github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/complete/juliaset/juliaset_main.py (about)

     1  #
     2  # Licensed to the Apache Software Foundation (ASF) under one or more
     3  # contributor license agreements.  See the NOTICE file distributed with
     4  # this work for additional information regarding copyright ownership.
     5  # The ASF licenses this file to You under the Apache License, Version 2.0
     6  # (the "License"); you may not use this file except in compliance with
     7  # the License.  You may obtain a copy of the License at
     8  #
     9  #    http://www.apache.org/licenses/LICENSE-2.0
    10  #
    11  # Unless required by applicable law or agreed to in writing, software
    12  # distributed under the License is distributed on an "AS IS" BASIS,
    13  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    14  # See the License for the specific language governing permissions and
    15  # limitations under the License.
    16  #
    17  
    18  """A Julia set computing workflow: https://en.wikipedia.org/wiki/Julia_set.
    19  
    20  This example has in the juliaset/ folder all the code needed to execute the
    21  workflow. It is organized in this way so that it can be packaged as a Python
    22  package and later installed in the VM workers executing the job. The root
    23  directory for the example contains just a "driver" script to launch the job
    24  and the setup.py file needed to create a package.
    25  
    26  The advantages for organizing the code is that large projects will naturally
    27  evolve beyond just one module and you will have to make sure the additional
    28  modules are present in the worker.
    29  
    30  In Python Dataflow, using the --setup_file option when submitting a job, will
    31  trigger creating a source distribution (as if running python setup.py sdist) and
    32  then staging the resulting tarball in the staging area. The workers, upon
    33  startup, will install the tarball.
    34  
    35  Below is a complete command line for running the juliaset workflow remotely as
    36  an example:
    37  
    38  python juliaset_main.py \
    39    --job_name juliaset-$USER \
    40    --project YOUR-PROJECT \
    41    --region GCE-REGION \
    42    --runner DataflowRunner \
    43    --setup_file ./setup.py \
    44    --staging_location gs://YOUR-BUCKET/juliaset/staging \
    45    --temp_location gs://YOUR-BUCKET/juliaset/temp \
    46    --coordinate_output gs://YOUR-BUCKET/juliaset/out \
    47    --grid_size 20
    48  
    49  """
    50  
    51  # pytype: skip-file
    52  
    53  import logging
    54  
    55  from apache_beam.examples.complete.juliaset.juliaset import juliaset
    56  
    57  if __name__ == '__main__':
    58    logging.getLogger().setLevel(logging.INFO)
    59    juliaset.run()