app.py

import joblib
import pandas as pd
import gradio as gr

class BioQuest:
    def __init__(self):
        self.liver_model = None

    def load_liver_model(self, model_path):
        self.liver_model = joblib.load(model_path)

    def liver_prediction(self, input_values):
        feature_names = [
            'age', 'gender', 'total_bilirubin', 'alkaline_phosphotase',
            'alamine_aminotransferase', 'albumin_and_globulin_ratio'
        ]

        input_data = dict(zip(feature_names, input_values))
        input_df = pd.DataFrame([input_data])
        result = self.liver_model.predict(input_df)

        if result[0] == 0:
            return 'The person does not have liver disease.'
        else:
            return 'The person has liver disease.'

# Load the model
bioquest = BioQuest()
bioquest.load_liver_model('liver_model.sav')  

# Define the Gradio prediction function
def predict_liver_disease(age, gender, total_bilirubin, alkaline_phosphotase,
                          alamine_aminotransferase, albumin_and_globulin_ratio):
    input_values = [
        age,
        1 if gender == "Male" else 0,  
        total_bilirubin,
        alkaline_phosphotase,
        alamine_aminotransferase,
        albumin_and_globulin_ratio
    ]

    # Get the prediction from the BioQuest instance
    prediction = bioquest.liver_prediction(input_values)

    return prediction,image_url

# Image URL 
image_url = "liver.PNG" 

# Create Gradio interface
iface = gr.Interface(
    fn=predict_liver_disease,
    inputs=[
        gr.Slider(minimum=1, maximum=100, value=65, label="Age"),
        gr.Radio(choices=["Male", "Female"], label="Gender", value="Female"),
        gr.Slider(minimum=0.0, maximum=10.0, step=0.01, value=0.7, label="Total Bilirubin"),
        gr.Slider(minimum=0, maximum=500, value=187, label="Alkaline Phosphotase"),
        gr.Slider(minimum=0, maximum=500, value=16, label="Alamine Aminotransferase"),
        gr.Slider(minimum=0.0, maximum=10.0, step=0.01, value=0.9, label="Albumin and Globulin Ratio")
    ],
    outputs=[
        gr.Text(label="Prediction"),
        gr.Image(value=image_url, label="Image", show_label=True)  # Set the image to be static
    ],
    title="Liver Disease Prediction",
    description="Enter the patient's details to predict the likelihood of liver disease."
)

# Launch the interface
iface.launch()