AI Autonomous Data Scientist

AI Autonomous Data Scientist is a Streamlit application that turns a CSV upload and a business question into an exploratory analysis, baseline machine learning models, visual recommendations, and an executive report.

What it does

• Upload a CSV dataset.
• Ask a business question in natural language.
• Profile columns, missing values, data types, and candidate targets.
• Clean common tabular data issues.
• Train baseline classification or regression models.
• Compare model quality with clear metrics.
• Generate useful charts automatically.
• Produce a plain-English analysis report.

Quick start

python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt
streamlit run app.py

Project status

This is a portfolio-ready prototype focused on tabular CSV workflows. It uses deterministic local analysis by default and includes an optional AI narrative layer that can be connected to an LLM provider later.