openclassroom-ai/oc-p07-sentiment-api
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
P7 Air Paradis sentiment analysis (OpenClassrooms)
86 commits 1 branch 0 tags 77 MiB
Jupyter Notebook 99.2%
Python 0.7%
Find a file
Grégoire Mureau db1305f5c2 Recâbler les URLs MLflow/MinIO vers gregoiremureau.com dans les exemples. 
Les secrets restent dans Vaultwarden ; la prod k3s utilise déjà les SVC in-cluster.
2026-09-09 15:30:19 +02:00
.github/workflows Préparer le repo P7 autonome : CI preprocessing, fetch-data, URLs prod. 2026-09-09 12:58:39 +02:00
deployment start.sh fixed (dos2unix) 2025-11-11 15:35:20 +01:00
docs Recâbler les URLs MLflow/MinIO vers gregoiremureau.com dans les exemples. 2026-09-09 15:30:19 +02:00
notebooks minor changes 2025-11-11 08:39:23 +01:00
presentation minor changes 2025-11-11 08:39:23 +01:00
.env.example Recâbler les URLs MLflow/MinIO vers gregoiremureau.com dans les exemples. 2026-09-09 15:30:19 +02:00
.gitignore Recâbler les URLs MLflow/MinIO vers gregoiremureau.com dans les exemples. 2026-09-09 15:30:19 +02:00
fetch-data.sh Préparer le repo P7 autonome : CI preprocessing, fetch-data, URLs prod. 2026-09-09 12:58:39 +02:00
functions.py minor changes 2025-11-11 08:39:23 +01:00
README.fr.md Aligner le README français sur Forgejo et l'URL de prod actuelle. 2026-09-09 12:58:44 +02:00
README.md Préparer le repo P7 autonome : CI preprocessing, fetch-data, URLs prod. 2026-09-09 12:58:39 +02:00

README.md

Air Paradis Project – Sentiment Analysis

📘 This project is also available in French 🇫🇷

This repository contains the notebooks and source code for the sentiment analysis project on tweets, conducted as part of the OpenClassrooms "Air Paradis" program.

Source of truth : Forgejo (self-hosted). GitHub, when mirrored, is the public shop window.

git clone https://git.gregoiremureau.com/grgmro/oc-p07-sentiment-api.git
# HTTPS (Cloudflare, fine for clone) :
git clone https://git.gregoiremureau.com/grgmro/oc-p07-sentiment-api.git

Business Context

The objective is to predict whether a tweet (or short written expression) is perceived as positive or negative, in the context of an airline company.
The project is based on the public Sentiment140 dataset.

Project Description

The project aims to develop a complete sentiment analysis system, including:

  • Exploratory analysis of textual data,
  • Rigorous comparison of 10+ classification models (classical ML, LSTM + word embeddings, DistilBERT),
  • Deployment of a FastAPI REST API exposing the best advanced model (LSTM + Word2Vec),
  • Implementation of a complete MLOps pipeline: MLFlow, CI/CD (GitHub Actions), monitoring,
  • Local hosting on NAS server to ensure data sovereignty.

📖 For detailed information on experiments conducted and results obtained, see docs/blog.md.

Repository Structure

  • notebooks/: exploratory analysis and modeling notebooks,
  • deployment/: FastAPI API code, unit tests, Dockerfile and deployment configuration,
  • docs/: detailed documentation (blog.md), diagrams, screenshots,
  • presentation/: project presentation slides (PDF),
  • .github/workflows/: CI (Forgejo Actions on the homelab runner; same YAML on GitHub),
  • fetch-data.sh: where to get Sentiment140 (dataset not in git).

Model Training

Training phases were primarily conducted on Google Colab to leverage GPU resources required for deep learning models.

Usage

Notebooks detail the analysis and training steps.
The API is available in the deployment/api folder with Streamlit testing interface.

To test the production API: https://api.gregoiremureau.com/ml/sentiment/

Notes

  • The requirements.txt files in notebooks/ come from Google Colab environments and may contain dependencies not optimized for local use.
  • The .env file, excluded from the repository, contains necessary environment variables (MLFlow, MinIO, alerting configuration).
  • Training data: run ./fetch-data.sh (Sentiment140 is not stored in git).

Project completed as part of OpenClassrooms "Data Scientist – Project 7" program