titanic_data_visualizations.Rmd

---
title: "titanic_data_visualizations"
author: "Ghinwa Moujaes"
date: "15/03/2022"
output: html_document
---

```{r message=FALSE, warning=FALSE}
library(tidyverse)
library(ggplot2)
library(ggthemes)
library(dplyr)
```

```{r message=FALSE, warning=FALSE}
rm(list = ls())

df <- read_csv("../data/Titanic_Data/titanic.csv")
```

1. Percentage of Males vs. Percentage of Females
```{r}
windowsFonts(Times=windowsFont("TT Times New Roman"))


df %>% 
  group_by(Sex) %>% 
  summarise(count = n()) %>% 
  mutate(percentage = count/sum(count)) %>% 
  ggplot(aes(x = Sex, y = percentage)) + 
  geom_col(aes(fill = as.factor(Sex))) + 
  geom_text(aes(label = sprintf("%.1f%%", 100*percentage), y= percentage),  
            vjust = -1,
            hjust = 0.5,
            size = 5,
            col = "grey",
            fontface = "bold") +
  theme_classic() +
  theme(plot.title = element_text(hjust = 0.5, size = 16),
        axis.ticks.y = element_blank(),
       legend.position = "none") + 
  ylim(0, 1) + 
  labs(title = "Percentage of Female vs. Male Passengers on the Titanic", 
       x = "", 
       y = "") + 
  scale_x_discrete(labels = c("Female", "Male"))
```
```{r}
windowsFonts(Times=windowsFont("TT Times New Roman"))

df %>%  
  group_by(Survived, Sex) %>% 
  summarise(count = n()) %>% 
  ungroup() %>% 
  mutate(percentage = count/sum(count)*100) %>% 
  ggplot(aes(x = factor(Survived), y = percentage)) + 
  geom_col(aes(fill = factor(Sex)), position = "dodge", stat = "identity") + 
  theme_classic() + 
  labs(title = "Percentage of Survivors: Male vs. Female", 
       y = "", 
       x = "", 
       fill = "") + 
  theme(plot.title = element_text(hjust = 0.5, size = 14)) + 
  scale_y_continuous(expand = c(0, 0),
                     limits = c(0, 60)) + 
  scale_x_discrete(labels = c("Did not Survive", "Survived")) + 
  scale_fill_discrete(labels = c("Female", "Male")) + 
    geom_text(aes(label = sprintf("%.1f%%", percentage), y= percentage),  
            size = 4,
            col = "black",
            fontface = "bold",
            vjust = -0.5,
            hjust = c(1.75, -1, 1.75, -1))
```

```{r}
df %>% 
  ggplot(aes(x = Sex, y = Age)) + 
  geom_boxplot(outlier.color = NA) + 
  geom_point(aes(col = as.factor(Sex)),
             position = "jitter",
             alpha = 0.5) + 
  scale_x_discrete(labels = c("Female", "Male")) + 
  labs(title = "Age of Female vs. Male Passengers",
       x = "") + 
  theme_classic() + 
  theme(plot.title = element_text(hjust= 0.5), 
        legend.position = "None") + 
  scale_y_continuous(expand = c(0, 0),
                     limits = c(0, 90)) 
```

```{r}
df %>%
  ggplot(aes(x = Age, col = factor(Sex))) +
  geom_density() +
  facet_grid(Survived ~ Sex,
             labeller = labeller(Sex = c(female = "Female",
                                         male = "Male"),
                                 Survived = c("0" = "Did not Survive",                            
                                              "1" = "Survived")), 
             ) +
  theme_classic() +
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5)) +
  labs(x = "",
       y = "Density",
       title = "Age Distribution of Female vs. Male Survivors vs. Non-Survivors")

```

```{r}
df %>% 
  ggplot(aes(x = `Siblings/Spouses Aboard`, 
             fill = factor(Survived))) + 
  geom_bar() + 
  facet_wrap(~Survived,
             labeller = labeller(Survived = c("0" = "Did not Survive",
                                              "1" = "Survived"))) + 
  theme_classic() + 
  theme(legend.position = "none") + 
  labs(x = "Number of Passengers", 
       y = "Siblings") + 
  scale_fill_manual(values = c("darkblue", "darkred"))

```

```{r}
df %>%
  filter(Fare < 300) %>% 
  ggplot(aes(x = Fare, fill = factor(Sex))) +
  geom_histogram(bins = 15) +
  geom_freqpoly(col="black",size=1) + 
  facet_grid(~ Sex,
             labeller = labeller(Sex = c(female = "Female",
                                         male = "Male"))) +
  theme_classic() +
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5)) +
  labs(x = "Rate",
       y = "Number of Passengers",
       title = "Rate Distribution of Female vs. Male Passengers")
```