Sounds like a configuration issue, this algorithm should be able to output proper output CSVs.
Are you using
assemble_with="Line" on your
Transformer? Is your
strategy set to
content_type="text/csv" on the
I have had custom algorithms accidentally output row vectors instead of column vectors for multi-record batches in the past (because they gave a 1D output which the default serializer interpreted as a row), but not built-in algorithms.
SingleRecord could be a last resort (forcing Batch Transform itself to handle the serialization), but would decrease efficiency/speed.
Can't load xgboost models created with Sagemaker Estimatorasked 7 months ago
InternalServerError with SageMaker Batch transform jobasked 3 months ago
xgboost sagemaker batch transform job output in multiple linesAccepted Answerasked 2 years ago
Does Amazon SageMaker XGBoost support parallel training across multiple machines?Accepted Answer
Sagemaker batch transform 415 errorAccepted AnswerEXPERTasked 4 years ago
SageMaker XGBoost batch transform AttributeErrorasked 3 months ago
how to log error/messages in while running a sagemaker batch transform job?asked 4 months ago
SageMaker Batch Transform local mode?Accepted Answer
loading and deploying a previously trained sagemaker xgboost modelasked 3 years ago
Sagemaker XGBoost Forecast Horizon Perameterasked 4 months ago