Skip to content

abhip2565/M-Bagging

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 

Repository files navigation

M-Bagging: Unleash the Power of Modified Bagging 🚀

M-Bagging is a groundbreaking ensemble learning technique that supercharges classification models. By fusing modified bootstrapping with heterogeneous classifiers, it achieves superior prediction accuracy.

image

Why ride a bicycle, when you have a supercar

Table of Contents

🌟 Features

  • Modified Bootstrapping: Special handling of misclassified samples and utilization of out-of-bag samples.
  • Heterogeneous Classifiers: A blend of SVM, Naïve Bayes, KNN, Decision Trees, and Logistic Regression.
  • Improved Prediction Accuracy: Outshines standard Bagging and rivals state-of-the-art models.
  • Adaptability: Tailor it to various datasets and classification tasks.

🛠️ Installation

Get started with just a few commands:

git clone https://github.com/your-username/m-bagging.git
cd m-bagging
pip install -r requirements.txt

🎥 Demo

🚀 Usage

Launch M-Bagging on your dataset with a single command:

python m_bagging.py --dataset path/to/dataset.csv

Full Documentation & Options

📊 Datasets & Results

Tested on diverse datasets like Diabetes, Liver Disorder, and more, M-Bagging exhibits remarkable results.

Detailed Results | Datasets Info

📖 My Research Paper

Title: M-Bagging: A New Modified Bagging Classification Model to Improve Prediction Accuracy

In this research, I present M-Bagging, a novel model that significantly enhances traditional Bagging. The key contributions include special handling of misclassified samples, utilization of out-of-bag samples, various classifiers, and superior prediction accuracy.

For a comprehensive understanding of the methodology and results, please explore the full research paper.

🤝 Contributing

Join the innovation! Contribution Guidelines

📜 License & References

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published