Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View MohamedNassih's full-sized avatar

Block or report MohamedNassih

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MohamedNassih/README.md

💫 About Me:

📈 Passionate about Mathematics since High School: I developed a strong interest in models and quantitative analysis, which defined my path toward data science.
🏆 Baccalaureate in Mathematical Sciences: My solid foundation in mathematics enabled me to pursue advanced studies in engineering.
📚 Preparatory Classes for Engineering Schools (MPSI, MP): A rigorous education at Centre Ibn Abdoun, where I tackled complex mathematical challenges and honed my problem-solving skills.
🎖️ National Competitive Exam (CNC) and TIPE: An enriching experience with a TIPE focused on "Detecting People without Masks," highlighting my skills in applied research.
🏫 Data Science Studies at INSEA: A comprehensive program covering data analysis, statistics, programming, and artificial intelligence, preparing me for real-world challenges in data science.
💼 Professional Internships in Data Science:
YaneCode Digital: Creation of Darija datasets for translation with advanced NLP techniques.
3D Smart Factory: Development of a research assistant using an LLM model and RAG paradigm for scientific document analysis.
IWRI–UM6P (Final-Year Project – PFE): Built the “Plateforme-Analyse-Fréquentielle-Hydrologique” — a Streamlit app for hydrological extremes (EVT: GEV/GPD), model selection (AIC/BIC) and uncertainty analysis on real time-series.
🥇 Thesis Defense: Awarded 20/20 (highest distinction). Passionate about R&D and turning data into reliable, measurable products.
🚀 Technical Skills: NLP, Machine Learning, Deep Learning, Data Analysis, Databases, Operational Research.

🌐 Socials:

LinkedIn Portfolio

💻 Tech Stack:

Python Anaconda Pandas NumPy scikit-learn Keras PyTorch TensorFlow R Postgres Matplotlib Plotly MySQL Git Docker C++ Java Power Bi OpenCV Scipy Trello Confluence Streamlit

📊 GitHub Stats:



✍️ Random Dev Quote

🔝 Top Contributed Repo


Pinned Loading

  1. Personalized-Analysis-of-Scientific-Articles-using-LLMs-and-a-RAG-paradigm- Personalized-Analysis-of-Scientific-Articles-using-LLMs-and-a-RAG-paradigm- Public

    AI scientific research assistant. Segments, vectorizes (DistilBERT) and stores (ChromaDB) articles for semantic search. Generates personalized answers (Ollama) via a Streamlit interface.

    Jupyter Notebook 3

  2. Semi-supervised-spectral-unmixing-for-the-DLR-HySpex-dataset Semi-supervised-spectral-unmixing-for-the-DLR-HySpex-dataset Public

    Plate-forme Python modulaire pour l’analyse et le démélange spectral semi-supervisé d’images hyperspectrales HySpex (jeu de données DLR HySU). Elle combine : un pipeline NMF pour extraire endmember…

    Jupyter Notebook 1

  3. Stress-Hydrique-Tensift Stress-Hydrique-Tensift Public

    Agricultural water stress detection using satellite remote sensing (Sentinel-2, MODIS) and in-situ data for Tensift Basin, Morocco

    HTML 1

  4. Decodage-de-texte-partir-de-EEG-non-invasif Decodage-de-texte-partir-de-EEG-non-invasif Public

    NeuroText est un projet pour décoder des états/mots à partir d’EEG non invasif. Il fournit un pipeline complet : intégrité des données → prétraitements (HP/LP, Kalman) → caractéristiques spectro-te…

    Python

  5. Evaluation-Pertinence-Juridique-ML Evaluation-Pertinence-Juridique-ML Public

    Évaluation de la pertinence (question ↔ article juridique) en français. Pipeline complet (prépa → modèles → soumission) avec CamemBERT en bi-encodeur calibré (MSE/Spearman), + variantes cross-encoder.

    Python

  6. NLP-for-Darija-Enrichissement-de-traduction_darija.json NLP-for-Darija-Enrichissement-de-traduction_darija.json Public

    Pipeline Python pour enrichir un dataset Arabe (MSA) → Darija (MA) depuis livres PDF & transcriptions YouTube ; normalisation, segmentation par tokens, génération (OpenAI ou règles) et export JSON.…

    Python