github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/snippets/transforms/aggregation/cogroupbykey.py (about)

     1  # coding=utf-8
     2  #
     3  # Licensed to the Apache Software Foundation (ASF) under one or more
     4  # contributor license agreements.  See the NOTICE file distributed with
     5  # this work for additional information regarding copyright ownership.
     6  # The ASF licenses this file to You under the Apache License, Version 2.0
     7  # (the "License"); you may not use this file except in compliance with
     8  # the License.  You may obtain a copy of the License at
     9  #
    10  #    http://www.apache.org/licenses/LICENSE-2.0
    11  #
    12  # Unless required by applicable law or agreed to in writing, software
    13  # distributed under the License is distributed on an "AS IS" BASIS,
    14  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    15  # See the License for the specific language governing permissions and
    16  # limitations under the License.
    17  #
    18  
    19  # pytype: skip-file
    20  
    21  
    22  def cogroupbykey(test=None):
    23    # [START cogroupbykey]
    24    import apache_beam as beam
    25  
    26    with beam.Pipeline() as pipeline:
    27      icon_pairs = pipeline | 'Create icons' >> beam.Create([
    28          ('Apple', '🍎'),
    29          ('Apple', '🍏'),
    30          ('Eggplant', '🍆'),
    31          ('Tomato', '🍅'),
    32      ])
    33  
    34      duration_pairs = pipeline | 'Create durations' >> beam.Create([
    35          ('Apple', 'perennial'),
    36          ('Carrot', 'biennial'),
    37          ('Tomato', 'perennial'),
    38          ('Tomato', 'annual'),
    39      ])
    40  
    41      plants = (({
    42          'icons': icon_pairs, 'durations': duration_pairs
    43      })
    44                | 'Merge' >> beam.CoGroupByKey()
    45                | beam.Map(print))
    46      # [END cogroupbykey]
    47      if test:
    48        test(plants)