https://github.com/athrvvv/diabetes_prediction_system
The Diabetes Prediction System uses a Naive Bayes classification model to predict diabetes based on input data. It includes a Jupyter Notebook for model training, a Flask application (app.py) for deployment, and a pickle file (model.pkl) to load the trained model. The system processes user input and predicts the likelihood of diabetes.
https://github.com/athrvvv/diabetes_prediction_system
artificial-intelligence csv deployment machine-learning naive-bayes-classifier streamlit-webapp supervised-learning
Last synced: 11 months ago
JSON representation
The Diabetes Prediction System uses a Naive Bayes classification model to predict diabetes based on input data. It includes a Jupyter Notebook for model training, a Flask application (app.py) for deployment, and a pickle file (model.pkl) to load the trained model. The system processes user input and predicts the likelihood of diabetes.
- Host: GitHub
- URL: https://github.com/athrvvv/diabetes_prediction_system
- Owner: Athrvvv
- Created: 2025-03-21T07:58:53.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-21T08:13:49.000Z (over 1 year ago)
- Last Synced: 2025-03-21T09:22:29.602Z (over 1 year ago)
- Topics: artificial-intelligence, csv, deployment, machine-learning, naive-bayes-classifier, streamlit-webapp, supervised-learning
- Language: Jupyter Notebook
- Homepage: https://diabetespredictionsystem-x2sefw8mxybx2xbskpr9fu.streamlit.app/
- Size: 9.77 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Diabetes Prediction System 🩺
**Diabetes Prediction System** is a machine learning project that uses a **Naive Bayes classification model** to predict the likelihood of diabetes based on user inputs. The system processes medical data, applies predictive analysis, and provides results via a **Flask web application**.
## Why Naive Bayes?
**Naive Bayes** is ideal for medical predictions due to its simplicity and efficiency. It calculates the **probability of diabetes** by analyzing input features independently, ensuring quick and accurate predictions.
## Features
- **Machine Learning Model**: Trained using Naive Bayes on medical data.
- **Web Interface**: Flask-based UI for entering data and viewing results.
- **Pickle Model Deployment**: Pre-trained model stored and loaded via `model.pkl`.
- **Data Processing**: Pandas and NumPy for handling and transforming data.
## Technologies Used
- **Python**
- **Flask**
- **Scikit-learn**
- **Pandas, NumPy**
- **Jupyter Notebook**
## Installation & Setup
1. Clone the repository:
```bash
git clone https://github.com/Athrvvv/Diabetes_Prediction_System.git
cd Diabetes_Prediction_System
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Run the Flask app:
```bash
python app.py
```
## Usage
- Open `diabetes_model.ipynb` to analyze data and retrain the model if needed.
- Run `app.py` to launch the web application and interact with the prediction system.
- Input relevant medical data to receive a **diabetes prediction**.
## Dataset
The dataset used contains **medical attributes** such as glucose levels, BMI, and insulin, which are used by the model to predict diabetes.
## Future Enhancements
- Add more advanced models for comparison.
- Deploy on cloud platforms for wider accessibility.
- Enhance UI for better user experience.
## Contact
For queries or suggestions, open an issue in the repository.