This repository serves as the submission for the Machine Learning practical works within the Master 1 I2L program. We explore various aspects of machine learning using Python, including classification, regression, neural networks, and more.
- 📂 Projects
- 🛠️ Technical Stack
- 💻 Work Environment
- 📦 Dependencies
- 🏁 Getting Started
- ✨ Additional Sections
- 👨🏫 Authors
Here are the completed practical works (up to 3 for now) with links to their respective tags:
- TP0: Python for ML introduction - Introduction to Machine Learning.
- TP1: Linear and polynomial regression - Exploring polynomial and linear regressions.
- TP2: KNN - Classification and regressions using KNN.
- TP3: K-means - Use and understand the K-means algorithms.
- TP4: Upper Confidence Bound Create and use UCB agents.
- TP5: Q-learning Creation of a Q-learning algorithm for a game.
- TP6: Gradient Descent Creation of MLP algorithms and gradient descents.
- TP7: Deep Neural Network Creation of model with deep neural networks.
- TP8: Convolutional Neural Network Creation of convolutional neural networks.
Here are the directed works:
- TD1: Decision Tree - Classification and regression using Decision Trees.
Projects:
- Supervised Learning - Project concerning a classification problem.
- Advanced ML problem - Multi-class classification problem: recognising simpsons characters from their faces.
The repository primarily utilizes Python. Here's a list of the key technologies used with links to their documentation:
- 🐍 Python - The primary programming language.
- 📔 Jupyter Notebook - Interactive computing and report generation.
- 💻 Visual Studio Code - An integrated development environment.
With these tools we also use a lot of libraries to properly work with machine learning. Here are some libraries used in this repository:
- 🧠 scikit-learn - For machine learning and data analysis.
- 🔢 NumPy - For numerical computations.
- 🐼 Pandas - For data manipulation and analysis.
- 📊 Matplotlib - For data visualization.
- 🚀 TensorFlow - An open-source machine learning framework.
We use both Jupyter Notebook and Visual Studio Code for coding, analysis, and report generation. Our environment includes:
- 📓 Jupyter Notebook
- 🐍 Python 3
- 🌐 Python Virtual Environment
- 📦 List of Dependencies - See Pip for package management.
The list of dependencies can be found in the requirements.txt file in the repository. Please refer to Pip for installing these dependencies.
To get started with this repository, follow these steps:
-
Clone the repository to your local machine:
git clone https://gitlab.dpt-info.univ-littoral.fr/tremblay.jeremy/m1-ia-jtremblay.git
-
Create a Python virtual environment (Python 3 is assumed to be installed):
python3 -m venv myenv
-
Activate the virtual environment:
- On Windows (using Command Prompt):
myenv\Scripts\activate
- On macOS and Linux:
source myenv/bin/activate
-
Install pip (if not already installed):
python -m ensurepip --default-pip
-
Install the project dependencies from the
requirements.txt
file located at the root of the repository:pip install -r requirements.txt
-
You can now navigate to the folder corresponding to the desired TP (e.g., TP0, TP1, TP2, etc.) within the repository and open the Jupyter Notebook files using your preferred code editor like Visual Studio Code or Jupyter Notebook.
This will set up your local environment with the necessary dependencies and tools to run the notebooks for different TPs.
More will come here soon. 🚀
👨🏫 Jérémy TREMBLAY
- Github: @JeremyTremblay2
- LinkedIn: @Jérémy Tremblay
Repository created as part of the Machine Learning course of the I2L Master and intended for evaluation by M. Jérôme Buisine. The contents of the practical work come from his courses, more information.