Inspiration
Many people have valuable data but do not know how to analyze it. Traditional data analysis requires writing code, choosing the right chart, and understanding statistics. We wanted to make data exploration as simple as asking a question.
What it does
DataLens is an AI-powered data analysis assistant. Users upload a CSV file and ask questions in plain English, such as:
- Which category generated the most revenue?
- How did sales change over time?
- Are there any unusual records?
DataLens profiles the dataset, generates reproducible pandas analysis, creates charts, detects anomalies, and explains the results in clear language.
How we built it
We built the application with Python and Streamlit. pandas and NumPy handle data processing, while Plotly creates interactive visualizations. GPT-5.6 interprets user questions and helps generate analysis steps. Codex helped us design the project structure, implement features, debug issues, and improve the user experience.
To make the results more trustworthy, the application separates AI-generated explanations from actual calculations. Users can inspect the generated analysis code and see the data used to support each conclusion.
Challenges
The biggest challenge was handling different CSV formats, missing values, dates, and ambiguous natural-language questions. We added data profiling, validation, error handling, and transparent code output so users can understand how each result was produced.
What we learned
We learned that a useful AI data tool needs more than a chatbot interface. Reliable data processing, clear visual feedback, reproducibility, and graceful error handling are equally important.
What's next
We plan to add support for larger datasets, additional file formats, collaborative reports, and more advanced statistical analysis.
Log in or sign up for Devpost to join the conversation.