Data Science - Database on the Titanic Incident

Simon Zeru Image

Simon Zeru

Last modified : June 10, 2025 (1w ago)

📅 Period: December 2023 – January 2024

🛠️ Technologies: PostgreSQL

👩‍💻 Expertise: Data Science, Database Design, Data Management

🎓 Acquired skills: Managing information data, Conducting a project, Working in a team

🔗 GitHub: View repository

📄 Report: See PDF

This article discusses the implementation of my data science project, where I created a database on the Titanic incident and performed analysis on it.

Cover of the project

Project Overview

After modeling and implementing a database populated with the information provided about the Titanic incident, we performed analyses to extract insights about the passengers and the crew. Our analysis included exploring various aspects such as passenger demographics, survival rates, and relationships between different variables.

First, we performed the SEA (Structured Entity Analysis) and SLR (Structured Logical Representation) to modelize our database :

Image of the data schema model

The next step was to code the database using SQL. We created the create.sql file to define the structure of the database and create the necessary tables.

Image of an extract of the create.sql file

The analysis included exploring various aspects such as passenger demographics, survival rates, and relationships between different variables. SQL queries were used to extract key indicators, formalized as descriptive statistics.

Image of a Query example

Finally, we created an analysis report to visualize the results obtained from our queries and draw conclusions from them.

Image of one graph analysis

Project Results

This project enabled the development of skills in conceptual and logical data modeling, advanced SQL querying, and interpretation of statistical results, serving as a first practical application in data science.