This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 1 — Touch Grass.
AIXpo — AI Data Explorer 🌿
What I Built
AIXpo (AI Data Explorer) is an AI-powered data analysis application designed to help users explore datasets, discover patterns, and turn information into actionable insights.
For the Hacktoberfest Week 1 theme, Touch Grass, I wanted to connect data exploration with real-world activity. The application uses outdoor activity data as a demonstration, helping users explore walking, running, cycling, and hiking records.
AIXpo also supports custom user data, allowing users to explore their own datasets instead of relying exclusively on a predefined example.
Key Features
- Explore datasets and review their structure.
- Add custom data.
- Examine missing values and basic statistics.
- Create interactive data visualisations.
- Ask questions about datasets using AI-assisted analysis.
- Explore outdoor activity patterns and identify practical opportunities to spend more time outside.
Demo
Watch the AIXpo demonstration:
Source Code
Explore the project on GitHub:
How I Built It
AIXpo combines Python-based data processing with an interactive application interface.
The technology stack includes:
- Python for application logic.
- Streamlit for the user interface.
- Pandas for data processing and analysis.
- Plotly for interactive visualisations.
- Ollama with an open-weight language model for local AI inference.
The application combines conventional data analysis with AI-assisted interpretation to make datasets easier to explore.
Why Does Open Innovation Matter?
Open innovation gives developers the flexibility to inspect, adapt, and improve the tools they use.
Using an open-weight model through local inference can also give users greater control over where their data is processed, reducing dependence on proprietary hosted AI APIs.
For AIXpo, this approach supports experimentation with AI-assisted data exploration while keeping the underlying application accessible and adaptable.
What I Learned
Building AIXpo helped me explore how data-processing tools and open-weight AI can work together in a practical application.
It also highlighted the importance of making analytical results understandable and connecting technical insights to useful real-world decisions.
Future Improvements
Potential improvements include more reliable calculation tools, support for additional file formats, stronger data validation, and more personalised recommendations based on outdoor activity patterns.
Conclusion
AIXpo explores a simple idea: use AI to understand data, then turn those insights into meaningful action beyond the screen.
Top comments (0)