Kaggle Titanic Survival Prediction Competition Part 1/2 - Exploratory Data Analysis

In this video, I will walk through my solution and analysis for one of the most popular beginner's competitions on Kaggle, that is the Titanic survival prediction competition. This video is part one of a two-part series.
Kaggle is a subsidiary of Google and an online community of data scientists and machine learning practitioners. On Kaggle, you can find many published datasets, data science and machine learning tutorials but most importantly, Kaggle is best known for their competitions.
The Titanic survival prediction competition is a great beginner's competition that introduces beginners to not only the Kaggle platform but also the process behind an end-to-end machine learning project, from loading and reading datasets to building a fully functional predictive model.
The aim of this competition is to analyse how different passenger features such as age, gender and ticket class correlate with survival and subsequently train a machine learning model to classify unknown passenger data. This is an example of a binary classification problem in machine learning where passengers are classified as either survived or did not survive.
This video covers the exploratory data analysis (EDA) section of my notebook. EDA is the process of exploring our datasets as well as summarise the key characteristics and trends in our data such as data types, distributions and correlation between numerical variables.
I managed to gather three important insights as a result of the EDA process:
1. Female passengers were more likely to survive than male passengers
2. First-class passengers were most likely to survive in comparison to second class as well as third-class passengers
3. Passengers of younger ages, especially children were more likely to survive than the other passengers on the Titanic
A lot of time has gone into preparing the solution notebook as well as this video. So, if you enjoyed it or found it helpful in your own learning, it would mean the world to mean if you could like the video and subscribe to my channel.
If you have any questions, feel free to reach out to me. Happy learning!
Timestamp
00:00 - Introduction
05:06 - Import libraries
05:48 - Import and read data
08:20 - Data description
09:30 - Data types, missing data and summary statistics
12:35 - Feature analysis introduction
13:49 - Analyse categorical variables
19:26 - Analyse numerical variables
24:33 - Summary and conclusion
26:04 - Outro
Install Anaconda and Jupyter Notebook
www.anaconda.com/products/ind...
Kaggle Titanic Survival Prediction Competition
www.kaggle.com/c/titanic/over...
Link to my notebook on GitHub
github.com/chongjason914/kagg...
Follow me
Facebook - / chongjason914
Instagram - / chongjason914
Twitter - / chongjason914
Medium - / chongjason
LinkedIn - / chongjason914
#Kaggle #DataScience #MachineLearning

[@jeromeprovensal]

Best tutorial on the Kaggle Titanic competition!

[@SurajSingh-ff4ki]

Thank you Jason, you really helped me create my very first training model.

[@faith3220a]

Thank you very much for the detailed explanations

[@H99x2]

This is one of the best guides of the Kaggle Titanic dataset on YT! And you have a very good way of explaining. Subscribed for more like this :)

[@fairuzbackup72]

Fantastic video! Really useful for beginners such as myself to understand what are the steps that are performed during a data analysis process :)

[@l4dybu9]

Thank yiu so much for this vid ✌🏻🙌🏻💖💖

[@zozolovpuppies]

Awesome video! Excited to see the next ep!

[@JasonChong914]

Thanks bb 🥺

[@digigoliath]

Awesome. TQVM!

[@benjamindeworsop8348]

Awesome video, your hypothesis-driven approach is a great way to make sense of the crazy amounts of data. Nice conclusion too - really ties it all together

[@JasonChong914]

Thanks Ben! ❤️

[@akhilsoni729]

Looking forward to more videos like this being uploaded. Loved it.

[@JasonChong914]

Thanks Akhil - really appreciate your kind words! 😊

[@endernator]

pls more content like this... sooo goood

[@ai.simplified..]

I ve already done the competition but it will be very usefull for any beginer like me, thx for sharing I already was thinking about making a video about it.

[@mchafe]

Thanks, very educative

[@solaawodiya7360]

This was so amazing Jason!. Thanks for the direct, clear, and step-by-step guide through this project. I learnt a lot and I'm looking forward to learn more 👌

[@JasonChong914]

Thanks Sola - glad I was able to help! 😉

[@justinzhang4648]

Awesome

[@ashish-blessings]

You are simply awesome!

[@JasonChong914]

Aww thank you! 😊

[@jpsiyyadri]

Thanks Jason, u helped me a lot

[@JasonChong914]

You're most welcome, Jai. Happy I was able to help!

[@makotao7218]

What an amazing video! Im starting to learn data science and this was great - honestly, SWE feels so boring after this haha

[@franklynchidi4379]

great was direct...its just that am new to it but was heplful though i had some issues with the grid

[@raylow6213]

I find it useful when you explain the reason behind an occurrence, but did you come across any suspicious/interesting data that you might later explore on your own? Btw nice work!

[@rohanshava5490]

Good job bro :)

[@JasonChong914]

Thank you!

[@pontus_qwerty]

18:56: why is survival probability embarking from Q higher than from S when almost all passengers in Q are class 3? Are they most class 3 men embarking from Q as opposed to the class 3 women from S?

[@mrreese2342]

is this dataset real ? i mean are the people in the dataset the real people that were in the titanic ?