Hello all,

I’m glad you are reading this post. Here in this article, I will write a short introduction about a project that will help you in your journey to become better at data analysis and building, training, and deploying a machine learning program.

Before I start talking about it, I'd like to tell you that this project could or might interest people who are python enthusiasts and wish to learn more about data science, machine learning, and data analysis.

This is a dataset related to the passengers who traveled on the Titanic. In this web app, you will predict the life of the passengers using the machine learning model that is built in it. For technical information about it, please read the readme file that you will find in the GitHub repository. The Github link will be shared below.

Let's go ahead and check what the web app has to offer and the things that it can do. Here, open this website.

The website is intuitive which I'm sure when you check it out completely you get to experience the data science work and prediction program that it has to offer. I'd suggest you be a little patient while browsing the pages while you are navigating as it has a bit of reading. I built it by having a beginner's mindset throughout the program. Moreover, the pages are not that boring because I added a kind of short story about the Titanic which I'm sure you will enjoy it.

Before you post any reviews I'd like to inform you guys that I am not so great at CSS and HTML, although I tried to make it look good so that the user experience is better enough to understand the data science work that goes on in the real world. I used Bootstrap for styling and customizing the pages which I found is very simple to implement for people like me who wish to focus more on the backend tasks and much less UI.

Much work was done using python libraries. Flask is a web framework in python which will enable you to make web applications very easily. I liked it because of its simplicity and the extensions it has such as template inheritance and jinja.

To make predictions, again, I have used pythons libraries such as scikit learn and for pre-processing pandas, seaborn, and other scientific tools. It's worth your time to look at the code in the repository to understand how the program does the prediction and how the code is structured. This is the Github link.

Alright, that's it for this article. I kept it short because there is a readme file in the repository which you can read to know details about this project & also find the installation steps in it to install the codebase on your computer.