Data Analysis and Prediction of Survivors on the Titanic Dataset
Putu Sanisa Pascaline
1/04/2021
Introduction
The sinking of the RMS Titanic is one of the most infamous shipwrecks in history. On April 15, 1912, during her maiden voyage, the Titanic sank after colliding with an iceberg, killing 1502 out of 2224 passengers and crew. This sensational tragedy shocked the international community and led to better safety regulations for ships.
One of the reasons that the shipwreck led to such loss of life was that there were not enough lifeboats for the passengers and crew. Although there was some element of luck involved in surviving the sinking, some groups of people were more likely to survive than others, such as women, children, and the upper-class.
Here we try to analyze which factors were more likely to contribute to the death of the passengers and classify who is more likely to survive depending on the features.
Purpose
The purpose of this project was to gain introductory exposure to programmatic data analysis concepts, by analysing the factors that determined whether a passenger survived the Titanic disaster or did not.
The data has been split into two groups:
training set (train.csv) test set (test.csv) The training set should be used to build your machine learning models. For the training set, we provide the outcome (also known as the “ground truth”) for each passenger. Your model will be based on “features” like passengers’ gender and class. You can also use feature engineering to create new features.
The test set should be used to see how well your model performs on unseen data. For the test set, we do not provide the ground truth for each passenger. It is your job to predict these outcomes. For each passenger in the test set, use the model you trained to predict whether or not they survived the sinking of the Titanic.
below are the library that we need
library(ggplot2)we could input our data to R and put it into ‘titanic’ object
titanic <- read.csv("train.csv",stringsAsFactors = FALSE)
str(titanic)## '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 Cleansing & Coertions
head(titanic)## 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 Qfrom this result, we find some of data type not in the corect type. we need to convert it into corect type (data coercion)
# convert data types
titanic$Pclass <- as.factor(titanic$Pclass)
titanic$Survived <- as.factor(titanic$Survived)
titanic$Name <- as.character(titanic$Name)
titanic$Sex <- as.factor(titanic$Sex)
# titanic$Ticket <- as.character(titanic$Ticket)
titanic$Cabin <- as.character(titanic$Cabin)
titanic$Embarked <- as.factor(titanic$Embarked)str(titanic)## 'data.frame': 891 obs. of 12 variables:
## $ PassengerId: int 1 2 3 4 5 6 7 8 9 10 ...
## $ Survived : Factor w/ 2 levels "0","1": 1 2 2 2 1 1 1 1 2 2 ...
## $ Pclass : Factor w/ 3 levels "1","2","3": 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 : Factor w/ 2 levels "female","male": 2 1 1 1 2 2 2 2 1 1 ...
## $ 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 : Factor w/ 4 levels "","C","Q","S": 4 2 4 4 4 3 4 4 4 2 ...each of column already changed into desired data type and check null data
colSums(is.na(titanic))## PassengerId Survived Pclass Name Sex Age
## 0 0 0 0 0 177
## SibSp Parch Ticket Fare Cabin Embarked
## 0 0 0 0 0 0cool! now check null string data
colSums(titanic=="")## PassengerId Survived Pclass Name Sex Age
## 0 0 0 0 0 NA
## SibSp Parch Ticket Fare Cabin Embarked
## 0 0 0 0 687 2finding Age mean for data imputation
# library(dplyr)
# summarise(titanic, Average = mean(Age, na.rm = T))
# mean(titanic$Age, na.rm = TRUE)
summary(titanic$Age)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.42 20.12 28.00 29.70 38.00 80.00 177don’t forget to deleting null rows!
# x <- na.omit(titanic)
titanicNew <- titanic[complete.cases(titanic), ]roughly 20 percent of the Age data is missing. The proportion of Age missing is likely small enough for reasonable replacement with some form of imputation so the null cleaning more preferable.
about 687 out 891 of cabin data are missing, however, the cabin data not important since it just unique code of room, so i prefer to drop the Cabin colloum
dim(titanicNew)## [1] 714 12colSums(is.na(titanicNew))## PassengerId Survived Pclass Name Sex Age
## 0 0 0 0 0 0
## SibSp Parch Ticket Fare Cabin Embarked
## 0 0 0 0 0 0From that result, no missing value anymore with 714 data remaining
summary(titanicNew)## PassengerId Survived Pclass Name Sex
## Min. : 1.0 0:424 1:186 Length:714 female:261
## 1st Qu.:222.2 1:290 2:173 Class :character male :453
## Median :445.0 3:355 Mode :character
## Mean :448.6
## 3rd Qu.:677.8
## Max. :891.0
## Age SibSp Parch Ticket
## Min. : 0.42 Min. :0.0000 Min. :0.0000 Length:714
## 1st Qu.:20.12 1st Qu.:0.0000 1st Qu.:0.0000 Class :character
## Median :28.00 Median :0.0000 Median :0.0000 Mode :character
## Mean :29.70 Mean :0.5126 Mean :0.4314
## 3rd Qu.:38.00 3rd Qu.:1.0000 3rd Qu.:1.0000
## Max. :80.00 Max. :5.0000 Max. :6.0000
## Fare Cabin Embarked
## Min. : 0.00 Length:714 : 2
## 1st Qu.: 8.05 Class :character C:130
## Median : 15.74 Mode :character Q: 28
## Mean : 34.69 S:554
## 3rd Qu.: 33.38
## Max. :512.33Data Explanation
Summary : 1. There are 891 passengger in total 2. 177 Age values are missing 3. 714 Data remaining after null data cleansing 4. Southampton,Cherbourg and Queenstown is the most popular port of embarkment in in respective ways 5. There are 184 type of cabins 6. Maximum ticket fare is 512 and minimum of 0 (Free) 7. Passenger have Maximum of 6 siblings / spouses aboard 8. Passenger have Maximum of 5 parents / children aboard the Titanic 9. The oldest passenger is 80 years old and the youngest one is under 1 year old 10.Passenger dominated by men of 453 and women of 261 11.Pclass number 3 is most populated compared to others 12.290 passenger was survived and 424 was dead
now finding outlier of fare Plclass, also calculate mean, varriance and standard deviation between Fare and Pclass
aggregate(Fare~Pclass,titanicNew,mean)## Pclass Fare
## 1 1 87.96158
## 2 2 21.47156
## 3 3 13.22944aggregate(Fare~Pclass,titanicNew,var)## Pclass Fare
## 1 1 6537.8850
## 2 2 173.9083
## 3 3 100.8650aggregate(Fare~Pclass,titanicNew,sd)## Pclass Fare
## 1 1 80.85719
## 2 2 13.18743
## 3 3 10.04316boxplot(titanicNew$Fare)
From result above, I find great outliers posibilities of fare, especially found in passenger with class 1 (The Most Expensive) with calculation of Sd value is around 80, in my humble oppinion, its still be tolerated because Pclass 1 market segmentation dominated by the wealthy socio-economic status (SES) back then, so the process may continue
Analysis
##1. Which plcass more surviveable? ##2. Most Surviveable gender? ##3.What age is the most frequently survived? ##4. most survivor by port of embarkment?
first thing first is find the end of data length
LT=dim(titanicNew)[1]ggplot(data=titanicNew[1:LT,],aes(x=Pclass,fill=Survived))+geom_bar()
Answer 1: Passengers in class 1 are more survivable compared to others with approximately 70% passengers are survived, while class 2 and 3 have same number of survive passangers, furthermore the most fatality occured in class 3
ggplot(data=titanicNew[1:LT,],aes(x=Sex,fill=Survived))+geom_bar()
Answer 2: approximately arround 200 female and 100 male are survived the accident, however 70% of male are dead
ggplot(data = titanicNew[!(is.na(titanicNew[1:LT,]$Age)),],aes(x=Age,fill=Survived))+geom_histogram(binwidth =3)
Answer 3: the most surviveable passengers by age is around 18-40 years old, while the elder between 50-70 share small proportion of survivor, interestingly, all 80 year old of passenger are survived, while youngster beetween 2 - 15 mostly dead, however around 90% 1 year old children are survived
ggplot(data=titanicNew[1:LT,],aes(x=Embarked,fill=Survived))+geom_bar()