rezarokni commented on code in PR #27430: URL: https://github.com/apache/beam/pull/27430#discussion_r1262289788
########## sdks/python/apache_beam/examples/ml_transform/ml_transform_basic.py: ########## @@ -61,49 +61,89 @@ def parse_args(): return parser.parse_known_args() -def run(args): - data = [ - dict(x=["Let's", "go", "to", "the", "park"]), - dict(x=["I", "enjoy", "going", "to", "the", "park"]), - dict(x=["I", "enjoy", "reading", "books"]), - dict(x=["Beam", "can", "be", "fun"]), - dict(x=["The", "weather", "is", "really", "nice", "today"]), - dict(x=["I", "love", "to", "go", "to", "the", "park"]), - dict(x=["I", "love", "to", "read", "books"]), - dict(x=["I", "love", "to", "program"]), - ] - +def preprocess_data_for_ml_training(train_data, artifact_mode, args): with beam.Pipeline() as p: Review Comment: We need some notes that this is the first of two pipelines that a user will run . -- 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]
