Project narrative
A data science pipeline tool built with Streamlit that enables users to process, visualize data, and train models without writing code.
Users upload CSV or Excel files, profile datasets, and apply preprocessing steps with side-by-side panels showing original vs. transformed data. Every dropped column, type conversion, or imputed value is immediately visible.
After preprocessing, users can train scikit-learn models, review metrics, and download both the cleaned dataset and model artifacts along with reports. Built with Pandas, NumPy, Matplotlib, and Seaborn under the hood.