https://github.com/jatin-mehra119/bike-rentals-dataset

This repository focuses on optimizing bike rental availability during peak hours and days using machine learning techniques. Leveraging publicly available data from the UCI Machine Learning Repository, it includes scripts for data preprocessing, model training, and visualization, along with detailed observations and results.
https://github.com/jatin-mehra119/bike-rentals-dataset

data-analysis data-science ensemble-model pandas scikitlearn-machine-learning

Last synced: about 1 month ago
JSON representation

This repository focuses on optimizing bike rental availability during peak hours and days using machine learning techniques. Leveraging publicly available data from the UCI Machine Learning Repository, it includes scripts for data preprocessing, model training, and visualization, along with detailed observations and results.

• Host: GitHub
• URL: https://github.com/jatin-mehra119/bike-rentals-dataset
• Owner: Jatin-Mehra119
• License: mit
• Created: 2024-06-28T17:05:42.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-07-09T10:57:19.000Z (8 months ago)
• Last Synced: 2024-11-16T21:14:39.988Z (3 months ago)
• Topics: data-analysis, data-science, ensemble-model, pandas, scikitlearn-machine-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 1.19 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: License.txt

Awesome Lists containing this project

README

        
# Bike Rentals Optimization

## Overview

- **Objective**: Optimize bike rentals to ensure smooth availability during peak hours and days.

- **Data Source**: Publicly available data from the [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/datasets/Bike+Sharing+Dataset).

## Repository Contents

- **Data Preprocessing**:

  - Scripts for cleaning and transforming the raw data.

- **Model Training**:

  - Scripts for training machine learning models and saving their metrics.

- **Data Visualization**:

  - Jupyter Notebook (`Notebook.ipynb`) for visualizing the data using Matplotlib and Seaborn.

  - Includes brief points and observations based on visualizations.

- **Feature Importance**:

  - Extracted feature importances using trained models.

- **Output**:

  - `output.txt`: Contains results from the `main.py` script.

## Usage

1. **Use main.py script**:

   - This script will automatically preprocess the data and train the model, save the model and test metrics using preprocessing.py and train.py. 

2. **Visualize the Data**:

   - Open and run the `Notebook.ipynb` to explore the data and model performance visually.

## Observations

- Detailed observations and insights are documented within `Notebook.ipynb`.

## Notes

- Ensure all dependencies are installed before running the scripts and notebooks.

- The models and metrics are saved for easy retrieval and analysis.

## License

- This project is licensed under the MIT License - see the LICENSE file for details.

## Acknowledgements

- Special thanks to the UCI Machine Learning Repository for providing the dataset.

## Trained Models

- [Trained Models](https://drive.google.com/drive/folders/1vNOLwai1ssZ96fa1GcNegiT0aqLklbXf?usp=sharing)

## Project Overview

![Untitled drawing](https://github.com/Jatin-Mehra119/Bike-Rentals-Dataset/assets/165004724/d476d0f5-4d24-4e7a-ba1d-0c44e6cad56f)