FastAPI: Internal Server Error when returning ML model prediction

Question

I would like to test my pipeline in FastAPI, but I can't find the mistake in my code. When I test it using the Visual Studio Code (using a print() statement), it works. However, when I try accessing the endpoint through the browser, I get Internal Server Error. It works when I return something else as the prediction results (e.g., some string), instead of the actual prediction results.

Here is my code:

class FraudDetection333(BaseModel):
    """
    Input features validation for the ML model
    """
    user_id: int
    signup_day: int
    signup_month: int
    signup_year: int
    purchase_day: int
    purchase_month: int
    purchase_year: int
    purchase_value: float
    source: str
    browser: str
    sex: str
    age: int

@api.post("/predictions_test",tags=['DecisionTreeClassifier'])
def predictions_test(fraud:FraudDetection333):
    """
    :param:input data from the post request
    :return predicted type
    """
    features = [[
    fraud.user_id,
    fraud.signup_day,
    fraud.signup_month,
    fraud.signup_year,
    fraud.purchase_day,
    fraud.purchase_month,
    fraud.purchase_year,
    fraud.purchase_value,
    fraud.source,
    fraud.browser,
    fraud.sex,
    fraud.age
    ]]
    rf_model = joblib.load('./rf_model.pkl')
    new = (pd.DataFrame(features, index = ['0'], columns = ['user_id','signup_day',         
'signup_month', 'signup_year', 
        'purchase_day', 'purchase_month', 'purchase_year','purchase_value',
        'source','browser','sex','age']))
    new_prediction = rf_model.predict(new)
    return {
        "Predicted transaction(1 - fraud, 0 - not fraud)": new_prediction
    }

If I try the below (using a print() statement), it prints out the expected outcome:

featuress={
  "user_id": 22058,
  "signup_day": 24,
  "signup_month": 2,
  "signup_year": 2015,
  "purchase_day": 18,
  "purchase_month": 4,
  "purchase_year": 2015,
  "purchase_value": 34,
  "source": "SEO",
  "browser": "Chrome",
  "sex": "M",
  "age": 39
}
rf_model = joblib.load('./rf_model.pkl')
new = (pd.DataFrame(featuress, index = ['0'], columns = ['user_id','signup_day',     
 'signup_month', 'signup_year', 
        'purchase_day', 'purchase_month', 'purchase_year','purchase_value',
        'source','browser','sex','age']))
new_prediction = rf_model.predict(new)
print(new)
print(new_prediction)

If I type return {"Predicted transaction(1 - fraud, 0 - not fraud)": 'Hi'}, it also works. Image here.

How are you testing the API on the server, and what is the error message on the server? — M.O.
– M.O., Commented Jun 25, 2022 at 13:44
The server log should have the complete error message - i.e. exactly what caused the server to respond with internal server error. — MatsLindh
– MatsLindh, Commented Jun 25, 2022 at 13:49
Since you're not sending data into to your dataframe with identical structure between the working and borked code it seems like it can be caused other issues as well. — MatsLindh
– MatsLindh, Commented Jun 25, 2022 at 13:51
Maybe first use print() (and print(type(...)), print(len(...)), etc.) to see which part of code is executed and what you really have in variables. It is called "print debuging" and it helps to see what code is really doing. — furas
– furas, Commented Jun 25, 2022 at 19:09
it sends response as JSON but JSON can send only basis data types - string, int, float, list, dict. It can't send DataFrame nor numpy.array. You have to convert it to basis data types. — furas
– furas, Commented Jun 25, 2022 at 19:10

Chris · Accepted Answer · 2022-06-27 04:59:59Z

2

The model.predict() function returns a numpy.ndarray (you could verify that using print(type(new_prediction))). You can't just return it in that format; hence, the Internal Server Error.

Option 1 is to simply retireve and return the first element of that numpy array:

return {'prediction': new_prediction[0]}

Option 2 is to convert the numpy array into a Python list using the .tolist() method.

return {'prediction': new_prediction.tolist()}

Related answers can be found here and here.

edited Jun 27, 2022 at 4:59

answered Jun 25, 2022 at 15:33

Chris

38.5k11 gold badges106 silver badges282 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

FastAPI: Internal Server Error when returning ML model prediction

1 Answer 1

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related