10_demographics.Rmd

---
title: "Demographics"
output: html_document
---

This script is solely for displaying the demographics of the data.

We first declare ALL libraries up here. We make sure to have dplyr be the last one declared to prevent any errors.

```{r}
suppressWarnings(library(plyr))
suppressWarnings(library(ggplot2))
suppressWarnings(library(ggthemr))
library(tidyverse)

ggthemr('fresh', text_size = 20)
```

# Reading and Formatting the Data

Let's load the data.

```{r}
demo.sdat <- read_csv("z_demographics_data.csv")[,-1]
head(demo.sdat)
```

Group the participants based on their BMI according to known groupings.

```{r}
demo.sdat$bmi.group <- cut(demo.sdat$bmi, c(0,18.5,25,30,Inf))

levels(demo.sdat$bmi.group)[levels(demo.sdat$bmi.group)=="(0,18.5]"] <- "Underweight"
levels(demo.sdat$bmi.group)[levels(demo.sdat$bmi.group)=="(18.5,25]"] <- "Normal"
levels(demo.sdat$bmi.group)[levels(demo.sdat$bmi.group)=="(25,30]"] <- "Overweight"
levels(demo.sdat$bmi.group)[levels(demo.sdat$bmi.group)=="(30,Inf]"] <- "Obese"
```


# Demographics

In each of the plots below, we first summarize the data. For instance, for gender, we get the total number of participants who identified as male and female.

## Gender

It's pretty even so easy.

```{r, fig.width=4, fig.height=4}
sdat2 <- demo.sdat %>%
  group_by(gender) %>%
  summarise(n = n())
sdat2

ggplot(sdat2, aes(x=gender, y=n)) + 
  geom_bar(stat="Identity") + 
  xlab("") + ylab("Number of Participants") +
  scale_y_continuous(expand = c(0,0)) + 
  theme(axis.line.x = element_blank(), 
        axis.ticks = element_blank(), 
        panel.grid.major.y = element_line(size=0.5, linetype='solid'), 
        axis.line.y = element_blank(), 
        panel.grid.major.x = element_blank())
```

## Age

Participants gave their ages in age bins (e.g., 18-25). We get the number of participants in each age bin.

```{r, fig.width=8, fig.height=4}
sdat2 <- data.frame(demo.sdat) %>%
  group_by(age) %>%
  summarise(n = n())
sdat2

ggplot(sdat2, aes(x=age, y=n)) + 
  geom_bar(stat="Identity") + 
  xlab("Age") + ylab("Number of Participants") + #ggtitle("Number of Participants by Age") +
  scale_y_continuous(expand = c(0,0)) + 
  theme(axis.line.x = element_blank(), 
        axis.ticks = element_blank(), 
        panel.grid.major.y = element_line(size=0.5, linetype='solid'), 
        axis.line.y = element_blank(), 
        panel.grid.major.x = element_blank())
```


## BMI

We first plot the raw BMI values and then group them by underweight, overweight, obese, etc. 

```{r, fig.width=8, fig.height=4}
ggplot(demo.sdat, aes(x=bmi)) + 
  geom_histogram(bins=20) +
  xlab("BMI") + ylab("Number of Participants") + #ggtitle("Number of Participants by Age") +
  scale_y_continuous(expand = c(0,0)) + 
  theme(axis.line.x = element_blank(), 
        axis.ticks = element_blank(), 
        panel.grid.major.y = element_line(size=0.5, linetype='solid'), 
        axis.line.y = element_blank(), 
        panel.grid.major.x = element_blank())
```

```{r, fig.width=8, fig.height=4}
sdat2 <- data.frame(demo.sdat) %>%
  group_by(bmi.group) %>%
  summarise(n = n())
sdat2

ggplot(sdat2, aes(x=bmi.group, y=n)) + 
  geom_histogram(stat ="Identity") +
  xlab("BMI Group") + ylab("Number of Participants") + #ggtitle("Number of Participants by Age") +
  scale_y_continuous(expand = c(0,0)) +
  theme(axis.line.x = element_blank(), 
        axis.ticks = element_blank(), 
        panel.grid.major.y = element_line(size=0.5, linetype='solid'), 
        axis.line.y = element_blank(), 
        panel.grid.major.x = element_blank())
```