https://github.com/freedisch/optimization-with-multiple-variables

https://github.com/freedisch/optimization-with-multiple-variables

Last synced: 19 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/freedisch/optimization-with-multiple-variables
• Owner: Freedisch
• Created: 2023-11-19T19:47:06.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2023-11-19T20:22:45.000Z (about 1 year ago)
• Last Synced: 2023-11-20T20:38:31.622Z (about 1 year ago)
• Language: Jupyter Notebook
• Size: 127 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Submission for Summative Assignment: Linear Regression Optimization and Comparative Modeling

## Introduction

This document accompanies my submission for the Summative Assignment on optimizing a linear regression model using gradient descent and comparing it with Decision Trees and Random Forests models. 

## Work Process

### Notebook Review and Implementation

- **Code Snippets Completion**: I've thoroughly reviewed the provided notebook and completed all the required code snippets. 

- **Passing Unit Tests**: Each section of the notebook was carefully addressed, ensuring that the code passed all the unit tests.

### Exercises

The exercises I completed in the notebook include:

1. **Data Preparation and Analysis**: Preprocessing and understanding the dataset for TV sales prediction.

2. **Implementing Gradient Descent for Linear Regression**: Developing the linear regression model using gradient descent.

3. **Model Optimization and Evaluation**: Fine-tuning the linear regression model for optimal performance.

4. **Decision Trees and Random Forests Models**: Creating and analyzing these models for comparison.

5. **Comparative Analysis**: Evaluating the RMSE of all models and ranking them based on their performance.

## Results and Observations

- **Model Comparisons**: The RMSE of each model was carefully calculated and compared. 

- **Ranking Models**: Based on the RMSE, I ranked the models from best to least performing in terms of accuracy.

## Challenges and Learning

- I faced challenges in optimizing the gradient descent algorithm but managed to overcome them through research and experimentation.

- The comparative analysis of different models provided me with deeper insights into the strengths and weaknesses of each modeling approach.

## Conclusion

This assignment was a comprehensive learning experience in understanding and implementing linear regression optimization and comparative model analysis. It has significantly enhanced my skills in machine learning and data analysis.

## Additional Files

- **Notebook File**: Attached with this submission.

- **Cheat Sheet Reference**: Used for quick guidance and troubleshooting.

## Acknowledgements

I would like to thank the instructors and peers for their support and guidance throughout this project.

---

*Student Name: [Magnim Thibaut Batale]*  

*Date: [19 November 2023]*  

*Course: [Mathematics for Machine Learning]*