This project provides EDA, a small ML pipeline, a SQLite database, and a Streamlit app to explore a supply chain Excel dataset.
Quick steps (Windows PowerShell):
- Create a virtual environment and activate it:
python -m venv .venv
.\.venv\Scripts\Activate.ps1- Install dependencies:
pip install -r requirements.txt- Create the database from Excel:
python db_setup.py- Train a model (if numeric data exists):
python train_model.py- Run the Streamlit app:
streamlit run app.pyNotes:
- The scripts try to be resilient to different column names, but you may need to adapt
db_setup.pyandtrain_model.pyfor your dataset. - If pandas complains about reading Excel, ensure
openpyxlis installed (it's in requirements.txt).