Introduction
Welcome to my capstone project for the Gen AI Intensive Course 2025Q1! This project showcases how I applied what I learned throughout the 5-day course to create an interactive and insightful notebook using the Gemini API.
I chose the Oscar Awards dataset because of my love for movies and my prior experience analyzing this dataset without Gen AI. This time, I leveraged the power of Generative AI to enhance my analysis and create a more interactive experience.
Project Details
The notebook explores the Oscar Awards dataset, which contains information about winners and nominees from the inception of the awards up to 2025. Using the Gemini API, I implemented:
- Function calling to interact with a local SQLite database.
- Data analysis capabilities to extract insights from the dataset.
- An interactive chat interface powered by Gen AI.
This project demonstrates the capabilities of the Gemini API, including function calling, retrieval-augmented generation (RAG), and agent-based interactions.
You can view the full notebooks on Kaggle here:
Why Movies?
Movies have always been a passion of mine, and the Oscar Awards dataset provides a rich source of information for analysis. By combining my love for movies with the power of Generative AI, I was able to create a project that is both meaningful and exciting.
Key Findings
Top Female Oscar Winners
Here are the most successful actresses in Oscar history:
| Name | Number of Wins | Notable Films |
|---|---|---|
| Katharine Hepburn | 4 | Morning Glory, Guess Who's Coming to Dinner, The Lion in Winter, On Golden Pond |
| Frances McDormand | 3 | Fargo, Three Billboards Outside Ebbing Missouri, Nomadland |
| Ingrid Bergman | 3 | Gaslight, Anastasia, Murder on the Orient Express |
| Meryl Streep | 3 | Kramer vs. Kramer, Sophie's Choice, The Iron Lady |
Most Nominated Films
The following chart shows the films that received the most Oscar nominations throughout history:
Highlights
Here are some key highlights of the project:
- Created a local SQLite database from the Oscar Awards dataset.
- Defined functions for listing tables, describing schemas, and executing SQL queries.
- Implemented an interactive chat interface to answer movie-related questions.
- Used Gen AI to generate Python code for data visualization and analysis.
- Analyzed historical patterns in Oscar nominations and wins.
- Created visualizations to show distribution of nominations across films and actors.
Conclusion
This project was a fantastic opportunity to apply what I learned during the Gen AI Intensive Course. By combining my passion for movies with the power of Generative AI, I was able to create a project that is both fun and insightful. I hope this inspires others to explore the possibilities of Gen AI in their own projects!