mirror of
https://github.com/ArthurDanjou/artsite.git
synced 2026-01-14 13:54:05 +01:00
feat: Add personal profile, projects, and skills documentation
- Created index.md for personal introduction and interests. - Added languages.json to specify language proficiencies. - Developed profile.md detailing academic background, skills, and career goals. - Introduced multiple project markdown files showcasing personal and academic projects, including ArtChat, ArtHome, and various data science initiatives. - Implemented skills.json to outline technical skills and competencies. - Compiled uses.md to document hardware and software tools utilized for development and personal projects.
This commit is contained in:
77
content/contact.json
Normal file
77
content/contact.json
Normal file
@@ -0,0 +1,77 @@
|
||||
{
|
||||
"contact": [
|
||||
{
|
||||
"id": "personal-email",
|
||||
"name": "Email Personnel",
|
||||
"description": "Contactez-moi pour des questions personnelles",
|
||||
"category": "communication",
|
||||
"icon": "i-ph-envelope-simple-duotone",
|
||||
"value": "https://go.arthurdanjou.fr/mail-perso",
|
||||
"priority": 1
|
||||
},
|
||||
{
|
||||
"id": "professional-email",
|
||||
"name": "Email Professionnel",
|
||||
"description": "Pour les opportunités professionnelles et collaborations",
|
||||
"category": "communication",
|
||||
"icon": "i-ph-envelope-simple-duotone",
|
||||
"value": "https://go.arthurdanjou.fr/mail-pro",
|
||||
"priority": 1
|
||||
},
|
||||
{
|
||||
"id": "linkedin",
|
||||
"name": "LinkedIn",
|
||||
"description": "Profil professionnel et réseau",
|
||||
"category": "social",
|
||||
"icon": "i-ph:linkedin-logo-duotone",
|
||||
"value": "https://go.arthurdanjou.fr/linkedin",
|
||||
"priority": 2
|
||||
},
|
||||
{
|
||||
"id": "github",
|
||||
"name": "GitHub",
|
||||
"description": "Projets open-source et portefeuille technique",
|
||||
"category": "social",
|
||||
"icon": "i-ph:github-logo-duotone",
|
||||
"value": "https://go.arthurdanjou.fr/github",
|
||||
"username": "ArthurDanjou",
|
||||
"priority": 1
|
||||
},
|
||||
{
|
||||
"id": "twitter",
|
||||
"name": "Twitter / X",
|
||||
"description": "Actualités tech et partages d'idées",
|
||||
"category": "social",
|
||||
"icon": "i-ph:x-logo-duotone",
|
||||
"value": "https://go.arthurdanjou.fr/twitter",
|
||||
"priority": 3
|
||||
},
|
||||
{
|
||||
"id": "discord",
|
||||
"name": "Discord",
|
||||
"description": "Discussions en temps réel et communauté",
|
||||
"category": "communication",
|
||||
"icon": "i-ph:discord-logo-duotone",
|
||||
"value": "https://go.arthurdanjou.fr/discord",
|
||||
"priority": 2
|
||||
},
|
||||
{
|
||||
"id": "personal-website",
|
||||
"name": "Site Personnel",
|
||||
"description": "Accueil et portefeuille complet",
|
||||
"category": "web",
|
||||
"icon": "i-ph:globe-duotone",
|
||||
"value": "https://arthurdanjou.fr",
|
||||
"priority": 1
|
||||
},
|
||||
{
|
||||
"id": "status-page",
|
||||
"name": "Statut des Services",
|
||||
"description": "État et disponibilité des services",
|
||||
"category": "infrastructure",
|
||||
"icon": "i-ph:fire-duotone",
|
||||
"value": "https://go.arthurdanjou.fr/status",
|
||||
"priority": 3
|
||||
}
|
||||
]
|
||||
}
|
||||
15
content/education/bachelor.md
Normal file
15
content/education/bachelor.md
Normal file
@@ -0,0 +1,15 @@
|
||||
---
|
||||
title: Bachelor's Degree in Mathematics
|
||||
type: Bachelor
|
||||
institution: Paris-Saclay University
|
||||
location: Paris, France
|
||||
startDate: 2021-09
|
||||
endDate: 2024-06
|
||||
duration: 3 years
|
||||
description: Comprehensive study of pure and applied mathematics, providing a strong foundation in mathematical theory and problem-solving.
|
||||
tags:
|
||||
- Mathematics
|
||||
- Physics
|
||||
- Computer Science
|
||||
emoji: 🎓
|
||||
---
|
||||
16
content/education/m1.md
Normal file
16
content/education/m1.md
Normal file
@@ -0,0 +1,16 @@
|
||||
---
|
||||
title: Master's Degree in Applied Mathematics (Year 1)
|
||||
type: Master
|
||||
institution: Paris Dauphine-PSL University
|
||||
location: Paris, France
|
||||
startDate: 2023-09
|
||||
endDate: 2024-06
|
||||
duration: 1 year
|
||||
description: First year of specialized study in applied mathematics, combining theoretical knowledge with practical applications in data science, optimization, and machine learning.
|
||||
tags:
|
||||
- Applied Mathematics
|
||||
- Data Science
|
||||
- Machine Learning
|
||||
- Optimization
|
||||
emoji: 📚
|
||||
---
|
||||
16
content/education/m2.md
Normal file
16
content/education/m2.md
Normal file
@@ -0,0 +1,16 @@
|
||||
---
|
||||
title: Master's Degree in Applied Mathematics (Year 2)
|
||||
type: Master
|
||||
institution: Paris Dauphine-PSL University
|
||||
location: Paris, France
|
||||
startDate: 2024-09
|
||||
endDate: 2025-10
|
||||
duration: 1 year
|
||||
description: Second year of advanced study in applied mathematics with focus on specialized topics, research projects, and professional applications in industry and research.
|
||||
tags:
|
||||
- Applied Mathematics
|
||||
- Advanced Machine Learning
|
||||
- Data Engineering
|
||||
- Research
|
||||
emoji: 🏆
|
||||
---
|
||||
18
content/experiences/artdanjproduction.md
Normal file
18
content/experiences/artdanjproduction.md
Normal file
@@ -0,0 +1,18 @@
|
||||
---
|
||||
title: Freelancer
|
||||
type: Freelance
|
||||
company: ArtDanjProduction
|
||||
companyUrl: https://go.arthurdanjou.fr/website
|
||||
location: Paris, France
|
||||
startDate: 2022-02
|
||||
endDate: null
|
||||
duration: 3+ years
|
||||
description: As a freelancer, I designed, developed, and maintained various personal projects, exploring new programming languages and technologies. I also write documentation and articles related to my projects, fix bugs, and ensure their smooth operation in production. Additionally, I manage my Proxmox and Docker-based homelab, hosting multiple services, and set up network infrastructure to optimize performance and stability.
|
||||
tags:
|
||||
- Java
|
||||
- TypeScript
|
||||
- HomeLab
|
||||
- Docker
|
||||
- Self-Hosted
|
||||
emoji: 💼
|
||||
---
|
||||
18
content/experiences/erisium.md
Normal file
18
content/experiences/erisium.md
Normal file
@@ -0,0 +1,18 @@
|
||||
---
|
||||
title: Junior Developer
|
||||
type: Employment
|
||||
company: Erisium
|
||||
companyUrl: https://x.com/Erisium
|
||||
location: Remote, France
|
||||
startDate: 2021-09
|
||||
endDate: 2022-09
|
||||
duration: 1 year
|
||||
description: At Erisium, one of the most popular French-speaking Minecraft servers, I worked as a Junior Java Developer. I developed mini-games designed by the game design team, and worked on backend infrastructure optimizations to handle several thousand concurrent players. This experience allowed me to solve a wide range of complex bugs and to grow within a collaborative, high-performance technical environment.
|
||||
tags:
|
||||
- Java
|
||||
- Docker
|
||||
- Minecraft
|
||||
- Backend
|
||||
- Game Development
|
||||
emoji: 🎮
|
||||
---
|
||||
19
content/experiences/hackathon-dirisi.md
Normal file
19
content/experiences/hackathon-dirisi.md
Normal file
@@ -0,0 +1,19 @@
|
||||
---
|
||||
title: Hackathon CND - Machine Learning for Cybersecurity
|
||||
type: Hackathon
|
||||
company: Commissariat au numérique de défense (CND), French Armies ministry
|
||||
companyUrl: https://www.defense.gouv.fr/cnd
|
||||
location: Fort du Mont-Valérien, Suresnes, France
|
||||
startDate: 2025-11
|
||||
endDate: 2025-11
|
||||
duration: 3 days
|
||||
description: Developed a Python ML pipeline during the Dirisi hackathon to classify system logs for bug and attack detection. Implemented feature extraction and preprocessing, trained and evaluated models (tree-based and lightweight neural), tuned thresholds to favor recall, and delivered a realtime prototype with visualization and reproducible code in collaboration with CND engineers. Implemented a Streamlit application to test the classifier interactively and used an LLM to generate contextual help explaining the likely origin and indicators of detected bugs or attacks for end users.
|
||||
tags:
|
||||
- Python
|
||||
- Machine Learning
|
||||
- AI
|
||||
- Cybersecurity
|
||||
- Streamlit
|
||||
- LLM
|
||||
emoji: 🔒
|
||||
---
|
||||
17
content/experiences/picard.md
Normal file
17
content/experiences/picard.md
Normal file
@@ -0,0 +1,17 @@
|
||||
---
|
||||
title: Sales Assistant II
|
||||
type: Student Job
|
||||
company: Picard Surgelés
|
||||
companyUrl: https://picard.fr
|
||||
location: Paris, France
|
||||
startDate: 2022-09
|
||||
endDate: 2024-10
|
||||
duration: 2+ years
|
||||
description: As part of my student job at Picard, I welcomed and advised customers while handling product restocking and in-store deliveries. I placed orders according to overall stock, monitored the cold chain, and maintained freezer cleanliness, ensuring product quality and safety.
|
||||
tags:
|
||||
- Sales
|
||||
- Customer Service
|
||||
- Retail
|
||||
- Team Work
|
||||
emoji: 🛒
|
||||
---
|
||||
18
content/experiences/sevetys.md
Normal file
18
content/experiences/sevetys.md
Normal file
@@ -0,0 +1,18 @@
|
||||
---
|
||||
title: Data Analyst Intern
|
||||
type: Internship
|
||||
company: Sevetys
|
||||
companyUrl: https://sevetys.fr
|
||||
location: Paris, France
|
||||
startDate: 2025-06
|
||||
endDate: 2025-07
|
||||
duration: 2 months
|
||||
description: At Sevetys, I worked as a Data Analyst on topics related to client and patient data. My responsibilities included Python development using PySpark on Microsoft Azure, data modeling based on business needs, and ensuring data quality. This experience allowed me to deepen my data engineering skills while working autonomously in a demanding cloud-based environment.
|
||||
tags:
|
||||
- Python
|
||||
- PySpark
|
||||
- Microsoft Azure
|
||||
- Data Engineering
|
||||
- Data Quality
|
||||
emoji: 📊
|
||||
---
|
||||
28
content/hobbies.md
Normal file
28
content/hobbies.md
Normal file
@@ -0,0 +1,28 @@
|
||||
---
|
||||
title: "Balance and Drive: Beyond the Data"
|
||||
description: Exploring my passions outside of data science and machine learning engineering that fuel my creativity and performance.
|
||||
---
|
||||
|
||||
While my passion for data science and machine learning engineering is at the core of what I do, I am convinced that personal balance is the key to performance and creativity. Outside of my technical projects, I nurture this balance through several key interests.
|
||||
|
||||
## ⚽ Sports & Team Dynamics
|
||||
|
||||
**Rugby and volleyball** are fundamental to my equilibrium. These team sports have taught me the importance of collective strategy, communication, and physical commitment. The dynamics of working under pressure with diverse personalities mirrors the collaborative nature of ML projects.
|
||||
|
||||
As a long-time supporter of **PSG** in football, I appreciate the tactical analysis, performance management, and data-driven decision-making that occurs at the highest level of sport—much like optimizing complex systems.
|
||||
|
||||
## 🎵 Music & Creative Problem-Solving
|
||||
|
||||
**Music** is my creative outlet and a tool for different thinking patterns. Training my ear to recognize harmony and structure translates directly to identifying elegant solutions in system design, architecture, and mathematical modeling. It reinforces my belief that great engineering, like great music, requires both technical precision and artistic intuition.
|
||||
|
||||
## 🌍 Travel & Cultural Adaptation
|
||||
|
||||
**Travel** provides essential perspective and adaptability. Having discovered highly diverse cultures since childhood—from Egypt and South Africa to Thailand and the United States—has profoundly shaped my curiosity and flexibility. This exposure to different ways of thinking and problem-solving is crucial in a constantly evolving field like AI, where understanding multiple perspectives can lead to breakthrough insights.
|
||||
|
||||
## 🏎️ Motorsports & Optimization
|
||||
|
||||
As a **Formula 1 enthusiast**, I'm fascinated by the pursuit of pure performance and optimization under constraints. F1 represents the pinnacle of real-time, data-driven strategy, where decisions are made in milliseconds based on telemetry, weather, and tactical considerations. This mirrors my approach to machine learning: extracting maximum value from available resources and constraints.
|
||||
|
||||
## 🎯 Balance as Performance
|
||||
|
||||
These passions are not escapes—they're integral to my professional success. They reinforce my commitment to continuous improvement, adaptability, and the drive to progress. It is this balance that allows me to approach every new challenge with motivation, energy, and fresh perspective.
|
||||
@@ -1,34 +0,0 @@
|
||||
---
|
||||
title: Arthur Danjou • Mathematics Lover and IA Enthusiast
|
||||
description: I'm Arthur, a Mathematics lover and IA enthusiast. I'm currently
|
||||
studying at the University of Paris Dauphine-PSL. I'm passionate about
|
||||
Mathematics, Computer Science, and Artificial Intelligence.
|
||||
---
|
||||
|
||||
Hola ! Soy :home-name, estudiante de matemáticas especializado en Estadística en la Universidad Paris-Dauphine, en Francia.
|
||||
|
||||
Con una :hover-text{hover="la tecnología avanza demasiado rápido 🤯" position="top" text="comprensión profunda"} de las tecnologías emergentes, me sitúo en el centro de un ámbito en plena expansión. Mi formación en :hover-text{hover="las matemáticas son mi mayor pasión Σ" position="right" text="matemáticas"} me permite comprender ampliamente los conceptos y las teorías que gobiernan las dichas :hover-text{hover="mi segunda pasión 📲" text="tecnologías"} y también poder concebirlas de manera eficaz.
|
||||
|
||||
Como ingeniero de software y estudiante de matemáticas, mi :hover-text{hover="mi mochila de conocimientos 🎒" text="conocimientos"} cubre
|
||||
:prose-icon[TypeScript]{color="blue" icon="i-logos:typescript-icon"},
|
||||
:prose-icon[Vue]{color="green" icon="i-logos:vue"},
|
||||
:prose-icon[Nuxt]{color="emerald" icon="i-logos:nuxt-icon"},
|
||||
:prose-icon[Adonis]{color="purple" icon="i-logos:adonisjs-icon"},
|
||||
:prose-icon[Java]{color="red" icon="i-logos:java"},
|
||||
:prose-icon[Python]{color="amber" icon="i-logos:python"},
|
||||
:prose-icon[R]{color="blue" icon="i-logos:r-lang"},
|
||||
esto me permite :hover-text{hover="entender rápidamente la complejidad de los proyectos 🏎️" text="comprender"} las diferentes necesidades de los proyectos matemáticos, y proponer las mejores soluciones.
|
||||
Utilizo herramientas como
|
||||
:prose-icon[scikit-learn]{color="orange" icon="devicon-scikitlearn"} para el aprendizaje supervisado,
|
||||
:prose-icon[pandas]{color="blue" icon="i-logos:pandas-icon"} para la manipulación eficiente de datos,
|
||||
:prose-icon[NumPy]{color="indigo" icon="i-logos:numpy"} para el cálculo científico, y
|
||||
:prose-icon[TensorFlow]{color="orange" icon="i-logos:tensorflow"} así como :prose-icon[PyTorch]{color="orange" icon="i-logos:pytorch-icon"} para construir y entrenar modelos de aprendizaje profundo. También he aprendido otras tecnologías importantes como :prose-icon[Docker]{color="sky" icon="i-logos:docker-icon"},
|
||||
:prose-icon[Redis]{color="red" icon="i-logos:redis"},
|
||||
:prose-icon[MySQL]{color="zinc" icon="i-logos:mysql-icon"} y
|
||||
:prose-icon[Git]{color="orange" icon="i-logos:git-icon"} que :hover-text{hover="todas estas tecnologías se complementan 📎" text="completan"} mis competencias.
|
||||
|
||||
Estas herramientas me permiten ir desde :hover-text{hover="Exploración, limpieza, reorganización…" text="preparación de datos"} hasta :hover-text{hover="Entrenamiento, evaluación, despliegue" text="despliegue"} de modelos en entornos reales, siempre con rigurosidad estadística y un enfoque en el rendimiento. Me apasiona la IA y la :hover-text{hover="La IA es el futuro de la tecnología 🤖" text="ciencia de datos"} .
|
||||
|
||||
Estoy :hover-text{hover="me gusta estar siempre al día 🖥️" position="top" text="constantemente"} aprendiendo cosas nuevas, desde la tecnología hasta las finanzas, pasando por el emprendimiento. Me gusta :hover-text{hover="me encanta compartir y ayudar a los demás 🫂" text="compartir"} mis conocimientos y aprender nuevos teoremas y tecnologías. Soy una persona :hover-text{hover="busco cosas nuevas que descubrir 🔍" text="curiosa"} y con el deseo de seguir aprendiendo y creciendo a lo largo de toda mi vida.
|
||||
|
||||
Aparte de la programación, me gusta el :hover-text{hover="el deporte me permite gastar mi energía 🏋️♂️" text="deporte"} y :hover-text{hover="los viajes me permiten desconectar ✈️" text="viajar"} . Mi pasión, mi compromiso y mis ganas de aprender y mejorar son las cualidades que me permiten triunfar en mi :hover-text{hover="carrera que ya he empezado, y le queda mucho para terminar 😎" text="carrera"} y en mis :hover-text{hover="solo me quedan 2 años de estudios 💪" text="estudios"} .
|
||||
@@ -1,46 +0,0 @@
|
||||
---
|
||||
title: Arthur Danjou • Mathematics Lover and IA Enthusiast
|
||||
description: I'm Arthur, a Mathematics lover and IA enthusiast. I'm currently
|
||||
studying at the University of Paris Dauphine-PSL. I'm passionate about
|
||||
Mathematics, Computer Science, and Artificial Intelligence.
|
||||
---
|
||||
|
||||
Salut, je suis :home-name, étudiant en mathématiques spécialisé en Statistiques à l'Université Paris-Dauphine en France.
|
||||
|
||||
Avec une :hover-text{hover="La technologie évolue beaucoup trop vite 🤯" position="top" text="compréhension profonde"} des technologies émergentes, je suis au cœur d'un domaine en pleine expansion. Ma formation en :hover-text{hover="Les
|
||||
mathématiques sont ma principale passion ∑" position="right" text="mathématiques"} me donne une longueur d'avance pour
|
||||
comprendre les concepts et les théories qui sous-tendent ces :hover-text{hover="Ma deuxième passion 📱" text="technologies"} et à les concevoir efficacement.
|
||||
|
||||
En tant qu'ingénieur logiciel et étudiant en mathématiques, mon :hover-text{hover="Mon sac de connaissances 🎒" text="expertise"} couvre
|
||||
:prose-icon[TypeScript]{color="blue" icon="i-logos:typescript-icon"},
|
||||
:prose-icon[Vue]{color="green" icon="i-logos:vue"},
|
||||
:prose-icon[Nuxt]{color="emerald" icon="i-logos:nuxt-icon"},
|
||||
:prose-icon[Adonis]{color="purple" icon="i-logos:adonisjs-icon"},
|
||||
:prose-icon[Java]{color="red" icon="i-logos:java"},
|
||||
:prose-icon[Python]{color="amber" icon="i-logos:python"},
|
||||
:prose-icon[R]{color="blue" icon="i-logos:r-lang"},
|
||||
ce qui me permet de :hover-text{hover="Comprendre rapidement la complexité des projets 🏎️" text="comprendre"} les
|
||||
différents besoins des projets mathématiques et de proposer les meilleures solutions.
|
||||
J'utilise des outils comme
|
||||
:prose-icon[scikit-learn]{color="orange" icon="i-devicon-scikitlearn"} pour l'apprentissage supervisé,
|
||||
:prose-icon[pandas]{color="blue" icon="i-logos:pandas-icon"} pour la manipulation efficace de données,
|
||||
:prose-icon[NumPy]{color="indigo" icon="i-logos:numpy"} pour le calcul scientifique, et
|
||||
:prose-icon[TensorFlow]{color="orange" icon="i-logos:tensorflow"} ainsi que :prose-icon[PyTorch]{color="orange" icon="i-logos:pytorch-icon"} pour la création et l'entraînement de modèles profonds.
|
||||
J'ai également appris d'autres technologies importantes, telles que
|
||||
:prose-icon[Docker]{color="sky" icon="i-logos:docker-icon"},
|
||||
:prose-icon[Redis]{color="red" icon="i-logos:redis"},
|
||||
:prose-icon[MySQL]{color="zinc" icon="i-logos:mysql-icon"} et
|
||||
:prose-icon[Git]{color="orange" icon="i-logos:git-icon"} pour :hover-text{hover="Toutes ces technologies se complètent 🔗" text="compléter"} mes connaissances.
|
||||
|
||||
Ma maîtrise de ces bibliothèques me permet de passer de la :hover-text{hover="Exploration, nettoyage, mise en forme…" text="préparation des données"} jusqu'au :hover-text{hover="Entraînement, évaluation, déploiement" text="déploiement"} de modèles dans des environnements réels, toujours avec rigueur statistique et souci de performance.
|
||||
Je suis passionné par l'IA et la :hover-text{hover="L'IA est l'avenir de la technologie 🤖" text="science des données"} .
|
||||
|
||||
Je suis :hover-text{hover="Je dois toujours chercher à être à jour 🖥️" position="top" text="constamment"} dans
|
||||
l'apprentissage de nouvelles choses, de la technologie à la finance en passant par l'entrepreneuriat. J'aime
|
||||
:hover-text{hover="J'aime partager et aider les autres 🫂" text="partager"} mes connaissances et apprendre de nouveaux
|
||||
théorèmes et technologies. Je suis une personne :hover-text{hover="Je cherche à découvrir de nouvelles choses" text="curieuse"} et désireuse de continuer à apprendre et à grandir tout au long de ma vie.
|
||||
|
||||
Outre la programmation, j'aime le :hover-text{hover="Le sport me permet de dépenser de l'énergie 🏋️♂️" text="sport"} et :hover-text{hover="Les voyages me libèrent et m'évadent ✈️" text="voyager"} .
|
||||
Ma passion, mon engagement et mon envie d'apprendre et de progresser sont les qualités qui me permettent de réussir dans
|
||||
ma :hover-text{hover="Carrière déjà commencée et loin d'être terminée 😎" text="carrière"} et mes :hover-text{hover="Il
|
||||
ne me reste que 2 ans d'études 💪" text="études"} .
|
||||
19
content/languages.json
Normal file
19
content/languages.json
Normal file
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"languages": [
|
||||
{
|
||||
"name": "French",
|
||||
"level": "Native",
|
||||
"proficiency": "C2"
|
||||
},
|
||||
{
|
||||
"name": "English",
|
||||
"level": "Fluent",
|
||||
"proficiency": "C1"
|
||||
},
|
||||
{
|
||||
"name": "Spanish",
|
||||
"level": "Intermediate",
|
||||
"proficiency": "A2"
|
||||
}
|
||||
]
|
||||
}
|
||||
98
content/profile.md
Normal file
98
content/profile.md
Normal file
@@ -0,0 +1,98 @@
|
||||
---
|
||||
title: Arthur Danjou - Data Science & Applied AI Student.
|
||||
description: Profile of Arthur Danjou, a Data Science and Applied AI student at Paris Dauphine-PSL University, highlighting his skills, experience, and career aspirations.
|
||||
---
|
||||
|
||||
# Arthur Danjou
|
||||
**Data Science & Applied AI**
|
||||
|
||||
Rigorous, curious, and motivated, I put my skills in statistics, machine learning, and applied artificial intelligence to work on concrete and innovative projects[cite: 9]. Passionate about mathematical modelling and the deployment of AI solutions, I enjoy transforming theory into measurable results[cite: 10].
|
||||
|
||||
## 📞 Contact & Links
|
||||
|
||||
* **Email:** `arthur.danjou@dauphine.eu`
|
||||
* **Portfolio:** `go.arthurdanjou.fr/portfolio`
|
||||
* **GitHub:** `go.arthurdanjou.fr/github`
|
||||
* **LinkedIn:** `go.arthurdanjou.fr/linkedin`
|
||||
|
||||
## 📍 Location
|
||||
|
||||
* **Current:** Paris, France
|
||||
* **Timezone:** Europe/Paris (CET/CEST)
|
||||
* **Remote:** Open (confirmed by "REMOTE" experience)
|
||||
|
||||
## 🗓️ Availability
|
||||
|
||||
* **Status:** Available for a final-year internship.
|
||||
* **Start Date:** **April 2026**.
|
||||
* **Contract Types:** Internship (priority).
|
||||
|
||||
## 🎯 Career Goals
|
||||
|
||||
* To join a team of Data Scientists or AI Researchers to deepen my knowledge.
|
||||
* Contribute to high-impact projects.
|
||||
* **Prepare for a future doctorate in artificial intelligence**.
|
||||
* Become an expert in Machine Learning Engineering and MLOps.
|
||||
* Combine mathematical rigor (from education) with practical engineering solutions (from experience).
|
||||
|
||||
## 💼 Work Preferences
|
||||
|
||||
* **Target Roles:** Data Scientist, AI Researcher.
|
||||
* **Industries:** AI/ML, Data Science, Health, DevOps.
|
||||
* **Work Style:** Remote, Hybrid.
|
||||
* **Company Size:** Startup, Scale-up, Enterprise.
|
||||
|
||||
## 🏆 Notable Achievements
|
||||
|
||||
* Administration of a personal home lab (servers, databases, storage, backups) for MLOps experimentation since 2022.
|
||||
* Implemented daily data cleaning pipelines on Azure with PySpark, enhancing data quality by 20-30% at Sevetys.
|
||||
* Design, development, and maintenance of web, data, and cloud projects (Python, TypeScript, Nuxt 3) via ArtDanj Production.
|
||||
* Developed an automated monthly data quality report (completeness, consistency) for business teams.
|
||||
|
||||
## 📚 Education
|
||||
|
||||
* **Master's in Applied Mathematics** (M280) - Paris Dauphine-PSL University (2023-2025)
|
||||
- Specialization: Data Science & Applied Artificial Intelligence
|
||||
- Focus: Deep Learning, Probabilistic Models, Statistical Learning Theory
|
||||
* **Bachelor's in Applied Mathematics** - Paris Dauphine-PSL University (2020-2023)
|
||||
- Foundation in linear algebra, probability, statistics, and numerical analysis
|
||||
|
||||
## 🔐 Certifications & Competencies
|
||||
|
||||
* Advanced Python & Data Science practices
|
||||
* MLOps & Cloud Infrastructure (Azure, Docker, Kubernetes)
|
||||
* Full-stack Web Development (Nuxt 3, TypeScript, Vue.js)
|
||||
* Linux System Administration & Networking
|
||||
|
||||
## 🎓 Research & Academic Interests
|
||||
|
||||
* Machine Learning Engineering and deployment pipelines
|
||||
* Probabilistic inference and Bayesian methods
|
||||
* Statistical learning theory and generalization bounds
|
||||
* Deep Learning architectures for structured data
|
||||
* Data quality and governance in production systems
|
||||
* Former rugby team captain, participating in the French school championships.
|
||||
|
||||
## 📚 Education & Core Competencies
|
||||
|
||||
### Paris Dauphine-PSL University (MSc)
|
||||
|
||||
* **Dual Expertise:** Theory & Practice in Advanced Data Science and AI Systems.
|
||||
* **Core Theoretical Focus:** Strong background in statistical modeling and advanced AI principles (Advanced Machine Learning, Learning Theory, Clustering, Deep Learning, Climate Risk Modeling).
|
||||
* **Practical Skills:** Hands-on experience in NLP, Reinforcement Learning, Generative AI, Data Quality, and Data Visualisation.
|
||||
* **Key Courses (M1/M2):** Supervised Statistical Learning, Generalised Linear Models (GLMs), Monte Carlo Methods, Data Analysis, Non-parametric Statistics, Time Series, Numerical Optimisation.
|
||||
* **Active Engagement:** Scheduled participation in the Natixis and DIRISI Hackathons.
|
||||
|
||||
### Technical Skillset
|
||||
|
||||
* **Programming:** Python, R, TypeScript, Java, Git, LaTeX.
|
||||
* **Libraries & Frameworks:** NumPy, Pandas, Scikit-learn, PyTorch, Matplotlib, Seaborn.
|
||||
* **Databases:** SQL, Redis.
|
||||
* **Cloud & DevOps:** Proxmox, Docker, Azure, Linux, SysAdmin.
|
||||
|
||||
### Statistical & AI Modeling
|
||||
|
||||
* **Multivariate Data Analysis:** Principal Component Analysis (PCA), Correspondence Analysis (CA), clustering techniques, correlation analysis.
|
||||
* **Supervised Learning:** k-NN, linear and logistic regression, CNN, Naive Bayes.
|
||||
* **Unsupervised Learning:** Clustering, dimensionality reduction, k-means, CNN.
|
||||
* **IA & Modern Models:** Natural Language Processing, Transformers, Large Language Models, AI agents, embeddings, and fine-tuning.
|
||||
38
content/projects/artchat.md
Normal file
38
content/projects/artchat.md
Normal file
@@ -0,0 +1,38 @@
|
||||
---
|
||||
slug: artchat
|
||||
title: ArtChat - Portfolio & Blog
|
||||
type: Personal Project
|
||||
description: My personal space on the web — a portfolio, a blog, and a digital lab where I showcase my projects, write about topics I care about, and experiment with design and web technologies.
|
||||
publishedAt: 2024-06-01
|
||||
readingTime: 1
|
||||
cover: artchat/cover.png
|
||||
favorite: true
|
||||
status: Active
|
||||
tags:
|
||||
- Vue.js
|
||||
- Nuxt
|
||||
- TypeScript
|
||||
- Tailwind CSS
|
||||
- Web
|
||||
emoji: 🌍
|
||||
---
|
||||
|
||||
[**ArtChat**](https://go.arthurdanjou.fr/website) is my personal space on the web — a portfolio, a blog, and a digital lab where I showcase my projects, write about topics I care about, and experiment with design and web technologies.
|
||||
|
||||
It's designed to be fast, accessible, and fully responsive. The site also serves as a playground to explore and test modern frontend tools.
|
||||
|
||||
## ⚒️ Tech Stack
|
||||
|
||||
- **UI** → [Vue.js](https://vuejs.org/): A progressive JavaScript framework for building interactive interfaces.
|
||||
- **Framework** → [Nuxt](https://nuxt.com/): A powerful full-stack framework built on Vue, perfect for modern web apps.
|
||||
- **Content System** → [Nuxt Content](https://content.nuxtjs.org/): File-based CMS to manage blog posts and pages using Markdown.
|
||||
- **Design System** → [Nuxt UI](https://nuxtui.com/): Fully styled, customizable UI components tailored for Nuxt.
|
||||
- **CMS & Editing** → [Nuxt Studio](https://nuxt.studio): Visual editing and content management integrated with Nuxt Content.
|
||||
- **Language** → [TypeScript](https://www.typescriptlang.org/): A statically typed superset of JavaScript.
|
||||
- **Styling** → [Sass](https://sass-lang.com/) & [Tailwind CSS](https://tailwindcss.com/): Utility-first CSS framework enhanced with SCSS flexibility.
|
||||
- **Deployment** → [NuxtHub](https://hub.nuxt.com/): Cloudflare-powered platform for fast, scalable Nuxt app deployment.
|
||||
- **Package Manager** → [pnpm](https://pnpm.io/): A fast, disk-efficient package manager for JavaScript/TypeScript projects.
|
||||
- **Linter** → [ESLint](https://eslint.org/): A tool for identifying and fixing problems in JavaScript/TypeScript code.
|
||||
- **ORM** → [Drizzle ORM](https://orm.drizzle.team/): A lightweight, type-safe ORM for TypeScript.
|
||||
- **Validation** → [Zod](https://zod.dev/): A TypeScript-first schema declaration and validation library with full static type inference.
|
||||
- **Deployment** → [NuxtHub](https://hub.nuxt.com/): A platform to deploy and scale Nuxt apps globally with minimal latency and full-stack capabilities.
|
||||
30
content/projects/arthome.md
Normal file
30
content/projects/arthome.md
Normal file
@@ -0,0 +1,30 @@
|
||||
---
|
||||
slug: arthome
|
||||
title: ArtHome - Browser Homepage
|
||||
type: Personal Project
|
||||
description: A customizable browser homepage that lets you organize all your favorite links in one place with categories, tabs, icons and colors.
|
||||
publishedAt: 2024-09-04
|
||||
readingTime: 1
|
||||
cover: arthome/cover.png
|
||||
status: Active
|
||||
tags:
|
||||
- Nuxt
|
||||
- Vue.js
|
||||
- Web
|
||||
- Productivity
|
||||
emoji: 🏡
|
||||
---
|
||||
|
||||
[ArtHome](https://go.arthurdanjou.fr/arthome) is a customizable browser homepage that lets you organize all your favorite links in one place.
|
||||
|
||||
Create categories and tabs to group your shortcuts, personalize them with icons and colors, and make the page private if you want to keep your links just for yourself. The interface is clean, responsive, and works across all modern browsers.
|
||||
|
||||
## 🛠️ Built with
|
||||
|
||||
- [Nuxt](https://nuxt.com): An open-source framework for building performant, full-stack web applications with Vue.
|
||||
- [NuxtHub](https://hub.nuxt.com): A Cloudflare-powered platform to deploy and scale Nuxt apps globally with minimal latency and full-stack capabilities.
|
||||
- [NuxtUI](https://ui.nuxt.com): A sleek and flexible component library that helps create beautiful, responsive UIs for Nuxt applications.
|
||||
- [ESLint](https://eslint.org): A linter that identifies and fixes problems in your JavaScript/TypeScript code.
|
||||
- [Drizzle ORM](https://orm.drizzle.team/): A lightweight, type-safe ORM built for TypeScript, designed for simplicity and performance.
|
||||
- [Zod](https://zod.dev/): A TypeScript-first schema declaration and validation library with full static type inference.
|
||||
- and a lot of ❤️
|
||||
46
content/projects/artlab.md
Normal file
46
content/projects/artlab.md
Normal file
@@ -0,0 +1,46 @@
|
||||
---
|
||||
slug: artlab
|
||||
title: ArtLab - Personal HomeLab
|
||||
type: Infrastructure Project
|
||||
description: A personal homelab environment where I deploy, test, and maintain self-hosted services with privacy-focused networking through VPN and Cloudflare Tunnels.
|
||||
publishedAt: 2025-09-04
|
||||
readingTime: 1
|
||||
cover: artlab/cover.png
|
||||
favorite: true
|
||||
status: Active
|
||||
tags:
|
||||
- Docker
|
||||
- Proxmox
|
||||
- HomeLab
|
||||
- Self-Hosted
|
||||
- Infrastructure
|
||||
emoji: 🏡
|
||||
---
|
||||
|
||||
[**ArtLab**](https://go.arthurdanjou.fr/status) is my personal homelab, where I experiment with self-hosting and automation.
|
||||
|
||||
My homelab is a self-hosted environment where I deploy, test, and maintain personal services. Everything is securely exposed **only through a private VPN** using [Tailscale](https://tailscale.com/), ensuring encrypted, access-controlled connections across all devices.
|
||||
For selected services, I also use **Cloudflare Tunnels** to enable secure external access without opening ports or exposing my public IP.
|
||||
|
||||
## 🛠️ Running Services
|
||||
|
||||
- **MinIO**: S3-compatible object storage for static files and backups.
|
||||
- **Immich**: Self-hosted photo management platform — a private alternative to Google Photos.
|
||||
- **Jellyfin**: Media server for streaming movies, shows, and music.
|
||||
- **Portainer & Docker**: Container orchestration and service management.
|
||||
- **Traefik**: Reverse proxy and automatic HTTPS with Let's Encrypt.
|
||||
- **Homepage**: A sleek dashboard to access and monitor all services.
|
||||
- **Proxmox**: Virtualization platform used to manage VMs and containers.
|
||||
- **Uptime Kuma**: Self-hosted uptime monitoring.
|
||||
- **Home Assistant**: Smart home automation and device integration.
|
||||
- **AdGuard Home**: Network-wide ad and tracker blocking via DNS.
|
||||
- **Beszel**: Self-hosted, lightweight alternative to Notion for notes and knowledge management.
|
||||
- **Palmr**: Personal logging and journaling tool.
|
||||
|
||||
## 🖥️ Hardware
|
||||
|
||||
- **Beelink EQR6**: AMD Ryzen mini PC, main server host.
|
||||
- **TP-Link 5-port Switch**: Network connectivity for all devices.
|
||||
- **UGREEN NASync DXP4800 Plus**: 4-bay NAS, currently populated with 2 × 8TB drives for storage and backups.
|
||||
|
||||
This homelab is a sandbox for DevOps experimentation, infrastructure reliability, and privacy-respecting digital autonomy.
|
||||
75
content/projects/artstudies.md
Normal file
75
content/projects/artstudies.md
Normal file
@@ -0,0 +1,75 @@
|
||||
---
|
||||
slug: artstudies
|
||||
title: ArtStudies - Academic Projects Collection
|
||||
type: Academic Project
|
||||
description: A curated collection of mathematics and data science projects developed during my academic journey, spanning Bachelor's and Master's studies.
|
||||
publishedAt: 2023-09-01
|
||||
readingTime: 1
|
||||
favorite: true
|
||||
status: Active
|
||||
tags:
|
||||
- Python
|
||||
- R
|
||||
- Data Science
|
||||
- Machine Learning
|
||||
- Mathematics
|
||||
emoji: 🎓
|
||||
---
|
||||
|
||||
# ArtStudies
|
||||
|
||||
[ArtStudies Projects](https://github.com/ArthurDanjou/artstudies) is a curated collection of academic projects completed throughout my mathematics studies. The repository showcases work in both _Python_ and _R_, focusing on mathematical modeling, data analysis, and numerical methods.
|
||||
|
||||
The projects are organized into two main sections:
|
||||
- **L3** – Third year of the Bachelor's degree in Mathematics
|
||||
- **M1** – First year of the Master's degree in Mathematics
|
||||
- **M2** – Second year of the Master's degree in Mathematics
|
||||
|
||||
## 📁 File Structure
|
||||
|
||||
- `L3`
|
||||
- `Analyse Matricielle`
|
||||
- `Analyse Multidimensionnelle`
|
||||
- `Calculs Numériques`
|
||||
- `Équations Différentielles`
|
||||
- `Méthodes Numériques`
|
||||
- `Probabilités`
|
||||
- `Projet Numérique`
|
||||
- `Statistiques`
|
||||
|
||||
- `M1`
|
||||
- `Data Analysis`
|
||||
- `General Linear Models`
|
||||
- `Monte Carlo Methods`
|
||||
- `Numerical Methods`
|
||||
- `Numerical Optimization`
|
||||
- `Portfolio Management`
|
||||
- `Statistical Learning`
|
||||
|
||||
- `M2`
|
||||
- `Data Visualisation`
|
||||
- `Deep Learning`
|
||||
- `Linear Models`
|
||||
- `Machine Learning`
|
||||
- `VBA`
|
||||
- `SQL`
|
||||
|
||||
## 🛠️ Technologies & Tools
|
||||
|
||||
- [Python](https://www.python.org): A high-level, interpreted programming language, widely used for data science, machine learning, and scientific computing.
|
||||
- [R](https://www.r-project.org): A statistical computing environment, perfect for data analysis and visualization.
|
||||
- [Jupyter](https://jupyter.org): Interactive notebooks combining code, results, and rich text for reproducible research.
|
||||
- [Pandas](https://pandas.pydata.org): A data manipulation library providing data structures and operations for manipulating numerical tables and time series.
|
||||
- [NumPy](https://numpy.org): Core package for numerical computing with support for large, multi-dimensional arrays and matrices.
|
||||
- [SciPy](https://www.scipy.org): A library for advanced scientific computations including optimization, integration, and signal processing.
|
||||
- [Scikit-learn](https://scikit-learn.org): A robust library offering simple and efficient tools for machine learning and statistical modeling, including classification, regression, and clustering.
|
||||
- [TensorFlow](https://www.tensorflow.org): A comprehensive open-source framework for building and deploying machine learning and deep learning models.
|
||||
- [Keras](https://keras.io): A high-level neural networks API, running on top of TensorFlow, designed for fast experimentation.
|
||||
- [Matplotlib](https://matplotlib.org): A versatile plotting library for creating high-quality static, animated, and interactive visualizations in Python.
|
||||
- [Plotly](https://plotly.com): An interactive graphing library for creating dynamic visualizations in Python and R.
|
||||
- [Seaborn](https://seaborn.pydata.org): A statistical data visualization library built on top of Matplotlib, providing a high-level interface for drawing attractive and informative graphics.
|
||||
- [RMarkdown](https://rmarkdown.rstudio.com): A dynamic tool for combining code, results, and narrative into high-quality documents and presentations.
|
||||
- [FactoMineR](https://factominer.free.fr/): An R package focused on multivariate exploratory data analysis (e.g., PCA, MCA, CA).
|
||||
- [ggplot2](https://ggplot2.tidyverse.org): A grammar-based graphics package for creating complex and elegant visualizations in R.
|
||||
- [RShiny](https://shiny.rstudio.com): A web application framework for building interactive web apps directly from R.
|
||||
- and my 🧠.
|
||||
57
content/projects/bikes-glm.md
Normal file
57
content/projects/bikes-glm.md
Normal file
@@ -0,0 +1,57 @@
|
||||
---
|
||||
slug: bikes-glm
|
||||
title: Generalized Linear Models for Bikes Prediction
|
||||
type: Academic Project
|
||||
description: Predicting the number of bikes rented in a bike-sharing system using Generalized Linear Models and various statistical techniques.
|
||||
publishedAt: 2025-01-24
|
||||
readingTime: 1
|
||||
status: Completed
|
||||
tags:
|
||||
- R
|
||||
- Statistics
|
||||
- Data Analysis
|
||||
- GLM
|
||||
- Mathematics
|
||||
emoji: 🚲
|
||||
---
|
||||
|
||||
# Generalized Linear Models for Bikes Prediction
|
||||
|
||||
## Overview
|
||||
|
||||
This project was completed as part of the **Generalized Linear Models** course at Paris-Dauphine PSL University. The objective was to develop and compare statistical models to predict the number of bicycle rentals in a bike-sharing system based on various environmental and temporal characteristics.
|
||||
|
||||
## 📊 Project Objectives
|
||||
|
||||
- Determine the best predictive model for bicycle rental counts
|
||||
- Analyze the impact of various features (temperature, humidity, wind speed, seasonality, etc.)
|
||||
- Apply and evaluate different generalized linear modeling techniques
|
||||
- Validate model assumptions and performance metrics
|
||||
|
||||
## 🔍 Methodology
|
||||
|
||||
The study employs rigorous statistical approaches including:
|
||||
|
||||
- **Exploratory Data Analysis (EDA)** - Understanding feature distributions and relationships
|
||||
- **Model Comparison** - Testing multiple GLM families (Poisson, Negative Binomial, Gaussian)
|
||||
- **Feature Selection** - Identifying the most influential variables
|
||||
- **Model Diagnostics** - Validating assumptions and checking residuals
|
||||
- **Cross-validation** - Ensuring robust performance estimates
|
||||
|
||||
## 📁 Key Findings
|
||||
|
||||
The analysis identified critical factors influencing bike-sharing demand:
|
||||
- Seasonal patterns and weather conditions
|
||||
- Temperature and humidity effects
|
||||
- Holiday and working day distinctions
|
||||
- Time-based trends and cyclical patterns
|
||||
|
||||
## 📚 Resources
|
||||
|
||||
- **Code Repository**: [GLM Bikes Code](https://go.arthurdanjou.fr/glm-bikes-code)
|
||||
- **Full Report**: See embedded PDF below
|
||||
|
||||
## 📄 Detailed Report
|
||||
|
||||
<iframe src="/projects/bikes-glm/Report.pdf" width="100%" height="1000px">
|
||||
</iframe>
|
||||
47
content/projects/breast-cancer.md
Normal file
47
content/projects/breast-cancer.md
Normal file
@@ -0,0 +1,47 @@
|
||||
---
|
||||
slug: breast-cancer
|
||||
title: Breast Cancer Detection
|
||||
type: Academic Project
|
||||
description: Prediction of breast cancer presence by comparing several supervised classification models using machine learning techniques.
|
||||
publishedAt: 2025-06-06
|
||||
readingTime: 2
|
||||
status: Completed
|
||||
tags:
|
||||
- Python
|
||||
- Machine Learning
|
||||
- Data Science
|
||||
- Classification
|
||||
- Healthcare
|
||||
emoji: 💉
|
||||
---
|
||||
|
||||
The project was carried out as part of the `Statistical Learning` course at Paris-Dauphine PSL University. Its objective is to identify the most effective model for predicting or explaining the presence of breast cancer based on a set of biological and clinical features.
|
||||
|
||||
This project aims to develop and evaluate several supervised classification models to predict the presence of breast cancer based on biological features extracted from the Breast Cancer Coimbra dataset, provided by the UCI Machine Learning Repository.
|
||||
|
||||
The dataset contains 116 observations divided into two classes:
|
||||
|
||||
- 1: healthy individuals (controls)
|
||||
|
||||
- 2: patients diagnosed with breast cancer
|
||||
|
||||
There are 9 explanatory variables, including clinical measurements such as age, insulin levels, leptin, insulin resistance, among others.
|
||||
|
||||
The project follows a comparative approach between several algorithms:
|
||||
|
||||
- Logistic Regression
|
||||
|
||||
- k-Nearest Neighbors (k-NN)
|
||||
|
||||
- Naive Bayes
|
||||
|
||||
- Artificial Neural Network (MLP with a 16-8-1 architecture)
|
||||
|
||||
Model evaluation is primarily based on the F1-score, which is more suitable in a medical context where identifying positive cases is crucial. Particular attention was paid to stratified cross-validation and to handling class imbalance, notably through the use of class weights and regularization techniques (L2, early stopping).
|
||||
|
||||
This project illustrates a concrete application of data science techniques to a public health issue, while implementing a rigorous methodology for supervised modeling.
|
||||
|
||||
You can find the code here: [Breast Cancer Detection](https://go.arthurdanjou.fr/breast-cancer-detection-code)
|
||||
|
||||
<iframe src="/projects/breast-cancer/report.pdf" width="100%" height="1000px">
|
||||
</iframe>
|
||||
157
content/projects/dropout-reduces-underfitting.md
Normal file
157
content/projects/dropout-reduces-underfitting.md
Normal file
@@ -0,0 +1,157 @@
|
||||
---
|
||||
slug: dropout-reduces-underfitting
|
||||
title: Dropout Reduces Underfitting
|
||||
type: Research Project
|
||||
description: TensorFlow/Keras implementation and reproduction of "Dropout Reduces Underfitting" (Liu et al., 2023). A comparative study of Early and Late Dropout strategies to optimize model convergence.
|
||||
publishedAt: 2024-12-10
|
||||
readingTime: 4
|
||||
status: Active
|
||||
tags:
|
||||
- Python
|
||||
- TensorFlow
|
||||
- Machine Learning
|
||||
- Deep Learning
|
||||
- Research
|
||||
emoji: 🔬
|
||||
---
|
||||
|
||||
📉 [Dropout Reduces Underfitting](https://github.com/arthurdanjou/dropoutreducesunderfitting): Reproduction & Analysis
|
||||
|
||||

|
||||

|
||||

|
||||
|
||||
> **Study and reproduction of the paper:** Liu, Z., et al. (2023). *Dropout Reduces Underfitting*. arXiv:2303.01500.
|
||||
|
||||
The paper is available at: [https://arxiv.org/abs/2303.01500](https://arxiv.org/abs/2303.01500)
|
||||
|
||||
This repository contains a robust and modular implementation in **TensorFlow/Keras** of **Early Dropout** and **Late Dropout** strategies. The goal is to verify the hypothesis that dropout, traditionally used to reduce overfitting, can also combat underfitting when applied solely during the initial training phase.
|
||||
|
||||
## 🎯 Scientific Objectives
|
||||
|
||||
The study aims to validate the three operating regimes of Dropout described in the paper:
|
||||
|
||||
1. **Early Dropout** (Targeting Underfitting): Active only during the initial phase to reduce gradient variance and align their direction, allowing for better final optimization.
|
||||
2. **Late Dropout** (Targeting Overfitting): Disabled at the start to allow rapid learning, then activated to regularize final convergence.
|
||||
3. **Standard Dropout**: Constant rate throughout training (Baseline).
|
||||
4. **No Dropout**: Control experiment without dropout.
|
||||
|
||||
## 🛠️ Technical Architecture
|
||||
|
||||
Unlike naive Keras callback implementations, this project uses a **dynamic approach via the TensorFlow graph** to ensure the dropout rate is properly updated on the GPU without model recompilation.
|
||||
|
||||
### Key Components
|
||||
|
||||
* **`DynamicDropout`**: A custom layer inheriting from `keras.layers.Layer` that reads its rate from a shared `tf.Variable`.
|
||||
* **`DropoutScheduler`**: A Keras `Callback` that drives the rate variable based on the current epoch and the chosen strategy (`early`, `late`, `standard`).
|
||||
* **`ExperimentPipeline`**: An orchestrator class that handles data loading (MNIST, CIFAR-10, Fashion MNIST), model creation (Dense or CNN), and execution of comparative benchmarks.
|
||||
|
||||
## File Structure
|
||||
|
||||
```
|
||||
.
|
||||
├── README.md # This documentation file
|
||||
├── Dropout reduces underfitting.pdf # Original research paper
|
||||
├── pipeline.py # Main experiment pipeline
|
||||
├── pipeline.ipynb # Jupyter notebook for experiments
|
||||
├── pipeline_mnist.ipynb # Jupyter notebook for MNIST experiments
|
||||
├── pipeline_cifar10.ipynb # Jupyter notebook for CIFAR-10 experiments
|
||||
├── pipeline_cifar100.ipynb # Jupyter notebook for CIFAR-100 experiments
|
||||
├── pipeline_fashion_mnist.ipynb # Jupyter notebook for Fashion MNIST experiments
|
||||
├── requirements.txt # Python dependencies
|
||||
├── .python-version # Python version specification
|
||||
└── uv.lock # Dependency lock file
|
||||
```
|
||||
|
||||
## 🚀 Installation
|
||||
|
||||
```bash
|
||||
# Clone the repository
|
||||
git clone https://github.com/arthurdanjou/dropoutreducesunderfitting.git
|
||||
cd dropoutreducesunderfitting
|
||||
```
|
||||
|
||||
## Install dependencies
|
||||
```bash
|
||||
pip install tensorflow numpy matplotlib seaborn scikit-learn
|
||||
```
|
||||
|
||||
## 📊 Usage
|
||||
|
||||
The main notebook pipeline.ipynb contains all necessary code. Here is how to run a typical experiment via the pipeline API.
|
||||
1. Initialization
|
||||
|
||||
Choose your dataset (cifar10, fashion_mnist, mnist) and architecture (cnn, dense).
|
||||
```python
|
||||
from pipeline import ExperimentPipeline
|
||||
|
||||
# Fashion MNIST is recommended to observe underfitting/overfitting nuances
|
||||
exp = ExperimentPipeline(dataset_name="fashion_mnist", model_type="cnn")
|
||||
```
|
||||
|
||||
2. Learning Curves Comparison
|
||||
|
||||
Compare training dynamics (Loss & Accuracy) of the three strategies.
|
||||
|
||||
```python
|
||||
exp.compare_learning_curves(
|
||||
modes=["standard", "early", "late"],
|
||||
switch_epoch=10, # The epoch where dropout state changes
|
||||
rate=0.4, # Dropout rate
|
||||
epochs=30
|
||||
)
|
||||
```
|
||||
|
||||
3. Ablation Studies
|
||||
|
||||
Study the impact of the "Early" phase duration or Dropout intensity.
|
||||
|
||||
```python
|
||||
# Impact of the switch epoch on final performance
|
||||
exp.compare_switch_epochs(
|
||||
switch_epochs=[5, 10, 15, 20],
|
||||
modes=["early"],
|
||||
rate=0.4,
|
||||
epochs=30
|
||||
)
|
||||
|
||||
# Impact of the dropout rate
|
||||
exp.compare_drop_rates(
|
||||
rates=[0.2, 0.4, 0.6],
|
||||
modes=["standard", "early"],
|
||||
switch_epoch=10,
|
||||
epochs=25
|
||||
)
|
||||
```
|
||||
|
||||
4. Data Regimes (Data Scarcity)
|
||||
|
||||
Verify the paper's hypothesis that Early Dropout shines on large datasets (or limited models) while Standard Dropout protects small datasets.
|
||||
|
||||
```python
|
||||
# Training on 10%, 50% and 100% of the dataset
|
||||
exp.run_dataset_size_comparison(
|
||||
fractions=[0.1, 0.5, 1.0],
|
||||
modes=["standard", "early"],
|
||||
rate=0.3,
|
||||
switch_epoch=10
|
||||
)
|
||||
```
|
||||
|
||||
## 📈 Expected Results
|
||||
|
||||
According to the paper, you should observe:
|
||||
|
||||
- Early Dropout: Higher initial Loss, followed by a sharp drop after the switch_epoch, often reaching a lower minimum than Standard Dropout (reduction of underfitting).
|
||||
- Late Dropout: Rapid rise in accuracy at the start (potential overfitting), then stabilized by the activation of dropout.
|
||||
|
||||
## 📝 Authors
|
||||
|
||||
- [Arthur Danjou](https://github.com/ArthurDanjou)
|
||||
- [Alexis Mathieu](https://github.com/Alex6535)
|
||||
- [Axelle Meric](https://github.com/AxelleMeric)
|
||||
- [Philippine Quellec](https://github.com/Philippine35890)
|
||||
- [Moritz Von Siemens](https://github.com/MoritzSiem)
|
||||
M.Sc. Statistical and Financial Engineering (ISF) - Data Science Track at Université Paris-Dauphine PSL
|
||||
|
||||
Based on the work of Liu, Z., et al. (2023). Dropout Reduces Underfitting.
|
||||
54
content/projects/loan-ml.md
Normal file
54
content/projects/loan-ml.md
Normal file
@@ -0,0 +1,54 @@
|
||||
---
|
||||
slug: loan-ml
|
||||
title: Machine Learning for Loan Prediction
|
||||
type: Academic Project
|
||||
description: Predicting loan approval and default risk using machine learning classification techniques.
|
||||
publishedAt: 2025-01-24
|
||||
readingTime: 2
|
||||
status: Completed
|
||||
tags:
|
||||
- Python
|
||||
- Machine Learning
|
||||
- Classification
|
||||
- Data Science
|
||||
- Finance
|
||||
emoji: 💰
|
||||
---
|
||||
|
||||
# Machine Learning for Loan Prediction
|
||||
|
||||
## Overview
|
||||
|
||||
This project focuses on building machine learning models to predict loan approval outcomes and assess default risk. The objective is to develop robust classification models that can effectively identify creditworthy applicants.
|
||||
|
||||
## 📊 Project Objectives
|
||||
|
||||
- Build and compare multiple classification models for loan prediction
|
||||
- Identify key factors influencing loan approval decisions
|
||||
- Evaluate model performance using appropriate metrics
|
||||
- Optimize model parameters for better predictive accuracy
|
||||
|
||||
## 🔍 Methodology
|
||||
|
||||
The study employs various machine learning approaches:
|
||||
|
||||
- **Exploratory Data Analysis (EDA)** - Understanding applicant characteristics and patterns
|
||||
- **Feature Engineering** - Creating meaningful features from raw data
|
||||
- **Model Comparison** - Testing multiple algorithms (Logistic Regression, Random Forest, Gradient Boosting, etc.)
|
||||
- **Hyperparameter Tuning** - Optimizing model performance
|
||||
- **Cross-validation** - Ensuring robust generalization
|
||||
|
||||
## 📁 Key Findings
|
||||
|
||||
[To be completed with your findings]
|
||||
|
||||
## 📚 Resources
|
||||
|
||||
- **Code Repository**: [Add link to your code]
|
||||
- **Dataset**: [Add dataset information]
|
||||
- **Full Report**: See embedded PDF below
|
||||
|
||||
## 📄 Detailed Report
|
||||
|
||||
<iframe src="/projects/loan-ml/Report.pdf" width="100%" height="1000px">
|
||||
</iframe>
|
||||
31
content/projects/monte-carlo-project.md
Normal file
31
content/projects/monte-carlo-project.md
Normal file
@@ -0,0 +1,31 @@
|
||||
---
|
||||
slug: monte-carlo-project
|
||||
title: Monte Carlo Methods Project
|
||||
type: Academic Project
|
||||
description: An implementation of different Monte Carlo methods and algorithms in R, including inverse CDF simulation, accept-reject methods, and stratification techniques.
|
||||
publishedAt: 2024-11-24
|
||||
readingTime: 3
|
||||
status: Completed
|
||||
tags:
|
||||
- R
|
||||
- Mathematics
|
||||
- Statistics
|
||||
- Monte Carlo
|
||||
- Numerical Methods
|
||||
emoji: 💻
|
||||
---
|
||||
|
||||
This is the report for the Monte Carlo Methods Project. The project was done as part of the course `Monte Carlo Methods` at the Paris-Dauphine University. The goal was to implement different methods and algorithms using Monte Carlo methods in R.
|
||||
|
||||
Methods and algorithms implemented:
|
||||
- Plotting graphs of functions
|
||||
- Inverse c.d.f. Random Variation simulation
|
||||
- Accept-Reject Random Variation simulation
|
||||
- Random Variable simulation with stratification
|
||||
- Cumulative density function
|
||||
- Empirical Quantile Function
|
||||
|
||||
You can find the code here: [Monte Carlo Project Code](https://go.arthurdanjou.fr/monte-carlo-code)
|
||||
|
||||
<iframe src="/projects/monte-carlo-project/Report.pdf" width="100%" height="1000px">
|
||||
</iframe>
|
||||
23
content/projects/schelling-segregation-model.md
Normal file
23
content/projects/schelling-segregation-model.md
Normal file
@@ -0,0 +1,23 @@
|
||||
---
|
||||
slug: schelling-segregation-model
|
||||
title: Schelling Segregation Model
|
||||
type: Academic Project
|
||||
description: A Python implementation of the Schelling Segregation Model using statistics and data visualization to analyze spatial segregation patterns.
|
||||
publishedAt: 2024-05-03
|
||||
readingTime: 4
|
||||
status: Completed
|
||||
tags:
|
||||
- Python
|
||||
- Data Visualization
|
||||
- Statistics
|
||||
- Modeling
|
||||
- Mathematics
|
||||
emoji: 📊
|
||||
---
|
||||
|
||||
This is the French version of the report for the Schelling Segregation Model project. The project was done as part of the course `Projet Numérique` at the Paris-Saclay University. The goal was to implement the Schelling Segregation Model in Python and analyze the results using statistics and data visualization.
|
||||
|
||||
You can find the code here: [Schelling Segregation Model Code](https://go.arthurdanjou.fr/schelling-code)
|
||||
|
||||
<iframe src="/projects/schelling/Projet.pdf" width="100%" height="1000px">
|
||||
</iframe>
|
||||
31
content/projects/sevetys.md
Normal file
31
content/projects/sevetys.md
Normal file
@@ -0,0 +1,31 @@
|
||||
---
|
||||
slug: sevetys
|
||||
title: Data Engineer Internship at Sevetys
|
||||
type: Internship Project
|
||||
description: Summary of my internship as a Data Engineer at Sevetys, focusing on data quality, cleaning, standardization, and comprehensive data quality metrics.
|
||||
publishedAt: 2025-07-31
|
||||
readingTime: 2
|
||||
status: Completed
|
||||
tags:
|
||||
- Python
|
||||
- PySpark
|
||||
- Data Engineering
|
||||
- Azure
|
||||
- Big Data
|
||||
emoji: 🐶
|
||||
---
|
||||
|
||||
[Sevetys](https://sevetys.fr) is a leading French network of over 200 veterinary clinics, employing more than 1,300 professionals. Founded in 2017, the group provides comprehensive veterinary care for companion animals, exotic pets, and livestock, with services ranging from preventive medicine and surgery to cardiology, dermatology, and 24/7 emergency care.
|
||||
|
||||
Committed to digital innovation, Sevetys leverages centralized data systems to optimize clinic operations, improve patient data management, and enhance the overall client experience. This combination of medical excellence and operational efficiency supports veterinarians in delivering the highest quality care nationwide.
|
||||
|
||||
During my two-month internship as a Data Engineer, I focused primarily on cleaning and standardizing customer and patient data — a critical task, as this data is extensively used by clinics, Marketing, and Performance teams. Ensuring data quality was therefore essential to the company's operations.
|
||||
|
||||
Additionally, I took charge of revising and enhancing an existing data quality report designed to evaluate the effectiveness of my cleaning processes. The report encompassed 47 detailed metrics assessing data completeness and consistency, providing valuable insights that helped maintain high standards across the organization.
|
||||
|
||||
## ⚙️ Stack
|
||||
|
||||
- [Microsoft Azure Cloud](https://azure.microsoft.com/)
|
||||
- [PySpark](https://spark.apache.org/docs/latest/api/python/)
|
||||
- [Python](https://www.python.org/)
|
||||
- [GitLab]()
|
||||
110
content/skills.json
Normal file
110
content/skills.json
Normal file
@@ -0,0 +1,110 @@
|
||||
{
|
||||
"description": "Master's student in Applied Mathematics (M280 - Paris Dauphine) specializing in Data Science and AI. My profile sits at the intersection of theoretical research and software engineering. I leverage my strong background in probability, statistics, and optimization to design robust Deep Learning architectures, while using my engineering skills (MLOps, Infrastructure) to deploy them efficiently. Currently looking for a research-oriented final year internship (April 2026) leading to a PhD.",
|
||||
"skills": [
|
||||
{
|
||||
"id": "scientific-computing",
|
||||
"name": "Scientific Computing & AI",
|
||||
"description": "Core expertise in mathematics, statistics, and machine learning. Building and training neural networks, statistical models, and data science solutions.",
|
||||
"items": [
|
||||
{
|
||||
"name": "Python",
|
||||
"icon": "i-logos-python"
|
||||
},
|
||||
{
|
||||
"name": "PyTorch",
|
||||
"icon": "i-logos-pytorch-icon"
|
||||
},
|
||||
{
|
||||
"name": "R Lang",
|
||||
"icon": "i-logos-r-lang"
|
||||
},
|
||||
{
|
||||
"name": "LaTeX",
|
||||
"icon": "i-file-icons-latex"
|
||||
},
|
||||
{
|
||||
"name": "Tensorflow",
|
||||
"icon": "i-logos-tensorflow"
|
||||
},
|
||||
{
|
||||
"name": "Scikit-Learn",
|
||||
"icon": "i-devicon-scikitlearn"
|
||||
},
|
||||
{
|
||||
"name": "Pandas & Numpy",
|
||||
"icon": "i-devicon-pandas"
|
||||
},
|
||||
{
|
||||
"name": "MatPlotLib",
|
||||
"icon": "i-devicon-matplotlib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "data-engineering-mlops",
|
||||
"name": "Data Engineering & MLOps",
|
||||
"description": "Infrastructure, data pipelines, and production deployment. Managing databases, containerization, and scalable systems for ML models.",
|
||||
"items": [
|
||||
{
|
||||
"name": "PostgreSQL",
|
||||
"icon": "i-logos-postgresql"
|
||||
},
|
||||
{
|
||||
"name": "MySQL",
|
||||
"icon": "i-logos-mysql-icon"
|
||||
},
|
||||
{
|
||||
"name": "Docker",
|
||||
"icon": "i-logos-docker-icon"
|
||||
},
|
||||
{
|
||||
"name": "Linux",
|
||||
"icon": "i-logos-linux-tux"
|
||||
},
|
||||
{
|
||||
"name": "Git",
|
||||
"icon": "i-logos-git-icon"
|
||||
},
|
||||
{
|
||||
"name": "Proxmox",
|
||||
"icon": "i-devicon-proxmox-wordmark"
|
||||
},
|
||||
{
|
||||
"name": "Redis",
|
||||
"icon": "i-logos-redis"
|
||||
},
|
||||
{
|
||||
"name": "Apache Spark (PySpark)",
|
||||
"icon": "i-logos-apache-spark"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "software-development",
|
||||
"name": "Fullstack Development",
|
||||
"description": "Web and backend development with modern frameworks. Building responsive UIs and scalable server-side applications.",
|
||||
"items": [
|
||||
{
|
||||
"name": "TypeScript",
|
||||
"icon": "i-logos-typescript-icon"
|
||||
},
|
||||
{
|
||||
"name": "Vue.js & Nuxt",
|
||||
"icon": "i-logos-nuxt-icon"
|
||||
},
|
||||
{
|
||||
"name": "Java",
|
||||
"icon": "i-logos-java"
|
||||
},
|
||||
{
|
||||
"name": "TailwindCSS",
|
||||
"icon": "i-logos-tailwindcss-icon"
|
||||
},
|
||||
{
|
||||
"name": "AdonisJs",
|
||||
"icon": "i-logos-adonisjs-icon"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
79
content/uses.md
Normal file
79
content/uses.md
Normal file
@@ -0,0 +1,79 @@
|
||||
---
|
||||
title: What I Use
|
||||
description: My favorite equipment, tools and software for productivity and development
|
||||
---
|
||||
|
||||
# What I Use
|
||||
|
||||
This page documents all the tools, equipment and services I use daily for my work as a developer and my personal projects.
|
||||
|
||||
## 🖥️ Hardware
|
||||
|
||||
### Computers
|
||||
|
||||
- **Apple MacBook Pro 13'** - My main workstation with Apple M1 Chip and 16GB RAM, running macOS Sonoma
|
||||
- **Custom Built Gaming PC** - A customized computer for gaming with Intel Core i5-10400F, 16GB DDR4, RTX 2060 and Windows 11
|
||||
|
||||
### Peripherals and Accessories
|
||||
|
||||
- **Apple AirPods Pro** - Probably my most used accessory after my phone and laptop. Excellent sound quality and very convenient
|
||||
- **Apple iPad Air** - For reading books, watching movies, browsing the web, taking notes and writing equations during classes
|
||||
- **Apple iPhone 14 Pro** - The best phone on the market in my opinion
|
||||
- **SteelSeries Apex 9 TKL** - A compact and powerful TKL keyboard perfect for gamers and developers
|
||||
- **Logitech G203 LightSync Black** - A classic gaming mouse with simple and clean design
|
||||
|
||||
### Apple Suite
|
||||
|
||||
- Using Mail, Calendar, Notes, Music and Reminders for my daily organization
|
||||
|
||||
---
|
||||
|
||||
## 💻 Development
|
||||
|
||||
### IDEs
|
||||
|
||||
- **Visual Studio Code** - My main development environment. Flexible, performant and lightweight. Supports Python, JavaScript, TypeScript, SQL and much more. I especially appreciate the extensions and AI integrations
|
||||
- **JetBrains Suite** (IntelliJ IDEA Ultimate, PyCharm Professional, WebStorm, DataGrip) - Which I've been using for 7 years. The best IDEs for Java, Python, JavaScript, SQL and other languages
|
||||
|
||||
### Theme and Fonts
|
||||
|
||||
- **Theme**: Catppuccin Macchiato - A community-driven pastel theme that strikes the balance between low and high contrast
|
||||
- **Font**: JetBrains Mono
|
||||
|
||||
---
|
||||
|
||||
## 🛠️ Software and Tools
|
||||
|
||||
### Communication and Collaboration
|
||||
|
||||
- **Discord** - For chatting with my friends, clients and community members
|
||||
- **Notion & Notion Calendar** - My all-in-one tool for note-taking, kanban boards, wikis, and drafts. Notion Calendar allows me to sync my databases with my calendar
|
||||
|
||||
### Navigation and System Tools
|
||||
|
||||
- **Firefox Browser** - My main browser for browsing, developer tools and the extension marketplace
|
||||
- **Raycast** - An extensible launcher replacing Apple Spotlight. Allows me to complete tasks, calculate, share common links, and much more thanks to extensions
|
||||
- **Warp** - A modern, Rust-based terminal reimagined with AI and collaborative tools for better productivity
|
||||
|
||||
---
|
||||
|
||||
## 🏠 Personal HomeLab
|
||||
|
||||
### Hardware Infrastructure
|
||||
|
||||
- **Beelink EQR6 AMD Ryzen** - The main server in my homelab running Proxmox to host self-hosted services, run Docker containers and test open-source tools
|
||||
- **5-Port TP-Link Switch** - To connect my network devices to the main server and ensure fast, stable local communication
|
||||
- **UGREEN NASync DXP4800 Plus** - A 4-bay NAS to store and manage my data centrally. Currently equipped with 2 8TB hard drives, with the possibility to add 2 more in the future
|
||||
|
||||
### Self-Hosted Services
|
||||
|
||||
I maintain several services:
|
||||
- **Monitoring & Infrastructure**: Uptime Kuma, Beszel, Traefik, Portainer
|
||||
- **Security & Privacy**: Cloudflare, AdGuard Home, Vaultwarden, Tailscale
|
||||
- **Storage & Media**: Minio, Immich
|
||||
- **Smart Home**: Home Assistant
|
||||
- **Other Utilities**: MySpeed, Palmr, Cap.so
|
||||
|
||||
---
|
||||
|
||||
*This list is constantly updated as I experiment with new tools and equipment.*
|
||||
Reference in New Issue
Block a user