https://github.com/saritaphd/diabetes-prediction-deployment-with-flask

Business Objective The objective of this project is to deploy a machine learning model through a Flask-based web application to predict whether a patient is diabetic or non-diabetic based on their medical details, such as glucose level, BMI, age, and other health indicators.
https://github.com/saritaphd/diabetes-prediction-deployment-with-flask

Last synced: 3 days ago
JSON representation

Business Objective The objective of this project is to deploy a machine learning model through a Flask-based web application to predict whether a patient is diabetic or non-diabetic based on their medical details, such as glucose level, BMI, age, and other health indicators.

• Host: GitHub
• URL: https://github.com/saritaphd/diabetes-prediction-deployment-with-flask
• Owner: SaritaPhD
• License: mit
• Created: 2024-11-04T08:31:12.000Z (15 days ago)
• Default Branch: main
• Last Pushed: 2024-11-13T05:45:56.000Z (6 days ago)
• Last Synced: 2024-11-13T06:25:56.398Z (6 days ago)
• Language: Jupyter Notebook
• Size: 57.6 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Diabetes Prediction Web Application

The objective of this project is to build and deploy a machine learning model through a Flask-based web application to predict whether a patient is diabetic or non-diabetic based on their medical details, such as glucose level, BMI, age, and other health indicators. This application aims to provide healthcare providers and patients with a tool to easily and quickly assess the likelihood of diabetes, aiding in early detection and intervention.     

## Business Constraints

- Real-time Prediction: The application should respond quickly to user input for an efficient and seamless experience.

- Scalability: The application may need to handle multiple users simultaneously.

- Model Compatibility: Compatibility of the deployed model with the production environment is critical, as differences in library versions may affect functionality.

- User Privacy: Patient data used for prediction should be handled securely to maintain confidentiality.

## Business Success Criteria

- User Experience: The application should have a user-friendly interface, allowing easy input of medical details and interpretation of results.

- Reliability: The app should perform consistently and return accurate predictions without downtime or errors.

- Interpretability: The prediction results ("Diabetic" or "Non-Diabetic") should be presented in a way that is easy for non-technical users to understand.

- Machine Learning Success Criteria

- Prediction Accuracy: The model should correctly classify patients as diabetic or non-diabetic based on the provided input data.

- Scalability: The model should support scaling up to handle increasing loads of prediction requests without significant degradation in response time.

## Project Structure

- application.py: The main Flask application script containing routes for the homepage and data prediction.

- Model/standardScalar.pkl: Pre-trained scaler object to standardize input features.

- Model/modelForPrediction.pkl: Pre-trained machine learning model used for diabetes prediction.

- templates/index.html: HTML template for the application's homepage.

- templates/single_prediction.html: HTML template for displaying individual prediction results.

- templates/home.html: HTML template for additional application pages if needed.

- Dataset/diabetes.csv: Dataset

## Running the Application

- Install required dependencies: pip install -r requirements.txt

- Run the Flask application: python application.py

- Access the app by navigating to http://localhost:5001 in your web browser.

## Dependencies

- Flask, Numpy, Pandas, Scikit-learn