from fastapi import FastAPI, File, UploadFile, HTTPException
from fastapi.responses import JSONResponse
import cv2
import numpy as np
from tensorflow import keras
import uvicorn

app = FastAPI()

@app.get("/")
async def app_status():
    return {"message": "APP is running"}

# model = keras.models.load_model('savedModel/facialemotionmodel.h5')

# def prepare_image(img):
#     img = cv2.cvtColor(np.array(img), cv2.COLOR_BGR2GRAY)  # Convert to grayscale
#     img = cv2.resize(img, (48, 48))  # Resize image to 48x48
#     img = img / 255.0  # Normalize pixel values to 0-1
#     img = img.reshape(1, 48, 48, 1)  # Reshape for the model
#     return img

# def predict_emotion(img):
#     prediction = model.predict(img)
#     return prediction

# def interpret_prediction(prediction):
#     emotions = ['angry', 'disgust', 'fear', 'happy', 'neutral', 'sad', 'surprise']
#     max_index = prediction.argmax()
#     return emotions[max_index]

# @app.post("/detect-emotion/")
# async def detect_emotion(file: UploadFile = File(...)):
#     if file.content_type.startswith('image/'):
#         # Read image through file stream
#         image_data = await file.read()
#         image_array = np.frombuffer(image_data, np.uint8)
#         image = cv2.imdecode(image_array, cv2.IMREAD_COLOR)
#         if image is None:
#             raise HTTPException(status_code=400, detail="Could not read the image")
        
#         prepared_image = prepare_image(image)
#         prediction = predict_emotion(prepared_image)
#         emotion = interpret_prediction(prediction[0])
#         return JSONResponse(content={"detected_emotion": emotion})
#     else:
#         raise HTTPException(status_code=400, detail="File format not supported")

if __name__ == "__main__":
    uvicorn.run(app, host="0.0.0.0", port=8000)