Diabetes Prediction Machine Learning Project Using Python Streamlit

Last Updated : 24 Apr, 2025

In this article, we will demonstrate how to create a Diabetes Prediction Machine Learning Project using Python and Streamlit. Our primary objective is to build a user-friendly graphical interface using Streamlit, allowing users to input data for diabetes prediction. To achieve this, we will leverage a dataset as our backend, along with a generated .sav file to facilitate diabetes prediction.

Diabetes Prediction Machine Learning Project using Python Streamlit

Below are the steps by which we can make a Diabetes Prediction Machine Learning Project using Python Streamlit:

Step 1: Create a Virtual Environment

First, we need to create a virtual environment and enter into a virtualenv

virtualenv env 
.\env\Scripts\activate.ps1

Note.

Step 2: Install Libraries

First, install all the essential libraries using the following commands. In a Diabetes prediction GUI built with Streamlit, these libraries serve critical roles. Numpy enables efficient data handling, Pickle5 is essential for saving and loading machine learning models, and Streamlit empowers the creation of simple web apps from data analysis scripts, making them accessible to users without the need for advanced web development skills.

pip install numpy
pip install pickle5
pip install streamlit

Step 3 : File Structure

Step 4: Writing Our Code

After installing all the libraries we write our coding part :

Model Loading: The code loads a pre-trained machine learning model from a file named 'trained_model.sav' using the pickle.load method. This model is stored in the variable loaded_model and will be used for making predictions.
Diabetes Prediction Function: The diabetes_prediction function is defined to make predictions based on user input. It takes a list of input data, converts it to a NumPy array, reshapes it, and then uses the loaded model to make a prediction. If the prediction is 0, it returns 'Non Diabetic,' otherwise, it returns 'Diabetic'.
Main Function: The main function is the core of the web application. It uses Streamlit to create a simple web interface for diabetes prediction. It displays input fields for various features related to diabetes, such as number of pregnancies, glucose level, blood pressure, and more. After entering the data, the user can click a "Predict" button to trigger the prediction.
User Interface: The code defines the layout of the web app, takes user input for the diabetes-related features, calls the diabetes_prediction function with the user's input, and displays the prediction result using the st.success function. If the user clicks the "Predict" button, the result is shown, indicating whether the individual is predicted to be diabetic or non-diabetic.

Python3

# import all libraries
import numpy as np
import pickle
import streamlit as st

# Loading the saved model
loaded_model = pickle.load(open('trained_model.sav', 'rb'))

# Creating a function for prediction

def diabetes_prediction(input_data):

    # Changing the data into a NumPy array
    input_data_as_nparray = np.asarray(input_data)

    # Reshaping the data since there is only one instance
    input_data_reshaped = input_data_as_nparray.reshape(1, -1)

    prediction = loaded_model.predict(input_data_reshaped)

    if prediction == 0:
        return 'Non Diabetic'
    else:
        return 'Diabetic'

def main():

    # Giving a title
    st.title('Diabetes Prediction Web App')

    # Getting input from the user
    Pregnancies = st.text_input('No. of Pregnancies:')
    Glucose = st.text_input('Glucose level:')
    BloodPressure = st.text_input('Blood Pressure value:')
    SkinThickness = st.text_input('Skin thickness value:')
    Insulin = st.text_input('Insulin level:')
    BMI = st.text_input('BMI value:')
    DiabetesPedigreeFunction = st.text_input(
        'Diabetes pedigree function value:')
    Age = st.text_input('Age:')

    # Code for prediction
    diagnosis = ''

    # Making a button for prediction
    if st.button('Predict'):
        diagnosis = diabetes_prediction(
            [Pregnancies, Glucose, BloodPressure, SkinThickness, Insulin, BMI, DiabetesPedigreeFunction, Age])

    st.success(diagnosis)

if __name__ == '__main__':
    main()