Input and Output interface for the CatBoost algorithm

Question

to set up CatBoost Classifier as a built-in algorithm, aws in this [https://docs.aws.amazon.com/sagemaker/latest/dg/catboost.html] suggested this notebook [https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/lightgbm_catboost_tabular/Amazon_Tabular_Classification_LightGBM_CatBoost.ipynb] , my question is should I prepare inference file on top of the train.csv? if yes what is that and how it should be prepared?

Accepted Answer

According to the documentation,[https://docs.aws.amazon.com/sagemaker/latest/dg/catboost.html] 'The CatBoost built-in algorithm runs in script mode, but the training script is provided for you and there is no need to replace it. If you have extensive experience using script mode to create a SageMaker training job, then you can incorporate your own CatBoost training scripts.' Is the same with the Inference script, all provided artifacts.

Answer

For the built-in algorithms, you can simply specify `estimator.deploy()`, or `tuner.deploy()` and the trained model will be deployed to an endpoint for inference.

You can also bring your own code/model, in which case, you'll need an *inference.py* file. See [Use your own Inference Code](https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-main.html) for details.

Input and Output interface for the CatBoost algorithm

Conteúdo relevante