Preprocessing using Dataflow

In [1]:

    

pip install --user apache-beam[gcp]


    

In [ ]:

    

import apache_beam as beam
print(beam.__version__)


    

In [ ]:

    

# change these to try this notebook out
BUCKET = 'cloud-training-demos-ml'
PROJECT = 'cloud-training-demos'
REGION = 'us-central1'


    

In [ ]:

    

import os
os.environ['BUCKET'] = BUCKET
os.environ['PROJECT'] = PROJECT
os.environ['REGION'] = REGION


    

In [ ]:

    

%%bash
if ! gsutil ls | grep -q gs://${BUCKET}/; then
  gsutil mb -l ${REGION} gs://${BUCKET}
fi


    

In [ ]:

    

import datetime, os

def to_csv(rowdict):
  import hashlib
  import copy

  # TODO #1:
  # Pull columns from BQ and create line(s) of CSV input
  CSV_COLUMNS = None
    
  # Create synthetic data where we assume that no ultrasound has been performed
  # and so we don't know sex of the baby. Let's assume that we can tell the difference
  # between single and multiple, but that the errors rates in determining exact number
  # is difficult in the absence of an ultrasound.
  no_ultrasound = copy.deepcopy(rowdict)
  w_ultrasound = copy.deepcopy(rowdict)

  no_ultrasound['is_male'] = 'Unknown'
  if rowdict['plurality'] > 1:
    no_ultrasound['plurality'] = 'Multiple(2+)'
  else:
    no_ultrasound['plurality'] = 'Single(1)'

  # Change the plurality column to strings
  w_ultrasound['plurality'] = ['Single(1)', 'Twins(2)', 'Triplets(3)', 'Quadruplets(4)', 'Quintuplets(5)'][rowdict['plurality'] - 1]

  # Write out two rows for each input row, one with ultrasound and one without
  for result in [no_ultrasound, w_ultrasound]:
    data = ','.join([str(result[k]) if k in result else 'None' for k in CSV_COLUMNS])
    key = hashlib.sha224(data.encode('utf-8')).hexdigest()  # hash the columns to form a key
    yield str('{},{}'.format(data, key))
    
def preprocess(in_test_mode):
  import shutil, os, subprocess
  job_name = 'preprocess-babyweight-features' + '-' + datetime.datetime.now().strftime('%y%m%d-%H%M%S')

  if in_test_mode:
      print('Launching local job ... hang on')
      OUTPUT_DIR = './preproc'
      shutil.rmtree(OUTPUT_DIR, ignore_errors=True)
      os.makedirs(OUTPUT_DIR)
  else:
      print('Launching Dataflow job {} ... hang on'.format(job_name))
      OUTPUT_DIR = 'gs://{0}/babyweight/preproc/'.format(BUCKET)
      try:
        subprocess.check_call('gsutil -m rm -r {}'.format(OUTPUT_DIR).split())
      except:
        pass

  options = {
      'staging_location': os.path.join(OUTPUT_DIR, 'tmp', 'staging'),
      'temp_location': os.path.join(OUTPUT_DIR, 'tmp'),
      'job_name': job_name,
      'project': PROJECT,
      'region': REGION,
      'teardown_policy': 'TEARDOWN_ALWAYS',
      'no_save_main_session': True,
      'num_workers': 4,
      'max_num_workers': 5
  }
  opts = beam.pipeline.PipelineOptions(flags = [], **options)
  if in_test_mode:
      RUNNER = 'DirectRunner'
  else:
      RUNNER = 'DataflowRunner'
  p = beam.Pipeline(RUNNER, options = opts)
    
  query = """
SELECT
  weight_pounds,
  is_male,
  mother_age,
  plurality,
  gestation_weeks,
  FARM_FINGERPRINT(CONCAT(CAST(YEAR AS STRING), CAST(month AS STRING))) AS hashmonth
FROM
  publicdata.samples.natality
WHERE year > 2000
AND weight_pounds > 0
AND mother_age > 0
AND plurality > 0
AND gestation_weeks > 0
AND month > 0
    """

  if in_test_mode:
    query = query + ' LIMIT 100' 

  for step in ['train', 'eval']:
    if step == 'train':
      selquery = 'SELECT * FROM ({}) WHERE ABS(MOD(hashmonth, 4)) < 3'.format(query)
    else:
      selquery = 'SELECT * FROM ({}) WHERE ABS(MOD(hashmonth, 4)) = 3'.format(query)

    (p 
     ## TODO Task #2: Modify the Apache Beam pipeline such that the first part of the pipe reads the data from BigQuery
     | '{}_read'.format(step) >> None 
     | '{}_csv'.format(step) >> beam.FlatMap(to_csv)
     | '{}_out'.format(step) >> beam.io.Write(beam.io.WriteToText(os.path.join(OUTPUT_DIR, '{}.csv'.format(step))))
    )

  job = p.run()
  if in_test_mode:
    job.wait_until_finish()
    print("Done!")
 
# TODO  Task #3: Once you have verified that the files produced locally are correct, change in_test_mode to False
#               to execute this in Cloud Dataflow
preprocess(in_test_mode = True)


    

In [ ]:

    

%%bash
gsutil ls gs://${BUCKET}/babyweight/preproc/*-00000*