The Titanic - machine learning from disaster

• Historical context to understand "What does the data mean?"
• Learn one data set well, and then apply different algorithms and modelling tools.
• This is a true event and everybody knows about the Titanic.
• Whole information is in the internet and the data is verified.

1. Assignment on
Advanced Data Mining and Machine
Learning
Course Code: CSE-5208
Jagannath University
Submitted to:
Dr. Md Masbaul Alam Polash
Associate Professor
Dept. of Computer Science & Engineering
Jagannath University
Submitted by:
Mostafa Nizam
M.Scin CSE (2nd Semester)
7
th
Batch
Date of Submission: 28-06-2109

2. The Titanic: MachineLearning from
Disaster

3. Titanic: Machine Learning from
Disaster
Why we picked this project:
Historical context to understand "What does the data mean?"
Learn one data set well, and then apply different algorithms and modelling
tools.
This is a true event and everybody knows about the Titanic.
Whole information is in internet and the data is verified.

4. April 1912
The Titanic Disaster

5. About Titanic:
The ship sank in the North Atlantic ocean over one hundred years ago.
But almost everybody in the world today knows the name of the
Titanic. in 1912, the Titanic is the biggest ship that was ever built. It is 269
meters long and everyone thinks that the ship is also very safe. The ship
can carry more than 3.000 passengers, and has many decks, a
swimming pool, a library, Turkish baths, and excellent restaurants and
bars. The Titanic leaves Southampton, on the south coast of England,
on April 10, 1912.
First class: 322 passengers
Second class: 275 passengers
Third class: 712 passengers
Crew: 898 passengers

6. Survived:
First class: 60% survived 130 died
Second class: 42% survived 166 died
Third class: 25% survived 536 died
The crew : 24% survived 685 died

7. Overview
We take the Data from https://www.kaggle.com/c/titanic/data
We will use R programming language.
The data has been split into two groups:
training set (train.csv)
test set (test.csv)
The training setshould 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.
The test setshould 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.

8. Data Dictionary
Variable Definition Key
survival Survival 0 = No, 1 = Yes
pclass Ticket class 1 = 1st, 2 = 2nd, 3 = 3rd
sex Sex
Age Age in years
sibsp # of siblings / spouses aboard the Titanic
parch # of parents / children aboard the
Titanic
ticket Ticket number
fare Passenger fare
cabin Cabin number
embarked Port of Embarkation C = Cherbourg, Q = Queenstown, S =
Southampton

9. Variable Notes
pclass: A proxy for socio-economic status (SES)
1st = Upper
2nd = Middle
3rd = Lower
age: Age is fractional if less than 1. If the age is estimated, is it in the form of xx.5
sibsp: The dataset defines family relations in this way...
Sibling = brother, sister, stepbrother, stepsister
Spouse = husband, wife (mistresses and fiancés were ignored)
parch: The dataset defines family relations in this way...
Parent = mother, father
Child = daughter, son, stepdaughter, stepson
Some children travelled only with a nanny, therefore parch=0 for them.

10. Install R & R studio

11. 1
st
Prediction
See the data who survived and died. (0=die; 1=survive).
Proportion table in percentage.
Doing hypothesis. Let, all are died and submit to Kaggle.com

12. View “Train” Data

13. Data Structure of ‘Train’ Data

14. See the data who survived and
died. (0=die; 1=survive).

15. Proportion table in percentage

16. BarplotData visualization

17. Doing hypothesis. Let, all are died
and submit to Kaggle.com

18. Ladder board

19. Data Visualization
How many survived?
Passengers travelling in different classes
How many survived gender-wise?
Age distribution in the Titanic
How many parents and children were traveling?
What was the fair most people paid for Titanic?

20. How many survived?

21. Passengers travelling in different
classes

22. How many survived gender-wise?

23. Age distribution in the Titanic

24. How many parents and children
were traveling?

25. What was the fair most people
paid for Titanic?

26. 2
nd
Prediction
Summery of Gender
Proportion in Percentage
Let, all female were survive. Then submit the 2
nd
prediction in
Kaggle.com

27. Summery of Gender

28. Proportion in Percentage

29. Submit to Kaggle.com

30. Ladder Board

31. How can we know the passenger survived or
died? (With google search proof)

32. Google Search

33. View Result

34. Takeaways
Data Science requires a lot of data engineering before it can
succeed
Domain knowledge is key
This workflow can be applied to most data problems
R Studio is pretty cool too.

35. Thank you