ryanthompson591 commented on code in PR #22088: URL: https://github.com/apache/beam/pull/22088#discussion_r940522435
########## sdks/python/apache_beam/examples/inference/README.md: ########## @@ -255,4 +255,42 @@ This writes the output to the `predictions.txt` with contents like: 0,0 ... ``` -Each line has data separated by a comma ",". The first item is the actual label of the digit. The second item is the predicted label of the digit. \ No newline at end of file +Each line has data separated by a comma ",". The first item is the actual label of the digit. The second item is the predicted label of the digit. + +### Running `sklearn_japanese_housing_regression.py` + +#### Getting the data: +Data for this example can be found at: +https://www.kaggle.com/datasets/nishiodens/japan-real-estate-transaction-prices + +#### Models: +Prebuilt sklearn pipelines are hosted at: +https://storage.cloud.google.com/apache-beam-ml/models/japanese_housing/ + +Note: This example uses more than one model. Since not all features in an example are populated, a different model will be chosen based on available data. + +For example an example without distance to the nearest station will use a model that doesn't rely on that data. + +#### Running the Pipeline +To run locally, use the following command: +```sh +python -m apache_beam.examples.inference.sklearn_japanese_housing_regression.py \ + --input_file INPUT \ + --output OUTPUT \ + --model_path MODEL_PATH +``` +For example: +```sh +python -m apache_beam.examples.inference.sklearn_japanese_housing_regression.py \ + --input_file mnist_data.csv \ Review Comment: Let me give a better name. -- 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]
