rszper commented on code in PR #22763: URL: https://github.com/apache/beam/pull/22763#discussion_r948455636
########## website/www/site/content/en/documentation/sdks/python-machine-learning.md: ########## @@ -129,7 +129,7 @@ with pipeline as p: When doing a prediction in Apache Beam, the output `PCollection` includes both the keys of the input examples and the inferences. Including both these items in the output allows you to find the input that determined the predictions. -The `PredictionResult` is a `NamedTuple` object that contains both the input and the inferences, named `example` and `inference`, respectively. When keys are passed with the input data to the RunInference transform, the output `PCollection` returns a `Tuple[str, PredictionResult]`, which is the key and the `PredictionResult` object. Your pipeline interacts with a `PredictionResult` object in steps after the RunInference transform. Review Comment: This comma actually should be here. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
