TitanicAnalysis

Certainly! Here’s your script formatted as an R Markdown document:

1) Import dataset as csv

# Assuming the file is already downloaded and placed in the working directory
titanic_path <- "C:/Users/jawii/Downloads/titanic3.csv"
T3 <- read.csv(titanic_path)

2) Load into R into a variable called T3

titanic <- T3[, c("survived", "embarked", "sex", "sibsp", "parch", "fare")]

3) Perform a statistical analysis of the titanic dataset

summary(titanic)

##     survived       embarked             sex                sibsp       
##  Min.   :0.000   Length:1309        Length:1309        Min.   :0.0000  
##  1st Qu.:0.000   Class :character   Class :character   1st Qu.:0.0000  
##  Median :0.000   Mode  :character   Mode  :character   Median :0.0000  
##  Mean   :0.382                                         Mean   :0.4989  
##  3rd Qu.:1.000                                         3rd Qu.:1.0000  
##  Max.   :1.000                                         Max.   :8.0000  
##                                                                        
##      parch            fare        
##  Min.   :0.000   Min.   :  0.000  
##  1st Qu.:0.000   1st Qu.:  7.896  
##  Median :0.000   Median : 14.454  
##  Mean   :0.385   Mean   : 33.295  
##  3rd Qu.:0.000   3rd Qu.: 31.275  
##  Max.   :9.000   Max.   :512.329  
##                  NA's   :1

4) Find the proportion of Survived in the dataset

prop_survived <- prop.table(table(titanic$survived))
# View the proportions
prop_survived

## 
##        0        1 
## 0.618029 0.381971

5) Remove NAs if any

titanic <- na.omit(titanic)

6) Make Survived, embarked, and sex as factors

titanic$survived <- factor(titanic$survived)
titanic$embarked <- factor(titanic$embarked)
titanic$sex <- factor(titanic$sex)

7) Find the correlation matrix between survival and the other features

library(vcd)

## Warning: package 'vcd' was built under R version 4.3.3

## Loading required package: grid

# Calculate Cramér's V for the relationship between 'survived' and 'sex' 
cramer_v_sex <- assocstats(table(titanic$survived, titanic$sex))$cramer
cramer_v_embarked <- assocstats(table(titanic$survived, titanic$embarked))$cramer

# View the Cramér's V statistics
cramer_v_sex

## [1] 0.5272478

cramer_v_embarked

## [1] 0.1837218

8) Plot survival with other features to see if any correlation exists

library(ggplot2)
ggplot(titanic, aes(x = sex, fill = survived)) +
  geom_bar(position = "dodge")

9) Set a seed and split the dataset into training and testing

set.seed(1000)
train_index <- sample(1:nrow(titanic), 0.8 * nrow(titanic))
train <- titanic[train_index, ]
test <- titanic[-train_index, ]

10) Train your learner on the training dataset

library(rpart)

## Warning: package 'rpart' was built under R version 4.3.3

library(rattle)

## Warning: package 'rattle' was built under R version 4.3.3

## Loading required package: tibble

## Loading required package: bitops

## Rattle: A free graphical interface for data science with R.
## Version 5.5.1 Copyright (c) 2006-2021 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.

fit <- rpart(survived ~ sex + sibsp + parch + fare + embarked,
             data = train, method = "class")

11) Plot the regression tree

library(rpart.plot)

## Warning: package 'rpart.plot' was built under R version 4.3.3

pdf("regression_tree.pdf")
rpart.plot(fit)
dev.off()

## png 
##   2

12) Use fancyRpartPlot for a more readable plot

fancyRpartPlot(fit)

13) Examine the tree

# Tree splits over gender first
# Children are the future so they should be saved first. When it comes to the adults I believe in equality.

14) Make predictions on the test dataset

prediction <- predict(fit, test, type = "class")

15) Save results in a data frame

Results <- data.frame(passengersex = test$sex, survived = prediction)

16) Save data frame in a .csv file

write.csv(Results, file = "Titanicdtree.csv", row.names = FALSE)

```

This R Markdown document includes the code chunks for each step along with the comments and the corresponding output. When you knit this document, it will generate an HTML file with the analysis and outputs included.