data-optimization

A Python tool to identify and remove similar-looking images from a dataset. Utilizes image preprocessing and hashing techniques for efficient comparison.

Official Tensorflow implementation for ActiveTCR: Active Learning Framwork for Cost-Effective TCR-Epitope Binding Affinity Prediction

Lobster data analysis and modelling using Python

A CLI-based, open-source AI memory system that uses an existing local LLM to analyze and permanently store information from text-based sources such as PDFs, XLSX, DOCX, TXT, CSV, and JSON. The system converts data into an efficient searchable representation, stores it locally, and retrieves relevant information when answering questions

Production Delta Lake Medallion architecture. Orchestrates Bronze→Silver→Gold pipeline with PII masking, deduplication, MERGE/Upsert, OPTIMIZE/VACUUM, and Airflow DAGs.

A feature optimization module for high-dimensional datasets (bioinformatics-leaning). It automates variance filtering and backward elimination to remove redundant features while preserving meaningful predictive signal. Designed to boost classifier performance, interpretability, and efficiency.

LiderAhenk ile uyumlu çalışan bu proje, "Uçta Bilişim (Edge Computing)" mimarisini benimseyen akıllı bir uçbirim ve hibrit telemetri ajanı prototipidir. Mevcut izleme sistemlerinin yarattığı ağ darboğazı ve sunucu G/Ç yükü sorunlarını, veriyi kaynağında işleyerek sunucu yükünü minimize eder.

AutoSQL — Self-optimizing SQL query pipeline. Automatically rewrites slow queries, measures speedup, and keeps improvements. One file, zero dependencies, free API.