D

data analysis

Laravel based wordleSolver

A personal project to advance my career in data science as a whole.

Analysis of Kilter Board data, along with predictive models for V-grades based on holds and angle.

Analysis of Tension Board 2 data, along with predictive models for V-grades based on holds and angle.

DARTS/qemu-web-desktop: A web service that launches remote desktop virtual machines and displays them in your browser.

Autonomous Loop is a self-hosted Continuous Improvement Operating System designed for air-gapped AI factories. It enables organizations to continuously monitor, evaluate, govern, and improve AI applications through observability, data drift detection, human review workflows, autonomous improvement agents, and intelligence lifecycle management while keeping models, data, and operations under full control.

CortexCFO is an AGPL-3.0+ locally hosted AI CFO platform that transforms historical financial data into future strategy. It provides businesses with private financial intelligence through expense forecasting, cash flow prediction, risk detection, and AI-powered recommendations while keeping sensitive financial data under the organization's control.

PopMuse Data is an open source AI-driven analytics platform that maps the relationship between birthrates and creativity across countries and regions. By combining global demographic data with multi-factor creativity indicators—such as patents, cultural output, innovation metrics, and scientific publications—PopMuse Data reveals how population dynamics influence creative productivity. With automated data ingestion, correlation modeling, and interactive visualizations, it provides a clear, intelligent view of humanity’s creative patterns.

This software computes the electrical energy requirements of a fleet of vehicles. It also determines how much of this energy can be offset by renewable energy. It does all this by analyzing the fleet's GPS traces and applying EV and PV models. Please contact us if you require the source code. Contact details are provided on our project website: 🔗 www.ev-fleet-sim.online

MindLedger for Real Estate is a modular, self-hostable real estate operating system that unifies CRM, listings, marketing, analytics, compliance, accessibility, and AI automation into a single open-source platform. Built under the AGPL-3.0+ license, it is designed for continuous evolution through community contributions, strict legal compliance, and a dual-AI architecture that supports both public-facing user assistance and agent-side operational intelligence.

An open-source data journalism platform for acquiring, processing, and analyzing leaked datasets and public records.

Finds properties of Greenland fjords (e.g., length, width, bathymetry) and aggregates these along the length of the fjord at specified intervals (e.g., 10 km). Additional raster data can be aggregated along the fjord, such as sea-ice, chlorophyll-a, or turbidity.

See a snapshot of the fjords here: https://os.zhdk.cloud.switch.ch/spi-greenfjord-public/FjordProperties/fjord_polygons.html

Desktop application for interactive data analysis and visualization built in C++ and Qt6, featuring data preprocessing, custom plots, and ML algorithms including decision trees, clustering, and association rules.

Practical tasks on Deep Learning (DL) and Neural Networks (NN). 🤖

Fundamental theory and practice in Data Science (DS). 🧮

Tracks and heatmaps using the GPS tracks.

memory.fm is a web application for exploring music listening history from Last.fm and Spotify.

Building a pandemic simulation program inspired by the model SIR (susceptible, infectious, removed).

Projet académique de Master 2 en Python portant sur l’analyse de la qualité de l’air en France et en Île-de-France. Le projet combine scraping de données, traitement de données environnementales, analyse statistique des concentrations de polluants atmosphériques et visualisation cartographique des indices de qualité de l’air. Les analyses portent notamment sur les polluants NO₂, O₃ et PM10, avec une étude temporelle des données Airparif de 2014 à 2017.

Mots-clés :

python data-science web-scraping data-analysis data-visualization air-quality environmental-data geospatial-analysis time-series pandas