https://github.com/mjahmadee/mlp_regression

Multi-Layer Perceptron, MLP, Regression
https://github.com/mjahmadee/mlp_regression

mlp mlp-regressor multi-layer-perceptron regression

Last synced: 8 days ago
JSON representation

Multi-Layer Perceptron, MLP, Regression

• Host: GitHub
• URL: https://github.com/mjahmadee/mlp_regression
• Owner: MJAHMADEE
• License: mit
• Created: 2023-07-10T09:19:51.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-03-16T13:03:40.000Z (8 months ago)
• Last Synced: 2024-03-16T15:44:00.129Z (8 months ago)
• Topics: mlp, mlp-regressor, multi-layer-perceptron, regression
• Language: Jupyter Notebook
• Homepage:
• Size: 2.95 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MLP Regression for Car Price Prediction 🚗💰

![Python](https://img.shields.io/badge/Python-3.x-blue.svg)

![PyTorch](https://img.shields.io/badge/PyTorch-1.x-orange.svg)

![Machine Learning](https://img.shields.io/badge/Machine%20Learning-Regression-green.svg)

This repository contains a Multilayer Perceptron (MLP) regression model to predict car prices based on various features like make, model, engine size, etc., using the PyTorch framework.

## Features 🌟

- Implements MLP regression models with varying depths and complexities to predict car prices.

- Uses the CarPrice_Assignment dataset for training and testing the models.

- Includes comprehensive preprocessing, normalization, and encoding of the dataset.

- Provides performance evaluation through Mean Squared Error (MSE) and R2 Score metrics.

- Contains visualization of loss and R2 Score over training epochs.

## Setup and Installation 🛠️

1. Clone the repository.

2. Install the required Python packages listed in `requirements.txt`.

3. Download and preprocess the dataset using the provided scripts.

## Data Preprocessing 📊

- Data normalization and cleaning to handle missing values and outliers.

- Encoding of categorical features to numeric values for model training.

- Data split into training, validation, and test sets for model evaluation.

## Model Training 🚀

- Models with different configurations (MLP1, MLP2, MLP3) are trained to find the best architecture.

- Uses Adam and Adagrad optimizers with varying learning rates to optimize the models.

- Saves the best model based on validation performance.

## Results and Evaluation 📊

- Evaluation on test data to measure MSE and R2 Score.

- Visualization of model performance through loss and R2 Score plots.

- Detailed comparison of predicted vs. actual prices on test samples.

## Contributing 🤝

Contributions to improve the project and implement new features are welcome. Please fork the repository, make your changes, and submit a pull request.

## License 📜

The project is licensed under the MIT License. See the LICENSE file for more details.

## Acknowledgements 🙌

- Dataset providers for making the car price dataset publicly available.

- The PyTorch team for providing a powerful and user-friendly deep learning framework.

For more information and to view the source code, visit the [GitHub repository](https://github.com/MJAHMADEE/MLP_Regression/).