app.py

from fastapi import FastAPI, HTTPException
from keras.models import model_from_json
from pydantic import BaseModel
import numpy as np
from typing import List

class InputData(BaseModel):
    data: List[float]  # Lista de características numéricas (flotantes)
    
app = FastAPI()
model = None  # Inicializa el modelo como None

# Carga del modelo
def load_model():
    try:
        json_file = open("model.json", 'r')
        loaded_model_json = json_file.read()
        json_file.close()
        loaded_model = model_from_json(loaded_model_json)
        loaded_model.load_weights("model.h5")
        loaded_model.compile(loss='mean_squared_error', optimizer='adam', metrics=['binary_accuracy'])
        return loaded_model
    except Exception as e:
        print(f"Error al cargar el modelo: {e}")
        return None

# Ruta de predicción
@app.post("/predict/")
async def predict(data: InputData):
    global model
    if model is None:
        model = load_model()
        if model is None:
            raise HTTPException(status_code=500, detail="Model could not be loaded")
    try:
        # Convertir la lista de entrada a un array de NumPy para la predicción
        input_data = np.array(data.data).reshape(1, -1)  # Asumiendo que la entrada debe ser de forma (1, num_features)
        prediction = model.predict(input_data).round()
        return {"prediction": prediction.tolist()}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))