https://github.com/pialghosh2233/diabetes_prediction_using_ml
https://github.com/pialghosh2233/diabetes_prediction_using_ml
artificial-intelligence artificial-intelligence-projects data-science machine-learning machine-learning-project machine-learning-projects machinelearning ml-project python
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/pialghosh2233/diabetes_prediction_using_ml
- Owner: PialGhosh2233
- Created: 2024-05-05T22:08:34.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-05-05T22:21:13.000Z (about 2 years ago)
- Last Synced: 2025-03-02T02:15:53.643Z (over 1 year ago)
- Topics: artificial-intelligence, artificial-intelligence-projects, data-science, machine-learning, machine-learning-project, machine-learning-projects, machinelearning, ml-project, python
- Language: Jupyter Notebook
- Homepage:
- Size: 146 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Diabetes Prediction Model
This repository hosts a Python-based machine learning project aimed at predicting diabetes using patient health data from
https://www.kaggle.com/datasets/mathchi/diabetes-data-set
The project leverages common machine learning techniques and several popular libraries, including pandas, NumPy, scikit-learn, and Matplotlib, to preprocess data, train models, and evaluate their performance.
## Project Overview
The dataset used in this project is derived from the the National Institute of Diabetes and Digestive and Kidney Diseases. It includes several diagnostic measurements such as glucose concentration, blood pressure, skin thickness, insulin level, BMI, age, and more.
## Key Features
- **Data Preprocessing**: Includes handling missing values, feature scaling, and data transformations to prepare the dataset for modeling.
- **Model Training and Evaluation**: Employs three different machine learning models:
- Logistic Regression
- K-Nearest Neighbors (KNN)
- Support Vector Machine (SVM)
- **Performance Analysis**: Evaluates models based on accuracy, precision, and recall. Includes detailed visualizations of model performance.
- **Data Visualization**: Uses Matplotlib and Seaborn for insightful visualizations of the dataset distribution and model outcomes.
## Contributing
Contributions are welcome! For major changes, please open an issue first to discuss what you would like to change. Please ensure to update tests as appropriate.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE.md) file for details.