Titanic_Project

Installing the right packages

install.packages("dplyr")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

Loading thr titanic dataset into r

titanic_data <- read.csv("Titanic-Dataset.csv")

View the first rows of the dataset

head(titanic_data)

##   PassengerId Survived Pclass
## 1           1        0      3
## 2           2        1      1
## 3           3        1      3
## 4           4        1      1
## 5           5        0      3
## 6           6        0      3
##                                                  Name    Sex Age SibSp Parch
## 1                             Braund, Mr. Owen Harris   male  22     1     0
## 2 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female  38     1     0
## 3                              Heikkinen, Miss. Laina female  26     0     0
## 4        Futrelle, Mrs. Jacques Heath (Lily May Peel) female  35     1     0
## 5                            Allen, Mr. William Henry   male  35     0     0
## 6                                    Moran, Mr. James   male  NA     0     0
##             Ticket    Fare Cabin Embarked
## 1        A/5 21171  7.2500              S
## 2         PC 17599 71.2833   C85        C
## 3 STON/O2. 3101282  7.9250              S
## 4           113803 53.1000  C123        S
## 5           373450  8.0500              S
## 6           330877  8.4583              Q

Check the structure of the data

str(titanic_data)

## 'data.frame':    891 obs. of  12 variables:
##  $ PassengerId: int  1 2 3 4 5 6 7 8 9 10 ...
##  $ Survived   : int  0 1 1 1 0 0 0 0 1 1 ...
##  $ Pclass     : int  3 1 3 1 3 3 1 3 3 2 ...
##  $ Name       : chr  "Braund, Mr. Owen Harris" "Cumings, Mrs. John Bradley (Florence Briggs Thayer)" "Heikkinen, Miss. Laina" "Futrelle, Mrs. Jacques Heath (Lily May Peel)" ...
##  $ Sex        : chr  "male" "female" "female" "female" ...
##  $ Age        : num  22 38 26 35 35 NA 54 2 27 14 ...
##  $ SibSp      : int  1 1 0 1 0 0 0 3 0 1 ...
##  $ Parch      : int  0 0 0 0 0 0 0 1 2 0 ...
##  $ Ticket     : chr  "A/5 21171" "PC 17599" "STON/O2. 3101282" "113803" ...
##  $ Fare       : num  7.25 71.28 7.92 53.1 8.05 ...
##  $ Cabin      : chr  "" "C85" "" "C123" ...
##  $ Embarked   : chr  "S" "C" "S" "S" ...

Data Cleaning and Transformation

Handling missing values

summary(titanic_data)

##   PassengerId       Survived          Pclass          Name          
##  Min.   :  1.0   Min.   :0.0000   Min.   :1.000   Length:891        
##  1st Qu.:223.5   1st Qu.:0.0000   1st Qu.:2.000   Class :character  
##  Median :446.0   Median :0.0000   Median :3.000   Mode  :character  
##  Mean   :446.0   Mean   :0.3838   Mean   :2.309                     
##  3rd Qu.:668.5   3rd Qu.:1.0000   3rd Qu.:3.000                     
##  Max.   :891.0   Max.   :1.0000   Max.   :3.000                     
##                                                                     
##      Sex                 Age            SibSp           Parch       
##  Length:891         Min.   : 0.42   Min.   :0.000   Min.   :0.0000  
##  Class :character   1st Qu.:20.12   1st Qu.:0.000   1st Qu.:0.0000  
##  Mode  :character   Median :28.00   Median :0.000   Median :0.0000  
##                     Mean   :29.70   Mean   :0.523   Mean   :0.3816  
##                     3rd Qu.:38.00   3rd Qu.:1.000   3rd Qu.:0.0000  
##                     Max.   :80.00   Max.   :8.000   Max.   :6.0000  
##                     NA's   :177                                     
##     Ticket               Fare           Cabin             Embarked        
##  Length:891         Min.   :  0.00   Length:891         Length:891        
##  Class :character   1st Qu.:  7.91   Class :character   Class :character  
##  Mode  :character   Median : 14.45   Mode  :character   Mode  :character  
##                     Mean   : 32.20                                        
##                     3rd Qu.: 31.00                                        
##                     Max.   :512.33                                        
## 

colSums(is.na(titanic_data)) 

## PassengerId    Survived      Pclass        Name         Sex         Age 
##           0           0           0           0           0         177 
##       SibSp       Parch      Ticket        Fare       Cabin    Embarked 
##           0           0           0           0           0           0

is.na is the function that looks for missing values

Age has 177 missing values

Cleaning data and replacing NA values with the median of Ages.

titanic_data$Age <- replace(titanic_data$Age ,is.na(titanic_data$Age), median(titanic_data$Age, na.rm = TRUE))

Removing rows with missing Embarked Values

titanic_data <- titanic_data %>%
  filter(Embarked != "")

Dropping the Cabin Column

titanic_data <- titanic_data %>% select(-Cabin)

Converting relevant columns to appropiate datatypes

titanic_data <- titanic_data %>% mutate(Survived = as.factor(Survived), Pclass = as.factor(Pclass), Sex = as.factor(Sex), Embarked = as.factor(Embarked))

Looking at the Column Names

names(titanic_data)

##  [1] "PassengerId" "Survived"    "Pclass"      "Name"        "Sex"        
##  [6] "Age"         "SibSp"       "Parch"       "Ticket"      "Fare"       
## [11] "Embarked"

Changing the Column Names to Lowercase

names(titanic_data) <- tolower(names(titanic_data))

Save my cleaned data to a new file

write.csv(titanic_data, "cleaned_titanic_data.csv", row.names = FALSE)

Data Visualisation

Installing the right packages

install.packages("tidyverse") ## Includes ggplot2

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)

library(tidyverse) 

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ readr     2.1.5
## ✔ ggplot2   3.5.1     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

install.packages("plotly") ## Used to make graphs interactive

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)

library(plotly)

## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout

install.packages("devtools")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)

library(devtools)

## Loading required package: usethis

Bar plot for Survived

ggplotly(
  ggplot(titanic_data, aes(x = as.factor(survived), fill = as.factor(survived))) +
    geom_bar(color = "black") +
    scale_fill_manual(values = c("yellow", "orange")) +
    xlab("Survived") +
    ylab("Count") +
    ggtitle("Count of Survived Passengers on the Titanic") +
    theme(axis.line = element_line(color = "black"))
)

Shows a bar plot for the survived variable, shows the count of passengers who survived and those who didnt.

Barplot for fair price

ggplotly(
  ggplot(titanic_data, aes(x = sex, fill = sex)) +
    geom_bar(color = "black") +  # Add black borders to the bars
    scale_fill_manual(values = c("blue", "pink")) +
    xlab("Sex") +
    ylab("Count") +
    ggtitle("Male to Female Ratio on The Titanic") +
    theme(axis.line = element_line(color = "black"))
)

Scatter plot Age vs Fair price

ggplotly(
  ggplot(titanic_data, aes(x = age, y = fare)) +
    geom_point(color = "red") +
    geom_smooth(method = "lm", se = FALSE) +  # Add line of best fit
    xlab("Age") +
    ylab("Fare") +
    ggtitle("Age vs Fare Price") +
    theme(axis.line = element_line(color = "black"))
)

## `geom_smooth()` using formula = 'y ~ x'

Histogram of Age

ggplotly(
  ggplot(titanic_data, aes(x = age, fill = sex)) +
    geom_histogram(binwidth = 5, color = "black") +
    xlab("Age") +
    ylab("Count") +
    ggtitle("Age Distribution of Passengers by Sex") +
    theme(axis.line = element_line(color = "black")) 
)

Facet grid of Age vs Fare by Passenger Class and Sex

ggplotly(
  ggplot(titanic_data, aes(x = age, y = fare, color = sex)) +
    geom_point() +
    facet_wrap(~ pclass) +
    xlab("Age") +
    ylab("Fare") +
    ggtitle("Age vs. Fare by Passenger Class and Sex") +
    theme(axis.line = element_line(color = "black")) 
  )

Boxplot of Age by Survived

ggplotly(ggplot(titanic_data, aes(x = as.factor(survived), y = age)) +
  geom_boxplot(fill = "green") +
  geom_point(data = . %>% filter(age > quantile(age, 0.75) + 1.5*IQR(age) | age < quantile(age, 0.25) - 1.5*IQR(age)), color = "red") +
  xlab("Survived") +
  ylab("Age") +
  ggtitle("Age Distribution by Survival Status")
  )

Bar Plot of Passenger Class

ggplotly(ggplot(titanic_data, aes(x = as.factor(pclass), fill = as.factor(pclass))) +
  geom_bar(color = "black") +
  scale_fill_manual(values = c("blue", "pink", "yellow")) +
  xlab("Pclass") +
  ylab("Count") +
  ggtitle("Count of Passenger Class") +
  theme(axis.line = element_line(color = "black"))
  )

Bar Plot of Embarked

ggplotly(
  ggplot(titanic_data, aes(x = embarked, fill = embarked)) +
    geom_bar(color = "black") +
    scale_fill_manual(values = c("blue", "pink", "yellow", "green")) +
    xlab("Embarked Point") +
    ylab("Count") +
    ggtitle("Count of Passengers by Embarkation Point") +
    theme(axis.line = element_line(color = "black"))
  )