github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/snippets/transforms/aggregation/sample.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 sample_fixed_size_globally(test=None):
    23    # [START sample_fixed_size_globally]
    24    import apache_beam as beam
    25  
    26    with beam.Pipeline() as pipeline:
    27      sample = (
    28          pipeline
    29          | 'Create produce' >> beam.Create([
    30              '🍓 Strawberry',
    31              '🥕 Carrot',
    32              '🍆 Eggplant',
    33              '🍅 Tomato',
    34              '🥔 Potato',
    35          ])
    36          | 'Sample N elements' >> beam.combiners.Sample.FixedSizeGlobally(3)
    37          | beam.Map(print))
    38      # [END sample_fixed_size_globally]
    39      if test:
    40        test(sample)
    41  
    42  
    43  def sample_fixed_size_per_key(test=None):
    44    # [START sample_fixed_size_per_key]
    45    import apache_beam as beam
    46  
    47    with beam.Pipeline() as pipeline:
    48      samples_per_key = (
    49          pipeline
    50          | 'Create produce' >> beam.Create([
    51              ('spring', '🍓'),
    52              ('spring', '🥕'),
    53              ('spring', '🍆'),
    54              ('spring', '🍅'),
    55              ('summer', '🥕'),
    56              ('summer', '🍅'),
    57              ('summer', '🌽'),
    58              ('fall', '🥕'),
    59              ('fall', '🍅'),
    60              ('winter', '🍆'),
    61          ])
    62          | 'Samples per key' >> beam.combiners.Sample.FixedSizePerKey(3)
    63          | beam.Map(print))
    64      # [END sample_fixed_size_per_key]
    65      if test:
    66        test(samples_per_key)