github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/wordcount_with_metrics.py (about)

     1  #
     2  # Licensed to the Apache Software Foundation (ASF) under one or more
     3  # contributor license agreements.  See the NOTICE file distributed with
     4  # this work for additional information regarding copyright ownership.
     5  # The ASF licenses this file to You under the Apache License, Version 2.0
     6  # (the "License"); you may not use this file except in compliance with
     7  # the License.  You may obtain a copy of the License at
     8  #
     9  #    http://www.apache.org/licenses/LICENSE-2.0
    10  #
    11  # Unless required by applicable law or agreed to in writing, software
    12  # distributed under the License is distributed on an "AS IS" BASIS,
    13  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    14  # See the License for the specific language governing permissions and
    15  # limitations under the License.
    16  #
    17  
    18  """A word-counting workflow."""
    19  
    20  # pytype: skip-file
    21  
    22  # beam-playground:
    23  #   name: WordCountWithMetrics
    24  #   description: A word-counting workflow with metrics.
    25  #   multifile: false
    26  #   default_example: true
    27  #   pipeline_options: --output output.txt
    28  #   context_line: 48
    29  #   categories:
    30  #     - Combiners
    31  #     - Options
    32  #     - Metrics
    33  #     - Quickstart
    34  #   complexity: MEDIUM
    35  #   tags:
    36  #     - count
    37  #     - metrics
    38  #     - strings
    39  
    40  import argparse
    41  import logging
    42  import re
    43  
    44  import apache_beam as beam
    45  from apache_beam.io import ReadFromText
    46  from apache_beam.io import WriteToText
    47  from apache_beam.metrics import Metrics
    48  from apache_beam.metrics.metric import MetricsFilter
    49  from apache_beam.options.pipeline_options import PipelineOptions
    50  from apache_beam.options.pipeline_options import SetupOptions
    51  
    52  
    53  class WordExtractingDoFn(beam.DoFn):
    54    """Parse each line of input text into words."""
    55    def __init__(self):
    56      # TODO(BEAM-6158): Revert the workaround once we can pickle super() on py3.
    57      # super().__init__()
    58      beam.DoFn.__init__(self)
    59      self.words_counter = Metrics.counter(self.__class__, 'words')
    60      self.word_lengths_counter = Metrics.counter(self.__class__, 'word_lengths')
    61      self.word_lengths_dist = Metrics.distribution(
    62          self.__class__, 'word_len_dist')
    63      self.empty_line_counter = Metrics.counter(self.__class__, 'empty_lines')
    64  
    65    def process(self, element):
    66      """Returns an iterator over the words of this element.
    67  
    68      The element is a line of text.  If the line is blank, note that, too.
    69  
    70      Args:
    71        element: the element being processed
    72  
    73      Returns:
    74        The processed element.
    75      """
    76      text_line = element.strip()
    77      if not text_line:
    78        self.empty_line_counter.inc(1)
    79      words = re.findall(r'[\w\']+', text_line, re.UNICODE)
    80      for w in words:
    81        self.words_counter.inc()
    82        self.word_lengths_counter.inc(len(w))
    83        self.word_lengths_dist.update(len(w))
    84      return words
    85  
    86  
    87  def main(argv=None, save_main_session=True):
    88    """Main entry point; defines and runs the wordcount pipeline."""
    89    parser = argparse.ArgumentParser()
    90    parser.add_argument(
    91        '--input',
    92        dest='input',
    93        default='gs://dataflow-samples/shakespeare/kinglear.txt',
    94        help='Input file to process.')
    95    parser.add_argument(
    96        '--output',
    97        dest='output',
    98        required=True,
    99        help='Output file to write results to.')
   100    known_args, pipeline_args = parser.parse_known_args(argv)
   101  
   102    # We use the save_main_session option because one or more DoFn's in this
   103    # workflow rely on global context (e.g., a module imported at module level).
   104    pipeline_options = PipelineOptions(pipeline_args)
   105    pipeline_options.view_as(SetupOptions).save_main_session = save_main_session
   106    p = beam.Pipeline(options=pipeline_options)
   107  
   108    # Read the text file[pattern] into a PCollection.
   109    lines = p | 'read' >> ReadFromText(known_args.input)
   110  
   111    # Count the occurrences of each word.
   112    def count_ones(word_ones):
   113      (word, ones) = word_ones
   114      return (word, sum(ones))
   115  
   116    counts = (
   117        lines
   118        | 'split' >> (beam.ParDo(WordExtractingDoFn()).with_output_types(str))
   119        | 'pair_with_one' >> beam.Map(lambda x: (x, 1))
   120        | 'group' >> beam.GroupByKey()
   121        | 'count' >> beam.Map(count_ones))
   122  
   123    # Format the counts into a PCollection of strings.
   124    def format_result(word_count):
   125      (word, count) = word_count
   126      return '%s: %d' % (word, count)
   127  
   128    output = counts | 'format' >> beam.Map(format_result)
   129  
   130    # Write the output using a "Write" transform that has side effects.
   131    # pylint: disable=expression-not-assigned
   132    output | 'write' >> WriteToText(known_args.output)
   133  
   134    result = p.run()
   135    result.wait_until_finish()
   136  
   137    # Do not query metrics when creating a template which doesn't run
   138    if (not hasattr(result, 'has_job')  # direct runner
   139        or result.has_job):  # not just a template creation
   140      empty_lines_filter = MetricsFilter().with_name('empty_lines')
   141      query_result = result.metrics().query(empty_lines_filter)
   142      if query_result['counters']:
   143        empty_lines_counter = query_result['counters'][0]
   144        logging.info('number of empty lines: %d', empty_lines_counter.result)
   145  
   146      word_lengths_filter = MetricsFilter().with_name('word_len_dist')
   147      query_result = result.metrics().query(word_lengths_filter)
   148      if query_result['distributions']:
   149        word_lengths_dist = query_result['distributions'][0]
   150        logging.info('average word length: %d', word_lengths_dist.result.mean)
   151  
   152  
   153  if __name__ == '__main__':
   154    logging.getLogger().setLevel(logging.INFO)
   155    main()