agvdndor commented on code in PR #23094: URL: https://github.com/apache/beam/pull/23094#discussion_r970855863
########## sdks/python/apache_beam/examples/ml-orchestration/kfp/components/preprocessing/src/preprocess.py: ########## @@ -0,0 +1,160 @@ +"""Dummy ingestion function that fetches data from one file and simply copies it to another.""" +import re +import json +import io +import argparse +import time +from pathlib import Path + +import requests +from PIL import Image, UnidentifiedImageError +import numpy as np +import torch +import torchvision.transforms as T +import torchvision.transforms.functional as TF +import apache_beam as beam +from apache_beam.options.pipeline_options import PipelineOptions + + +PROJECT_ID = "<project-id>" +LOCATION = "<project-location>" +STAGING_DIR = "<uri-to-data-flow-staging-dir>" +BEAM_RUNNER = "<beam-runner>" + +# [START preprocess_component_argparse] +def parse_args(): + """Parse preprocessing arguments.""" + parser = argparse.ArgumentParser() + parser.add_argument( + "--ingested-dataset-path", type=str, + help="Path to the ingested dataset") + parser.add_argument( + "--preprocessed-dataset-path", type=str, + help="The target directory for the ingested dataset.") + parser.add_argument( + "--base-artifact-path", type=str, + help="Base path to store pipeline artifacts.") + return parser.parse_args() Review Comment: Indeed! -- 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]
