app.py

# -*- coding: utf-8 -*-
"""
Diabetes Prediction Web App
"""

import numpy as np
import pickle
import streamlit as st

# Dictionary to hold different model names and their corresponding file paths
models = {
    "Logistic Regression": "LogisticRegression_model.pkl",
    "Decision Tree Classifier": "DecisionTreeClassifier_model.pkl",
    "Random Forest Classifier": "RandomForestClassifier_model.pkl",
    "SVC": "SVC_model.pkl"
}

# Load the default model (Logistic Regression in this case)
selected_model = "Logistic Regression"
loaded_model = pickle.load(open(models[selected_model], 'rb'))

# Function for making predictions
def diabetes_prediction(input_data, model):
    # Load the selected model
    loaded_model = pickle.load(open(models[model], 'rb'))
    
    # Convert input_data to numpy array
    input_data_as_numpy_array = np.asarray(input_data)
    input_data_reshaped = input_data_as_numpy_array.reshape(1, -1)
    
    prediction = loaded_model.predict(input_data_reshaped)

    if prediction[0] == 0:
        return 'The person is not diabetic'
    else:
        return 'The person is diabetic'

# Main function for the Streamlit app
def main():
    st.title('Diabetes Prediction Web App')
    
    # Dropdown for model selection
    selected_model = st.selectbox("Choose Prediction Method (Default: Logistic Regression)", list(models.keys()))
    
    # Input fields for user data
    Pregnancies = st.text_input('Number 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 of the Person')
    
    diagnosis = ''

    # Prediction button
    if st.button('Diabetes Test Result'):
        try:
            input_data = [
                float(Pregnancies),
                float(Glucose),
                float(BloodPressure),
                float(SkinThickness),
                float(Insulin),
                float(BMI),
                float(DiabetesPedigreeFunction),
                float(Age)
            ]
            diagnosis = diabetes_prediction(input_data, selected_model)
        except ValueError as e:
            diagnosis = "Invalid input. Please enter numeric values for all fields."

    st.success(diagnosis)

    # Dummy Entries or Demo for showcasing
    st.markdown('## Demo - Test with Dummy Entries')
    
    # You can set default values for the inputs to showcase the prediction functionality
    default_values = {
        "Number of Pregnancies": 5,
        "Glucose Level": 130,
        "Blood Pressure Value": 80,
        "Skin Thickness Value": 30,
        "Insulin Level": 100,
        "BMI Value": 35,
        "Diabetes Pedigree Function Value": 0.5,
        "Age of the Person": 40
    }
    
    demo_button = st.button('Run Demo')

    if demo_button:
        demo_input_data = [
            default_values["Number of Pregnancies"],
            default_values["Glucose Level"],
            default_values["Blood Pressure Value"],
            default_values["Skin Thickness Value"],
            default_values["Insulin Level"],
            default_values["BMI Value"],
            default_values["Diabetes Pedigree Function Value"],
            default_values["Age of the Person"]
        ]
        demo_diagnosis = diabetes_prediction(demo_input_data, selected_model)
        st.success(f'Demo Result: {demo_diagnosis}')

if __name__ == '__main__':
    main()