This web application predicts whether a person is diabetic based on their medical information. It utilizes a Support Vector Machine (SVM) model trained on a dataset of diabetes patients.
To use the web app, follow these steps:
- Clone this repository to your local machine.
- Install the required dependencies by running
pip install -r requirements.txt
. - Run the web app using Streamlit by running
streamlit run app.py
in your terminal. - Enter the required medical information in the sidebar.
- Click the "Predict" button to see the prediction.
The dataset used for training the SVM model is available on Kaggle. It contains various medical features such as glucose level, blood pressure, BMI, etc., along with the target variable indicating whether the person is diabetic or not.
The SVM model used for prediction is trained using scikit-learn library. The model achieves an accuracy of 72% on the test data.