Deployed xgboost model fail with an error when calling prediction function

I am using Amazon SageMaker (SageMaker: 2.24.1) to build and deploy a model on the classical "orders_with_predicted_value.csv" dataset. Everything works fine with the training, and the model deploys well, but when I call the prediction method on the test data I get the following error:

AttributeError: ("'NoneType' object has no attribute 'Accept'", 'occurred at index 0')

I opened the prediction function of SageMaker trying to solve this issue but to no effect.

Here's my code: 1

Read more here:

Content Attribution

This content was originally published by Diadie Sow at Recent Questions - Stack Overflow, and is syndicated here via their RSS feed. You can read the original post over there.

%d bloggers like this: