-
Welcome to the Diabetes Prediction System, the second project of my internship at MeriSKILL.
-
As a data analyst, I've developed this Python-based application to predict the likelihood of an individual having diabetes using machine learning techniques.
-
The predictive model, built with scikit-learn's logistic regression, boasts an accuracy score of approximately 0.81. To make the system accessible and user-friendly, I've deployed it using Django, creating a local server for seamless interaction.
-
Video Presentation: Click here
-
Linkedin Post: Click here
-
Machine Learning Model: Utilizes logistic regression for diabetes prediction, achieving an accuracy score of approximately 0.81.
-
Web Application: The model is deployed using Django, providing a user-friendly interface for input and displaying the prediction results.
-
NumPy: Fundamental package for scientific computing with Python.
-
Pandas: Data manipulation and analysis library.
-
Seaborn: Statistical data visualization.
-
scikit-learn: Machine learning library for classification, regression, and clustering.
-
joblib: Library for lightweight pipelining in Python.
-
Clone the repository:
git clone https://github.com/MohdAkif919/Diabetes-Prediction-System.git
-
Navigate to the project directory:
cd Diabetes-Prediction-System
-
Install the required dependencies:
pip install -r requirements.txt
-
Run the Django development server:
python manage.py runserver
-
Access the application:
- Open your web browser and navigate to http://127.0.0.1:8000/.
-
Input relevant features:
- Fill out the form with the required information. This typically includes input fields for features such as age, BMI, blood pressure, etc.
-
Get the prediction:
- Click the "Submit" button to send the input data to the machine learning model.
- The system will then provide a prediction for the likelihood of diabetes based on the input values.
- Home Page
- Non-Diabetes Patient
- Diabetes Patient
This project serves as the second project in my internship at MeriSKILL, where I hold the position of a data analyst. I am excited to contribute to the organization's goals and further enhance my skills in data analysis.