from fastai.vision.all import *
import gradio as gr

from pathlib import Path
import pandas as pd

def get_x(row):
    # All files are assumed to be '.jpg', so we directly return the path with '.jpg' extension
    return path_image_combined / f"{row['file_name']}.jpg"

def get_y(row):
    return row['Buried ODD']

# Load the models into a dictionary
models = {
    'Ultrasound': load_learner('ODDUltrasound.pkl'),
    'OCT': load_learner('ODDOCT.pkl'),
    'Fundus': load_learner('ODDfundus.pkl'),
    'Fluorescence': load_learner('ODDfluorescence.pkl')
}

modality_keys = ['Ultrasound', 'OCT', 'Fundus', 'Fluorescence']

def classify_images(img_ultrasound, img_oct, img_fundus, img_fluorescence):
    imgs = [img_ultrasound, img_oct, img_fundus, img_fluorescence]
    predictions = []
    detailed_predictions = []  # To store detailed predictions for each modality

    provided_imgs = [img for img in imgs if img is not None]
    
    if not provided_imgs:  # Check if no images were provided
        return "Please upload at least one image for prediction."
    
    # Convert provided images to PILImage and predict with each model
    for img, key in zip(imgs, modality_keys):
        if img is not None:
            pil_img = PILImage.create(img)
            pred, _, probs = models[key].predict(pil_img)
            prob_pred = probs.max()  # Get the highest probability score
            predictions.append(pred)
            detailed_predictions.append(f"{key}: {pred} ({prob_pred.item()*100:.2f}%)")
        else:
            detailed_predictions.append(f"{key}: No image provided")

    # Final decision logic here, if applicable
    
    return "\n".join(detailed_predictions)

# Define the Gradio interface inputs without using 'optional=True'
inputs = [gr.Image(label=f"{modality} Image") for modality in modality_keys]
output = gr.Text(label="Predictions")

intf = gr.Interface(fn=classify_images, inputs=inputs, outputs=output,
                    title="ODD Detection from Multiple Imaging Modalities",
                    description="Upload images for each modality (as available). It's not required to upload an image for every input field. At least one image is required for a prediction.")
intf.launch(share=True)