This is an Old Project from 2 years Ago. It does not represent my current skillset. However I keep it for sentimental reasons.

XGBoost Fetal Health Classification

This project implements an XGBoost model for fetal health classification using the Fetal Health dataset available on Kaggle.

Overview

The goal of this project is to predict fetal health based on various features using the XGBoost algorithm. The model achieves an accuracy of 94% on the test dataset.

Project Structure

• Notebook: XGBoost_Fetal_Health_Classification.ipynb
• Model: XGB Fetal Health
• Requirements: requirements.txt

Dependencies

• matplotlib: 3.7.1
• numpy: 1.23.5
• pandas: 2.0.0
• scikit-learn: 1.2.2
• seaborn: 0.13.1
• xgboost: 2.0.3

How to Use

1. Clone the repository:

git clone https://github.com/LazyDart/XGBoost-for-Fetal-Health.git
cd XGBoost-Fetal-Health

2. Install the required dependencies:

pip install -r requirements.txt

3. Run the Jupyter Notebook:

jupyter notebook XGBoost_Fetal_Health_Classification.ipynb

4. Explore the notebook for detailed insights into data analysis, model training, and evaluation.

Results

The trained XGBoost model achieves an accuracy of 94% on the test dataset. The feature importance analysis is presented in the notebook.

Issues and Future Work

If you encounter any issues or have suggestions for improvement, please feel free to open an issue or submit a pull request. Future work may involve fine-tuning the model, exploring additional features, or optimizing hyperparameters.

License

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