gender) %>%
  summarise(
    count = n(),
    mean_val = mean(S5_mean)
     )



#----------------------------------------------------------------------------------------------
# Data Collecting for amount of time playing the game
num_player <- num_player[-length(num_player)]

weeks_data <- otherdata
weeks_data$max_weeks <- 0

new_table <- data.frame(
  player_id = NA, weeks = NA, S5_mean = NA, max_weeks = NA)

for( i in 1:length(num_player)){
  table <- weeks_data %>%
    filter(player_id == num_player[i])
  table$max_weeks <- max(table$weeks)
  new_table <- rbind(new_table, table)
}
new_table <- new_table[-1, ]

data_time <- new_table %>%
  group_by(weeks, max_weeks) %>%
  summarise(
    count = n(),
    mean_val = mean(S5_mean)
     )



```


Test Graphs to see if there is any correlations between ethnicity, gender, school, or amount of time playing the game.

```{r setup, include=FALSE}

# graph for all of the schools
ggplot(data_each_school, aes(x=weeks, y=mean_val, color = school)) +
  geom_point(stat = "identity")+
  geom_line() +
  facet_wrap( ~ school, ncol = 3) +
  geom_text(aes(label = count), vjust = 1.1, position = position_dodge(.9), size = 4) +
  labs(
    x = "Number of Weeks",
    y = "Mean Value of Refusal Test Scores",
    title = "How Do the Refusal Test Scores Change Over Time?",
    color = "School ID"
  )


# graph for schools larger than 2 students
ggplot(at_least_2_students, aes(x=weeks, y=mean_val, color = school)) +
  geom_point(stat = "identity")+
  geom_line() +
  facet_wrap( ~ school, ncol = 3) +
  geom_text(aes(label = count), vjust = 1.1, position = position_dodge(.9), size = 4) +
  labs(
    x = "Number of Weeks",
    y = "Mean Value of Refusal Test Scores",
    title = "How Do the Refusal Test Scores Change Over Time?",
    color = "School ID"
  )


# graph for etnicities
ggplot(data_ethnicity, aes(x=weeks, y=mean_val, color = avatar_id)) +
  geom_point(stat = "identity") +
  geom_line() +
  facet_wrap( ~ avatar_id, ncol = 2) +
  geom_text(aes(label = count), vjust = 1.3, position = position_dodge(.9), size = 4) +
  labs(
    x = "Number of Weeks",
    y = "Mean Value of Refusal Test Scores",
    title = "How Do the Refusal Test Scores Change Over Time?",
    color = "Ethnicity"
  )


# graph for gender
ggplot(data_gender, aes(x=weeks, y=mean_val, color = avatar_gender)) +
  geom_point(stat = "identity")+
  geom_line() +
  facet_wrap( ~ avatar_gender, ncol = 2) +
  geom_text(aes(label = count), vjust = 1.3, position = position_dodge(.9), size = 4) +
  labs(
    x = "Number of Weeks",
    y = "Mean Value of Refusal Test Scores",
    title = "How Do the Refusal Test Scores Change Over Time?",
    color = "Gender"
  )


# graph for time
ggplot(data_time, aes(x=weeks, y=mean_val, color = max_weeks)) +
  geom_point(stat = "identity")+
  geom_line() +
  facet_wrap( ~ max_weeks, ncol = 2) +
  geom_text(aes(label = count), vjust = 1.3, position = position_dodge(.9), size = 4) +
  labs(
    x = "Number of Weeks",
    y = "Mean Value of Refusal Test Scores",
    title = "How Do the Refusal Test Scores Change Over Time?",
    color = "Time"
  )



data_ethnicity


```


Actual Graph for the Presentation: Finding the average Drug Refusal Test Scores for different age groups across a span of weeks after playing Elm Story (teaches students about drug/alcohol abuse)

```{r setup}

# graph for ages
data_age$avatar_age <- rep(c("11 Year Old", "12 Year Old", "13 Year Old", "14 Year Old"), 5)
  
ggplot(data_age, aes(x=weeks, y=mean_val, color = avatar_age)) +
  geom_point(stat = "identity") +
  geom_line(size = 1) +
  scale_color_manual(values = c("#223127", "#9C0D38", "#CE5374", "#A14EE4")) +
  facet_wrap( ~ avatar_age, ncol = 2) +
  theme(legend.position = "none") +
  theme(strip.text.x = element_text(size = 12), axis.title = element_text(size = 11), plot.title = element_text(size = 18)) +
  geom_label_repel(aes(label = count),
                  box.padding   = 0.1, 
                  point.padding = 0.3) +
  labs(
    x = "Number of Weeks",
    y = "Mean Value of Refusal Test Scores",
    title = "How Does the Refusal Test Differ Between Ages?",
    color = "Age"
  )


```