github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/snippets/transforms/aggregation/groupbykey.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 groupbykey(test=None):
    23    # [START groupbykey]
    24    import apache_beam as beam
    25  
    26    with beam.Pipeline() as pipeline:
    27      produce_counts = (
    28          pipeline
    29          | 'Create produce counts' >> beam.Create([
    30              ('spring', '🍓'),
    31              ('spring', '🥕'),
    32              ('spring', '🍆'),
    33              ('spring', '🍅'),
    34              ('summer', '🥕'),
    35              ('summer', '🍅'),
    36              ('summer', '🌽'),
    37              ('fall', '🥕'),
    38              ('fall', '🍅'),
    39              ('winter', '🍆'),
    40          ])
    41          | 'Group counts per produce' >> beam.GroupByKey()
    42          | beam.MapTuple(lambda k, vs: (k, sorted(vs)))  # sort and format
    43          | beam.Map(print))
    44      # [END groupbykey]
    45      if test:
    46        test(produce_counts)