📊 Perform Processing in a Big Data Environment on the Cloud

This repository contains deliverables created as part of Project 9 of the Data Scientist course offered by OpenClassrooms & CentraleSupélec.

⚠️ Important: This repository reflects personal work carried out by the author as part of a training course. It is in no way affiliated with, endorsed, or officially published by OpenClassrooms or CentraleSupélec.

📂 Content

Martineau_Alexandre_1_notebook_032025.ipynb

→ Jupyter notebook implementing a Big Data processing chain for fruit image classification with PySpark and AWS EMR.

• Image import and preprocessing
• Feature extraction with MobileNetV2
• Dimension reduction using PCA
• Saving results (Parquet, CSV)

Martineau_Alexandre_3_presentation_032025.pptx

→ Exhibitor presentation material:

• Context (Fruits! startup and biodiversity preservation)
• Principles of Big Data and Cloud Computing
• Technical architecture (EC2, EMR, S3, IAM)
• Steps for setting up a Spark cluster on AWS
• Results and conclusions (scalability, costs, technology dependencies)

⚖️ License & Terms of Use

• All rights reserved © 2025 Alexandre Martineau.
• No reuse, reproduction, distribution, or modification is permitted without prior agreement.
• Any commercial or profit-generating use requires the express permission of the author and financial compensation.

👤 Author

Alexandre Christophe Dominique Martineau

• GitHub
• LinkedIn