import tensorflow as tf
import numpy as np
from PIL import Image
from huggingface_hub import hf_hub_download
import json

# Download model and class names from Hugging Face
model_path = hf_hub_download(repo_id="abdo1176/brain-model-test", filename="model.keras")
class_names_path = hf_hub_download(repo_id="abdo1176/brain-model-test", filename="class_names.json")

# Load model and class names
model = tf.keras.models.load_model(model_path)
with open(class_names_path, 'r') as f:
    class_names = json.load(f)

def preprocess_image(image_path):
    """Preprocess image for model prediction"""
    image = Image.open(image_path).convert('RGB')
    image = image.resize((224, 224))
    image = np.array(image) / 255.0
    image = np.expand_dims(image, axis=0)
    return image

def predict_brain_tumor(image_path):
    """Predict brain tumor from MRI image"""
    image = preprocess_image(image_path)
    predictions = model.predict(image)
    predicted_idx = np.argmax(predictions[0])
    confidence = float(predictions[0][predicted_idx])
    
    return {
        "predicted_class": class_names[predicted_idx],
        "confidence": confidence,
        "all_predictions": {class_names[i]: float(predictions[0][i]) for i in range(len(class_names))}
    }

# Example usage:
# result = predict_brain_tumor("path/to/your/mri_image.jpg")
# print(f"Prediction: {result['predicted_class']} (Confidence: {result['confidence']:.2%})")