D

dataset

The OpenPowerlifting Project. https://www.openpowerlifting.org

A Hybrid Architecture for Multisensor 3D Reconstruction with Gaussian-based Splatting

The Open Energy Tracker is an open data platform for monitoring and visualizing energy policy targets.

🐵 Greasemonkey userscripts

A Python package designed to support scientists throughout the entire lifecycle of their research data.

Enterprise-Grade Account Moderation & Enforcement Toolkit

BETA: Dependency Scanning for supported projects

GEOP4TH (pronounced /ʤiɒpɑːθ/ jee-uh-pa-th for GEOspatial Python Pre-Processing Platform for Trajectories in Hydro-socio-ecosystems) is a collection of generic, format-agnostic, python tools (geobricks) designed to easily standardize, manipulate and visualize space-time data. These geobricks are made to be assembled into complete pre-processing workflows for specific data or to specific models. Such workflows can be collaboratively developped and shared within GEOP4TH. In the end, this toolbox aims at facilitating working on hydro-socio-ecosystems trajectories and diagnostics. Have fun! :)

A production-oriented Machine Learning pipeline that predicts whether an active user session will result in a purchase.

Model: XGBoost Classifier optimized for class imbalance.

Performance: ROC AUC 0.936 | F1-score 0.71 (at 0.30 threshold).

Key Features: Reproducible environment (uv), modular CLI for training/inference, leakage-free preprocessing, and SHAP interpretability analysis.

Data: UCI Online Shoppers Purchasing Intention Dataset.

Tech Stack: Python, XGBoost, Scikit-learn, Pandas, SHAP.

A collection of scripting and programming notes I've produced over the years in a searchable web format

CFD post-processing tools in python.

Benchmarking open source hydrological model Shyft: https://gitlab.com/shyft-os/shyft. This repo contains helper scripts for simulation setup, results analysis and preparation of figures for publication: O.Silantyeva and S.Huang “Benchmarking Shyft hydrologic model performance of streamflow simulations in mainland Norway"

Python for permafrost temperature data

Level-Set Particle And Geometry GEnerator (LS-PAGGE): Accurate representations of arbitrary particle shapes through the creation, simplification, and modification of signed distance functions. For more detail, see https://doi.org/10.1016/j.powtec.2026.122134

Parking Management System (ANPR) This project is a high-performance Automatic Number Plate Recognition (ANPR) system designed for parking management. It utilizes a custom-trained YOLO model for vehicle and plate detection, optimized ROI extraction, and a CRNN (Convolutional Recurrent Neural Network) architecture for high-accuracy OCR.

Analysis and reports of detection dataset