github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/snippets/transforms/aggregation/count.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 count_globally(test=None):
    23    # [START count_globally]
    24    import apache_beam as beam
    25  
    26    with beam.Pipeline() as pipeline:
    27      total_elements = (
    28          pipeline
    29          | 'Create plants' >> beam.Create(
    30              ['🍓', '🥕', '🥕', '🥕', '🍆', '🍆', '🍅', '🍅', '🍅', '🌽'])
    31          | 'Count all elements' >> beam.combiners.Count.Globally()
    32          | beam.Map(print))
    33      # [END count_globally]
    34      if test:
    35        test(total_elements)
    36  
    37  
    38  def count_per_key(test=None):
    39    # [START count_per_key]
    40    import apache_beam as beam
    41  
    42    with beam.Pipeline() as pipeline:
    43      total_elements_per_keys = (
    44          pipeline
    45          | 'Create plants' >> beam.Create([
    46              ('spring', '🍓'),
    47              ('spring', '🥕'),
    48              ('summer', '🥕'),
    49              ('fall', '🥕'),
    50              ('spring', '🍆'),
    51              ('winter', '🍆'),
    52              ('spring', '🍅'),
    53              ('summer', '🍅'),
    54              ('fall', '🍅'),
    55              ('summer', '🌽'),
    56          ])
    57          | 'Count elements per key' >> beam.combiners.Count.PerKey()
    58          | beam.Map(print))
    59      # [END count_per_key]
    60      if test:
    61        test(total_elements_per_keys)
    62  
    63  
    64  def count_per_element(test=None):
    65    # [START count_per_element]
    66    import apache_beam as beam
    67  
    68    with beam.Pipeline() as pipeline:
    69      total_unique_elements = (
    70          pipeline
    71          | 'Create produce' >> beam.Create(
    72              ['🍓', '🥕', '🥕', '🥕', '🍆', '🍆', '🍅', '🍅', '🍅', '🌽'])
    73          | 'Count unique elements' >> beam.combiners.Count.PerElement()
    74          | beam.Map(print))
    75      # [END count_per_element]
    76      if test:
    77        test(total_unique_elements)