[Advanced] - [Python] - Build processing data pipeline using 100 % open sources. The idea for this project comes from one sentence "Turn Your Laptop Into A Personal Analytics Engine"

Docker deployment of Dagster, DBT, and OpenMetadata

A comprehensive data orchestration pipeline built with Dagster for processing and analyzing bike-sharing station data from Wrocław's WRM (Wrocławski Rower Miejski) system.

A cross-platform solution for Few-Shot Instance Segmentation on mobile devices. It leverages a split-model architecture using DINOv3 as a static feature extractor and a lightweight, dynamically trained Logistic Regression classifier for specific objects.

CDC data pipeline for ecommerce market, using Nike website

🍀A data platform analyses 50,000+ LinkedIn job postings (2023–2024), provides insights into hiring trends and workforce demand