import gradio as gr
import joblib
from keras.preprocessing import image
import numpy as np

# Load the model using joblib
model = joblib.load("./your_model.pkl")

# Define a function to preprocess an image
def preprocess_image(image_path, target_size=(128, 128)):
    img = image.load_img(image_path, target_size=target_size)
    img_array = image.img_to_array(img)
    img_array = np.expand_dims(img_array, axis=0)
    img_array /= 255.0  # Normalize
    return img_array

# Define a prediction function for Gradio
def classify_skin_cancer(image):
    image_path = "uploaded_image.jpg"
    image.save(image_path)

    # Preprocess the image
    processed_image = preprocess_image(image_path)

    # Make a prediction using the model
    prediction = model.predict(processed_image)
    result = "Malignant" if prediction[0][0] > 0.5 else "Benign"
    
    return result

# Create a Gradio interface
iface = gr.Interface(
    fn=classify_skin_cancer,
    inputs=gr.inputs.Image(type="pil", label="Upload a skin image"),
    outputs="text",
    live=True,
    title="Skin Cancer Classifier",
    description="Upload a skin image and get a classification result (Malignant or Benign)."
)

if __name__ == "__main__":
    iface.launch()