Importing/Cleaning Data

remove(list = ls())
train <- read.csv("~/Downloads/train.csv")

colSums(is.na(train))
## PassengerId    Survived      Pclass        Name         Sex         Age 
##           0           0           0           0           0         177 
##       SibSp       Parch      Ticket        Fare       Cabin    Embarked 
##           0           0           0           0           0           0
train_clean <- na.omit(train)

Summary Statistics

library(stargazer)
## 
## Please cite as:
##  Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables.
##  R package version 5.2.3. https://CRAN.R-project.org/package=stargazer
?stargazer

stargazer(train_clean, type = "text", title="Titanic", digits=2, out="table1.txt")
## 
## Titanic
## ===========================================
## Statistic    N   Mean  St. Dev. Min   Max  
## -------------------------------------------
## PassengerId 714 448.58  259.12   1    891  
## Survived    714  0.41    0.49    0     1   
## Pclass      714  2.24    0.84    1     3   
## Age         714 29.70   14.53   0.42 80.00 
## SibSp       714  0.51    0.93    0     5   
## Parch       714  0.43    0.85    0     6   
## Fare        714 34.69   52.92   0.00 512.33
## -------------------------------------------

Boxplot

boxplot(train_clean$Survived, main = "Survived Based on Pclass", xlab = "Survived", ylab = "Pclass", border = "blue", col = "red", horizontal = TRUE)

Histogram

Fare <- train_clean$Fare
hist(Fare, xlab = "Fare", ylab = "Pounds", col = "blue")

Density Plot

library(ggplot2)
library(readxl)


den <- density(train_clean$Fare)
library(ggplot2)

ggplot(train_clean, aes(x = Fare)) +
  geom_density(fill = "skyblue", alpha = 0.7) +
  labs(title = "Titanic Fare",
       x = "Fare",
       y = "Density")

Key Takeaways