我已经训练了一个信用卡流失模型，并使用joblib保存了它。现在，我想使用FastAPI作为restful API进行部署。我已经完成了数据的预处理，如下所示，但是我得到了这个错误：

TypeError: float() argument must be a string or a number, not 'ModelMetaclass.

请看下面的代码和错误信息。谢谢。

from fastapi import FastAPI
import joblib
import uvicorn
from pydantic import BaseModel
from sklearn.pipeline import Pipeline, make_pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.compose import ColumnTransformer, make_column_selector as selector
import pandas as pd
import numpy as np


app = FastAPI(title ='Credit Card Churn Prediction', version = 1.0, description = 'Classification Machine Learning Prediction')

class model_input(BaseModel):
    Customer_Age : int
    Gender : int
    Dependent_count : int
    Education_level : int
    Marital_status : str
    Income_category : str
    Card_category : str
    months_on_book : int
    Total_Relationship_Count : int
    Months_Inactive_12_mon : int
    Contacts_Count_12_mon : int
    Credit_Limit : int
    Total_Revolving_Bal : int
    Avg_Open_To_Buy : int
    Total_Amt_Chng_Q4_Q1 : int
    Total_Trans_Amt : int
    Total_Trans_Ct : int
    Total_Ct_Chng_Q4_Q1 : int
    Avg_Utilization_Ratio : int

  

# load the model
model = joblib.load("joblib_CC_Model.pkl")

  
@app.post("/credit_card_churn_prediction")
async def predicts(input:model_input):
    # Numeric Features
    num_features = [[input.Customer_Age, input.Dependent_count, input.months_on_book, input.Total_Relationship_Count, input.Months_Inactive_12_mon, 
                   input.Contacts_Count_12_mon, input.Credit_Limit, input.Total_Revolving_Bal, input.Avg_Open_To_Buy, input.Total_Amt_Chng_Q4_Q1, input.Total_Trans_Amt, 
                   input.Total_Trans_Ct, input.Total_Ct_Chng_Q4_Q1, input.Avg_Utilization_Ratio, input.Gender, input.Education_level]]
    num_pipeline = Pipeline([("Scaler", StandardScaler())])
    
    # Categorical Features
    cat_features = [[input.Gender, input.Education_level, input.Marital_status, input.Card_category]]
    cat_pipeline = Pipeline([("onehot", OneHotEncoder())])

    final_input = ColumnTransformer(transformers = [("numeric_preprocessing", num_pipeline, num_features),
                                       ("categorical_preprocessing", cat_pipeline, cat_features)])
   
    prediction = model.predict([[model_input]])
    return prediction

if __name__ == '__main__':
    uvicorn.run("Main:app", reload = True)

我已经构建了一个分类ML模型，我正在使用FastAPI部署它，但我得到这个错误：

ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 419, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 78, in __call__
    return await self.app(scope, receive, send)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\fastapi\applications.py", line 270, in __call__
    await super().__call__(scope, receive, send)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\starlette\applications.py", line 124, in __call__
    await self.middleware_stack(scope, receive, send)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\starlette\middleware\errors.py", line 184, in __call__
    raise exc
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\starlette\middleware\errors.py", line 162, in __call__
    await self.app(scope, receive, _send)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\starlette\middleware\exceptions.py", line 79, in __call__
    raise exc
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\starlette\middleware\exceptions.py", line 68, in __call__
    await self.app(scope, receive, sender)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 21, in __call__
    raise e
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 18, in __call__
    await self.app(scope, receive, send)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\starlette\routing.py", line 706, in __call__
    await route.handle(scope, receive, send)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\starlette\routing.py", line 276, in handle
    await self.app(scope, receive, send)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\starlette\routing.py", line 66, in app
    response = await func(request)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\fastapi\routing.py", line 235, in app
    raw_response = await run_endpoint_function(
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\fastapi\routing.py", line 161, in run_endpoint_function
    return await dependant.call(**values)
  File "d:\Work\Mine\Data Science\Projects\Data Science\FastAPI\Main.py", line 59, in predicts
    prediction = model.predict([[model_input]])
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\xgboost\sklearn.py", line 1284, in predict
    class_probs = super().predict(
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\xgboost\sklearn.py", line 897, in predict
    test = DMatrix(
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\xgboost\core.py", line 506, in inner_f
    return f(**kwargs)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\xgboost\core.py", line 616, in __init__
    handle, feature_names, feature_types = dispatch_data_backend(
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\xgboost\data.py", line 768, in dispatch_data_backend
    return _from_list(data, missing, threads, feature_names, feature_types)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\xgboost\data.py", line 700, in _from_list
    return _from_numpy_array(array, missing, n_threads, feature_names, feature_types)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\xgboost\data.py", line 171, in _from_numpy_array
    data, _ = _ensure_np_dtype(data, data.dtype)
  File "D:\Work\Mine\Data Science\Projects\Data Science\FastAPI\venv\lib\site-packages\xgboost\data.py", line 138, in _ensure_np_dtype
    data = data.astype(np.float32, copy=False)
TypeError: float() argument must be a string or a number, not 'ModelMetaclass'

我让它在SwaggerUI上运行，并输入类BaseModel中显示的输入。