github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/snippets/transforms/aggregation/groupintobatches.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  
    20  def groupintobatches(test=None):
    21    # [START groupintobatches]
    22    import apache_beam as beam
    23  
    24    with beam.Pipeline() as pipeline:
    25      batches_with_keys = (
    26          pipeline
    27          | 'Create produce' >> beam.Create([
    28              ('spring', '🍓'),
    29              ('spring', '🥕'),
    30              ('spring', '🍆'),
    31              ('spring', '🍅'),
    32              ('summer', '🥕'),
    33              ('summer', '🍅'),
    34              ('summer', '🌽'),
    35              ('fall', '🥕'),
    36              ('fall', '🍅'),
    37              ('winter', '🍆'),
    38          ])
    39          | 'Group into batches' >> beam.GroupIntoBatches(3)
    40          | beam.Map(print))
    41      # [END groupintobatches]
    42      if test:
    43        test(batches_with_keys)