def run():
import time
gcs_path = "gs://marcin-playground/dataflow"
pipeline = beam.Pipeline(runner="DataflowRunner",
argv=[
"--project", "project-name",
"--staging_location",
("%s/staging_location" % gcs_path),
"--temp_location",
("%s/temp" % gcs_path), "--output",
("%s/output" % gcs_path), "--setup_file",
"./setup.py"
])
(pipeline
| "Load" >> ReadFromText("gs://marcin-playground/books/*.txt")
| "Count Words" >> CountWordsTransform()
| "FormatOutput" >>
beam.Map(lambda (word, count): "{0}: {1}".format(word, count))
| "Save" >> WriteToText("{0}/output/wordcount{1}".format(
gcs_path, int(time.time()))))
pipeline.run()
def run(p, input_file, output_file):
#pylint: disable=expression-not-assigned
(
p
# Read the lines from a text file.
| 'Read' >> ReadFromText(input_file)
# Split the line into individual words.
| 'Split' >> beam.FlatMap(lambda line: re.split(r'\W+', line))
# Map each word to an instance of MyRow.
| 'ToRow' >> beam.Map(MyRow).with_output_types(MyRow)
# SqlTransform yields a PCollection containing elements with attributes
# based on the output of the query.
| 'Sql!!' >> SqlTransform(
"""
SELECT
word as key,
COUNT(*) as `count`
FROM PCOLLECTION
GROUP BY word""")
| 'Format' >> beam.Map(lambda row: '{}: {}'.format(row.key, row.count))
| 'Write' >> WriteToText(output_file))
def run(argv=None):
"""Main entry point; defines and runs the tfidf pipeline."""
parser = argparse.ArgumentParser()
parser.add_argument('--uris', required=True, help='URIs to process.')
parser.add_argument('--output',
required=True,
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(argv)
# We use the save_main_session option because one or more DoFn's in this
# workflow rely on global context (e.g., a module imported at module level).
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
with beam.Pipeline(options=pipeline_options) as p:
# Read documents specified by the uris command line option.
pcoll = read_documents(p, glob.glob(known_args.uris))
# Compute TF-IDF information for each word.
output = pcoll | TfIdf()
# Write the output using a "Write" transform that has side effects.
# pylint: disable=expression-not-assigned
output | 'write' >> WriteToText(known_args.output)
def run(argv=None):
parser = argparse.ArgumentParser()
parser.add_argument('--input',
dest='input',
required=True,
help='Input file to process.')
parser.add_argument('--output',
dest='output',
required=True,
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(argv)
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
with beam.Pipeline(options=pipeline_options) as p:
lines = p | 'ReadFromText' >> ReadFromText(known_args.input)
results = (lines
| 'Split' >> beam.Map(split)
| 'Group' >> beam.GroupByKey()
| 'FormatResult' >> beam.Map(format_result))
results | 'WriteToText' >> WriteToText(known_args.output)
def run():
# set up location
PROJECT_ID = 'trim-cistern-288221'
BUCKET = 'gs://bhnk-milestone1-data'
DIR_PATH = BUCKET + '/output/' + datetime.datetime.now().strftime('%Y_%m_%d_%H_%M_%S') + '/'
# use DataflowRunner instead of DirectRunner
options = PipelineOptions(
flags=None,
runner='DataflowRunner',
project=PROJECT_ID,
job_name='kagglegenre',
temp_location=BUCKET + '/temp',
region='us-central1')
p = beam.pipeline.Pipeline(options=options)
# retrieve the data from imdb_refined dataset and save this information (location)
sql = 'SELECT * FROM kaggle_refined.Title_genre'
bq_source = ReadFromBigQuery(query=sql, use_standard_sql=True, gcs_location=BUCKET)
# use the previously saved information (location) and read from BigQuery
# query results is now input P collection
query_results = p | 'Read from BQ' >> beam.io.Read(bq_source)
# Use ParDo to call function on query results
out_pcoll = query_results | 'Split genres' >> beam.ParDo(SplitGenre())
out_pcoll | 'Log output' >> WriteToText(DIR_PATH + 'output.txt')
dataset_id = 'kaggle_refined'
table_id = PROJECT_ID + ':' + dataset_id + '.' + 'Title_genre_Dataflow'
schema_id = 'Title:STRING,Genre:STRING'
# write to BigQuery using the location set above
out_pcoll | 'Write to BQ' >> WriteToBigQuery(table=table_id, schema=schema_id, custom_gcs_temp_location=BUCKET)
# run and display results after everything is finished
result = p.run()
result.wait_until_finish()
def run(argv=None):
parser = argparse.ArgumentParser()
parser.add_argument(
'--input',
dest='input',
default='../data/spikey_sales_weekly.txt',
# required=True,
help='Input File to Process')
parser.add_argument(
'--output',
dest='output',
default='../output/products',
# required=True,
help='output processed file')
known_args, pipeline_Args = parser.parse_known_args(argv)
pipeline_option = PipelineOptions(argv)
pipeline_option.view_as(SetupOptions).save_main_session = True
logging.getLogger().setLevel(logging.INFO)
with beam.Pipeline(options=pipeline_option) as p:
# read input file
items = p | ReadFromText(known_args.input)
logging.info("Print the items %s", items)
split_item_result = (
items
| 'Split Result' >> beam.ParDo(
SplitItemBasedOnSalesFn()).with_outputs(
SplitItemBasedOnSalesFn.OUTPUT_TAG_TOP_SELLER,
SplitItemBasedOnSalesFn.OUTPUT_TAG_POOR_SELLER))
top_seller = split_item_result[
SplitItemBasedOnSalesFn.OUTPUT_TAG_TOP_SELLER]
poor_seller = split_item_result[
SplitItemBasedOnSalesFn.OUTPUT_TAG_POOR_SELLER]
# (top_seller | WriteToText(known_args.output + '_top_seller'))
(poor_seller | WriteToText(known_args.output + '_poor_seller'))
def run(argv=None):
"""Run the workflow."""
parser = argparse.ArgumentParser()
parser.add_argument('--output')
parser.add_argument('--ignore_corpus', default='')
parser.add_argument('--ignore_word', default='')
parser.add_argument('--num_groups')
known_args, pipeline_args = parser.parse_known_args(argv)
# We use the save_main_session option because one or more DoFn's in this
# workflow rely on global context (e.g., a module imported at module level).
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
with beam.Pipeline(options=pipeline_options) as p:
group_ids = []
for i in range(0, int(known_args.num_groups)):
group_ids.append('id' + str(i))
query_corpus = 'select UNIQUE(corpus) from publicdata:samples.shakespeare'
query_word = 'select UNIQUE(word) from publicdata:samples.shakespeare'
ignore_corpus = known_args.ignore_corpus
ignore_word = known_args.ignore_word
pcoll_corpus = p | 'read corpus' >> beam.io.ReadFromBigQuery(
query=query_corpus)
pcoll_word = p | 'read_words' >> beam.io.ReadFromBigQuery(
query=query_word)
pcoll_ignore_corpus = p | 'create_ignore_corpus' >> beam.Create(
[ignore_corpus])
pcoll_ignore_word = p | 'create_ignore_word' >> beam.Create(
[ignore_word])
pcoll_group_ids = p | 'create groups' >> beam.Create(group_ids)
pcoll_groups = create_groups(pcoll_group_ids, pcoll_corpus, pcoll_word,
pcoll_ignore_corpus, pcoll_ignore_word)
# pylint:disable=expression-not-assigned
pcoll_groups | WriteToText(known_args.output)
def process_entity(self, entity_name, pk):
with beam.Pipeline(options=self.pipeline_options) as p:
# First set up a stream for the data
data = read_file(
p,
entity_name,
self.get_staging('public.{0}'.format(entity_name)) + '*',
pk)
index = None
try:
# Also set up a stream for the index
index = read_file(
p,
'{0}index'.format(entity_name),
self.get_source_index('entity_{0}*'.format(entity_name)),
pk)
except IOError:
logging.info("Could not open index, maybe doesn't exist")
# create an empty pcollection, so we can at least run
index = p | beam.Create([])
# Generate business keys, checksum, dv_source, load_dtm
preproc_data = data | 'preprocess_' + entity_name >> \
beam.Map(add_cksum)
# Group with index to be able to identify new, updated, deleted
merge = ({'data': preproc_data, 'index': index}) | \
'grouped_by_' + pk >> beam.CoGroupByKey()
# Extract the modified data out of the records
extract = merge \
| 'filter_' + entity_name >> beam.Filter(unchanged_rows) \
| 'extract_' + entity_name >> beam.Map(extract_data)
# Write them out to disk in staging
extract | 'Write_' + entity_name >> \
WriteToText(
self.get_psa_location('public.{0}'.format(entity_name)),
coder=JsonCoder())
def run(argv=None, save_main_session=True):
"""Main entry point; defines and runs the wordcount pipeline."""
parser = argparse.ArgumentParser()
parser.add_argument('--input',
dest='input',
default='./kinglear.txt',
help='Input file to process.')
parser.add_argument('--output',
dest='output',
required=True,
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(argv)
# We use the save_main_session option because one or more DoFn's in this
# workflow rely on global context (e.g., a module imported at module level).
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(
SetupOptions).save_main_session = save_main_session
# The pipeline will be run on exiting the with block.
with beam.Pipeline(options=pipeline_options) as p:
# Read the text file[pattern] into a PCollection.
lines = p | 'Read' >> ReadFromText(known_args.input)
counts = (lines
| 'Split' >> (beam.FlatMap(lambda x: re.findall(
r'[A-Za-z\]+')).with_output_types(unicode))
| 'PairWIthOne' >> beam.Map(lambda x: (x, 1))
| 'GroupAndSum' >> beam.CombinePerKey(sum))
# Format the counts into a PCollection of strings.
def format_result(word, count):
return '%s: %d' % (word, count)
output = counts | 'Format' >> beam.MapTuple(format_result)
# Write the output using a "Write" transform that has side effects.
# pylint: disable=expression-not-assigned
output | 'Write' >> WriteToText(known_args.output)
def run(argv=None, save_main_session=True):
"""Main entry point; defines and runs the wordcount pipeline."""
parser = argparse.ArgumentParser()
parser.add_argument(
'--input',
dest='input',
default='gs://dataflow-samples/data/kinglear.txt',
help='Input file to process.')
parser.add_argument(
'--output',
dest='output',
# CHANGE 1/6: The Google Cloud Storage path is required
# for outputting the results.
default='gs://YOUR_OUTPUT_BUCKET/AND_OUTPUT_PREFIX',
help='Output file to write results to.')
parser.add_argument(
'--pid',
dest='pid',
help='project id')
parser.add_argument(
'--mbucket',
dest='mbucket',
help='model bucket name')
known_args, pipeline_args = parser.parse_known_args(argv)
# We use the save_main_session option because one or more DoFn's in this
# workflow rely on global context (e.g., a module imported at module level).
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = save_main_session
# The pipeline will be run on exiting the with block.
with beam.Pipeline(options=pipeline_options) as p:
# Read the text file[pattern] into a PCollection.
prediction_data = (p | 'CreatePCollection' >> beam.Create([known_args.input])
| 'ReadCSVFle' >> beam.FlatMap(get_csv_reader))
output = (prediction_data | 'Predict' >> beam.ParDo(MyPredictDoFn(project_id=known_args.pid,
bucket_name=known_args.mbucket)))
output | 'WritePR' >> WriteToText(known_args.output)
def run():
PROJECT_ID = 'starry-center-266501' # change to your project id # creating pipeline through direct runner
# Project ID is required when using the BQ source
options = {
'project': PROJECT_ID
}
opts = beam.pipeline.PipelineOptions(flags=[], **options)
# Create beam pipeline using local runner
p = beam.Pipeline('DirectRunner', options=opts)
sql = 'SELECT writers, tConst FROM imdb_modeled.Writes limit 100' # passing a query. Shouldn't process more than 1000 records w DR
# directors is an array of strings, tConst is a string
bq_source = beam.io.BigQuerySource(query=sql, use_standard_sql=True) # direct runner is not running in parallel on several workers. DR is local
query_results = p | 'Read from BigQuery' >> beam.io.Read(bq_source) # read results and assign them to a new p-collection
# apply ParDo to split the directors titles
# call pardo, pipe query results to pardo
split_directors_pcoll = query_results | 'Return title: writer i dictonaries' >> beam.ParDo(SplitWritersFn())
# write PCollection to log file
split_directors_pcoll | 'Write log 1' >> WriteToText('formatted_titles_pcoll.txt')
dataset_id = 'imdb_modeled'
table_id = 'Writes_Beam'
schema_id = 'writer:STRING, tConst:STRING'
# write PCollection to new BQ table
split_directors_pcoll | 'Write BQ table' >> beam.io.WriteToBigQuery(dataset=dataset_id,
table=table_id,
schema=schema_id,
project=PROJECT_ID,
create_disposition=beam.io.BigQueryDisposition.CREATE_IF_NEEDED,
write_disposition=beam.io.BigQueryDisposition.WRITE_TRUNCATE,
batch_size=int(100))
result = p.run()
result.wait_until_finish()
def run():
PROJECT_ID = 'acquired-rarity-288205'
BUCKET = 'gs://ykdb_beam_us'
DIR_PATH = BUCKET + '/output/' + datetime.datetime.now().strftime(
'%Y_%m_%d_%H_%M_%S') + '/'
options = PipelineOptions(flags=None,
runner='DataflowRunner',
project=PROJECT_ID,
job_name='application',
temp_location=BUCKET + '/temp',
region='us-central1')
p = beam.pipeline.Pipeline(options=options)
# ***************************************** REMOVE DUPLICATES ****************************************************
sql = "SELECT FARM_FINGERPRINT(TO_JSON_STRING(t)) AS case_id, * FROM (SELECT emp.employer_id, CASE_NUMBER, CASE_STATUS, CASE_SUBMITTED, DECESION_DATE AS DECISION_DATE, VISA_CLASS FROM (SELECT *, COUNT(*) AS count FROM H_1B_refined.Application GROUP BY CASE_NUMBER, CASE_STATUS, CASE_SUBMITTED, DECESION_DATE, VISA_CLASS, employer_name, employer_city HAVING count = 1) AS app JOIN H_1B_refined.Employer_Dataflow AS emp ON emp.employer_name = app.employer_name AND emp.employer_city = app.employer_city) AS t"
bq_source = ReadFromBigQuery(query=sql,
use_standard_sql=True,
gcs_location=BUCKET)
query_results = p | 'Read from BQ' >> beam.io.Read(bq_source)
out_pcoll = query_results | 'Application Transfromation' >> beam.ParDo(
NoDuplicates())
out_pcoll | 'Log output' >> WriteToText(DIR_PATH +
'output_appplication.txt')
# ***************************************** INSERT INTO BQ ****************************************************
dataset_id = 'H_1B_refined'
table_id = PROJECT_ID + ':' + dataset_id + '.' + 'Application_Dataflow'
schema_id = 'case_id:INTEGER, employer_id:INTEGER, CASE_NUMBER:STRING, CASE_STATUS:STRING, CASE_SUBMITTED:DATE, DECISION_DATE:DATE, VISA_CLASS:STRING'
out_pcoll | 'Write to BQ' >> WriteToBigQuery(
table=table_id, schema=schema_id, custom_gcs_temp_location=BUCKET)
result = p.run()
result.wait_until_finish()
def run(argv=None):
"""Main entry point; defines and runs the wordcount pipeline."""
parser = argparse.ArgumentParser()
parser.add_argument(
'--input',
dest='input',
default='gs://dataflow-samples/shakespeare/kinglear.txt',
help='Input file to process.')
parser.add_argument('--output',
dest='output',
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(argv)
# We use the save_main_session option because one or more DoFn's in this
# workflow rely on global context (e.g., a module imported at module level).
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
with beam.Pipeline(options=pipeline_options) as p:
# Read the text file[pattern] into a PCollection.
lines = p | ReadFromText(known_args.input)
# Count the occurrences of each word.
counts = (lines
| 'Split' >> (beam.FlatMap(lambda x: re.findall(
r'[A-Za-z\']+', x)).with_output_types(unicode))
| 'PairWithOne' >> beam.Map(lambda x: (x, 1))
| 'GroupAndSum' >> beam.CombinePerKey(sum))
# Format the counts into a PCollection of strings.
def format_result(word_count):
(word, count) = word_count
return '%s: %s' % (word, count)
output = counts | 'Format' >> beam.Map(format_result)
# Write the output using a "Write" transform that has side effects.
# pylint: disable=expression-not-assigned
output | WriteToText(known_args.output, shard_name_template='')
def run(argv=None):
"""Main entry point; defines and runs the wordcount pipeline."""
parser = argparse.ArgumentParser()
parser.add_argument('--input',
dest='input',
default='gs://dataflow-samples/shakespeare/kinglear.txt',
help='Input file to process.')
parser.add_argument('--output',
dest='output',
required=True,
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(argv)
# We use the save_main_session option because one or more DoFn's in this
# workflow rely on global context (e.g., a module imported at module level).
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
p = beam.Pipeline(options=pipeline_options)
# Read the text file[pattern] into a PCollection.
lines = p | 'read' >> ReadFromText(known_args.input)
# Count the occurrences of each word.
counts = (lines
| 'split' >> (beam.ParDo(WordExtractingDoFn())
.with_output_types(unicode))
| 'pair_with_one' >> beam.Map(lambda x: (x, 1))
| 'group' >> beam.GroupByKey()
| 'count' >> beam.Map(lambda (word, ones): (word, sum(ones))))
# Format the counts into a PCollection of strings.
output = counts | 'format' >> beam.Map(lambda (word, c): '%s: %s' % (word, c))
# Write the output using a "Write" transform that has side effects.
# pylint: disable=expression-not-assigned
output | 'write' >> WriteToText(known_args.output)
# Actually run the pipeline (all operations above are deferred).
result = p.run()
result.wait_until_finish()
def run(argv=None):
parser = argparse.ArgumentParser()
parser.add_argument('--input',
dest='input',
default='gs://loganalysis/error_log.txt',
help='Input file to process.')
parser.add_argument('--output',
dest='output',
default='gs://loganalysis/output',
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(argv)
pipeline_args.extend([
'--runner=DirectRunner',
'--project=springmldemoproject',
'--staging_location=gs://loganalysis/staging',
'--temp_location=gs://loganalysis/temp',
'--job_name=log-job',
])
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
with beam.Pipeline(options=pipeline_options) as p:
lines = p | ReadFromText(known_args.input)
counts = (
lines
| 'window' >> beam.WindowInto(window.GlobalWindows())
| 'Split' >> (beam.FlatMap(lambda x: re.findall(
r'((?:(?:[0-1][0-9])|(?:[2][0-3])|(?:[0-9])):(?:[0-5][0-9])(?::[0-5][0-9])?(?:\\s?(?:am|AM|pm|PM))?)',
x)).with_output_types(unicode))
| 'PairWithOne' >> beam.Map(lambda x: (x, 1))
| 'GroupAndSum' >> beam.CombinePerKey(sum))
def format_result(time_count):
(time, count) = time_count
return '%s: %s' % (time, count)
output = counts | 'Format' >> beam.Map(format_result)
output | WriteToText(known_args.output)
def run():
PROJECT_ID = 'acquired-rarity-288205'
BUCKET = 'gs://ykdb_beam_us'
DIR_PATH = BUCKET + '/output/' + datetime.datetime.now().strftime(
'%Y_%m_%d_%H_%M_%S') + '/'
options = PipelineOptions(flags=None,
runner='DataflowRunner',
project=PROJECT_ID,
job_name='ownership',
temp_location=BUCKET + '/temp',
region='us-central1')
p = beam.pipeline.Pipeline(options=options)
# ***************************************** REMOVE DUPLICATES ****************************************************
sql = "SELECT FARM_FINGERPRINT(TO_JSON_STRING(t)) as ownership_id, * FROM (SELECT * FROM (SELECT *, COUNT(*) AS count FROM H_1B_refined.Ownership GROUP BY occ_code, occ_title, ownership, naics_title, grp, tot_emp, emp_prse, h_mean, a_mean, mean_prse, a_pct10, a_pct25, a_median, a_pct75, a_pct90 HAVING count = 1)) as t"
bq_source = ReadFromBigQuery(query=sql,
use_standard_sql=True,
gcs_location=BUCKET)
query_results = p | 'Read from BQ' >> beam.io.Read(bq_source)
out_pcoll = query_results | 'Remove Dups Ownership' >> beam.ParDo(
NoDuplicates())
out_pcoll | 'Log output' >> WriteToText(DIR_PATH + 'output_ownership.txt')
# ***************************************** INSERT INTO BQ ****************************************************
dataset_id = 'H_1B_refined'
table_id = PROJECT_ID + ':' + dataset_id + '.' + 'Ownership_Dataflow'
schema_id = 'ownership_id:INTEGER, occ_code:STRING, occ_title:STRING, ownership:STRING, naics_title:STRING, grp:STRING, tot_emp:INTEGER, emp_prse:FLOAT, h_mean:FLOAT, a_mean:INTEGER, mean_prse:FLOAT, a_pct10:INTEGER, a_pct25:INTEGER, a_median:INTEGER, a_pct75:INTEGER, a_pct90:INTEGER'
out_pcoll | 'Write to BQ' >> WriteToBigQuery(
table=table_id, schema=schema_id, custom_gcs_temp_location=BUCKET)
result = p.run()
result.wait_until_finish()
def run_pipeline(source, target):
header = get_header(source)
fields = header.split(CSV_DELIMITER)
(bq_schema, schema) = get_schema(target)
input_path = 'gs://dotz-hiring-datalake/raw/{}.csv'.format(source)
output_path = 'gs://dotz-hiring-datalake/processed/{}.json/part'.format(
target)
pipeline_args = [
'--job_name={}-{}'.format(target,
str(time.time()).replace('.', '-')),
'--input={}'.format(input_path), '--output={}'.format(output_path)
]
pipeline_args.extend(BASE_PIPELINE_ARGS)
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
with beam.Pipeline(options=pipeline_options) as pipeline:
lines = pipeline | ReadFromText(input_path)
# not so bright way to remove a CSV header
lines = lines | 'RemoveHeader' >> beam.Filter(
lambda line: line != header)
objs = lines | 'CSV2JSON' >> beam.Map(csv2json(fields))
proc_objs = objs | 'ProcessJSONs' >> beam.Map(process(schema))
filtered_proc_objs = proc_objs | 'FilterEmpties' >> beam.Filter(
lambda x: x)
dumped_objs = filtered_proc_objs | 'DumpJSONs' >> beam.Map(json.dumps)
dumped_objs | WriteToText(output_path)
filtered_proc_objs | WriteToBigQuery(
'dotz-hiring:tubulation.{}'.format(target),
write_disposition=BigQueryDisposition.WRITE_TRUNCATE,
create_disposition=BigQueryDisposition.CREATE_NEVER)
def run():
PROJECT_ID = 'acquired-rarity-288205'
BUCKET = 'gs://ykdb_beam_us'
DIR_PATH = BUCKET + '/output/' + datetime.datetime.now().strftime(
'%Y_%m_%d_%H_%M_%S') + '/'
options = PipelineOptions(flags=None,
runner='DataflowRunner',
project=PROJECT_ID,
job_name='employer',
temp_location=BUCKET + '/temp',
region='us-central1')
p = beam.pipeline.Pipeline(options=options)
# ***************************************** REMOVE DUPLICATES ****************************************************
sql = "SELECT FARM_FINGERPRINT(TO_JSON_STRING(t)) AS employer_id, * FROM (SELECT employer_name, employer_address, employer_city, employer_state, employer_postal_code, employer_country, employer_province, h_1b_dependent, willful_violator FROM (SELECT *, COUNT(*) AS count FROM H_1B_refined.Employer GROUP BY employer_name, employer_address, employer_city, employer_state, employer_postal_code, employer_country, employer_province, h_1b_dependent, willful_violator HAVING count = 1)) AS t"
bq_source = ReadFromBigQuery(query=sql,
use_standard_sql=True,
gcs_location=BUCKET)
query_results = p | 'Read from BQ' >> beam.io.Read(bq_source)
out_pcoll = query_results | 'Remove Dups Employer' >> beam.ParDo(
NoDuplicates())
out_pcoll | 'Log output' >> WriteToText(DIR_PATH + 'output_employer.txt')
# ***************************************** INSERT INTO BQ ****************************************************
dataset_id = 'H_1B_refined'
table_id = PROJECT_ID + ':' + dataset_id + '.' + 'Employer_Dataflow'
schema_id = 'employer_id:INTEGER, employer_name:STRING, employer_address:STRING, employer_city:STRING, employer_state:STRING, employer_postal_code:STRING, employer_country:STRING, employer_province:STRING, h_1b_dependent:BOOLEAN, willful_violator:BOOLEAN'
out_pcoll | 'Write to BQ' >> WriteToBigQuery(
table=table_id, schema=schema_id, custom_gcs_temp_location=BUCKET)
result = p.run()
result.wait_until_finish()
def run(argv=None, save_main_session=True):
parser = argparse.ArgumentParser()
parser.add_argument(
'--input',
dest='input',
default='gs://dataflow-samples/shakespeare/kinglear.txt',
help='Input file to process.')
parser.add_argument(
'--output',
dest='output',
required=True,
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(argv)
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = save_main_session
with beam.Pipeline(options=pipeline_options) as p:
# Read the text file
lines = p | 'Read' >> ReadFromText(known_args.input)
counts = (
lines
| 'Split' >>
(beam.ParDo(WordExtractingDoFn()).with_output_types(unicode))
| 'PairWIthOne' >> beam.Map(lambda x: (x, 1))
| 'GroupAndSum' >> beam.CombinePerKey(sum))
def format_result(word, count):
return '%s: %d' % (word, count)
output = counts | 'Format' >> beam.MapTuple(format_result)
#Write the word count in output
output | 'Write' >> WriteToText(known_args.output)
def main():
options = PipelineOptions()
options.view_as(SetupOptions).save_main_session = True
opt = options.view_as(_Options)
inputs = opt.inputs
output_prefix = opt.output_prefix or os.path.join(
options.view_as(GoogleCloudOptions).temp_location, 'output')
shards = opt.shards
p = Pipeline(options=options)
def generate(n):
yield from range(n * _ELEMENTS_PER_INPUT,
(n + 1) * _ELEMENTS_PER_INPUT)
(p
| Create(range(inputs))
| ParDo(generate).with_output_types(int)
| WriteToText(output_prefix, num_shards=shards))
p.run()
def examples_wordcount_templated(renames):
"""Templated WordCount example snippet."""
import re
import apache_beam as beam
from apache_beam.io import ReadFromText
from apache_beam.io import WriteToText
from apache_beam.options.pipeline_options import PipelineOptions
# [START example_wordcount_templated]
class WordcountTemplatedOptions(PipelineOptions):
@classmethod
def _add_argparse_args(cls, parser):
# Use add_value_provider_argument for arguments to be templatable
# Use add_argument as usual for non-templatable arguments
parser.add_value_provider_argument(
'--input', help='Path of the file to read from')
parser.add_argument('--output',
required=True,
help='Output file to write results to.')
pipeline_options = PipelineOptions(['--output', 'some/output_path'])
p = beam.Pipeline(options=pipeline_options)
wordcount_options = pipeline_options.view_as(WordcountTemplatedOptions)
lines = p | 'Read' >> ReadFromText(wordcount_options.input)
# [END example_wordcount_templated]
(lines
| 'ExtractWords' >> beam.FlatMap(lambda x: re.findall(r'[A-Za-z\']+', x))
| 'PairWithOnes' >> beam.Map(lambda x: (x, 1))
| 'Group' >> beam.GroupByKey()
| 'Sum' >> beam.Map(lambda (word, ones): (word, sum(ones)))
| 'Format' >> beam.Map(lambda (word, c): '%s: %s' % (word, c))
| 'Write' >> WriteToText(wordcount_options.output))
p.visit(SnippetUtils.RenameFiles(renames))
result = p.run()
result.wait_until_finish()
def run(args=None, save_main_session=True):
"""Runs the workflow computing total points from a collection of matches."""
if args is None:
args = sys.argv[1:]
parser = argparse.ArgumentParser()
parser.add_argument('--input',
required=True,
help='Input file to process.')
parser.add_argument('--output',
required=True,
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(args)
# We use the save_main_session option because one or more DoFn's in this
# workflow rely on global context (e.g., a module imported at module level).
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(
SetupOptions).save_main_session = save_main_session
with beam.Pipeline(options=pipeline_options) as p:
# Register the custom coder for the Player class, so that it will be used in
# the computation.
coders.registry.register_coder(Player, PlayerCoder)
(p # pylint: disable=expression-not-assigned
| ReadFromText(known_args.input)
# The get_players function is annotated with a type hint above, so the type
# system knows the output type of the following operation is a key-value
# pair of a Player and an int. Please see the documentation for details on
# types that are inferred automatically as well as other ways to specify
# type hints.
| beam.Map(get_players)
# The output type hint of the previous step is used to infer that the key
# type of the following operation is the Player type. Since a custom coder
# is registered for the Player class above, a PlayerCoder will be used to
# encode Player objects as keys for this combine operation.
| beam.CombinePerKey(sum)
| beam.Map(lambda k_v: '%s,%d' % (k_v[0].name, k_v[1]))
| WriteToText(known_args.output))
def examples_ptransforms_templated(renames):
# [START examples_ptransforms_templated]
import apache_beam as beam
from apache_beam.io import WriteToText
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.options.value_provider import StaticValueProvider
class TemplatedUserOptions(PipelineOptions):
@classmethod
def _add_argparse_args(cls, parser):
parser.add_value_provider_argument('--templated_int', type=int)
class MySumFn(beam.DoFn):
def __init__(self, templated_int):
self.templated_int = templated_int
def process(self, an_int):
yield self.templated_int.get() + an_int
pipeline_options = PipelineOptions()
p = beam.Pipeline(options=pipeline_options)
user_options = pipeline_options.view_as(TemplatedUserOptions)
my_sum_fn = MySumFn(user_options.templated_int)
sum = (p
| 'ReadCollection' >>
beam.io.ReadFromText('gs://some/integer_collection')
| 'StringToInt' >> beam.Map(lambda w: int(w))
| 'AddGivenInt' >> beam.ParDo(my_sum_fn)
| 'WriteResultingCollection' >> WriteToText('some/output_path'))
# [END examples_ptransforms_templated]
# Templates are not supported by DirectRunner (only by DataflowRunner)
# so a value must be provided at graph-construction time
my_sum_fn.templated_int = StaticValueProvider(int, 10)
p.visit(SnippetUtils.RenameFiles(renames))
result = p.run()
result.wait_until_finish()
def run(argv=None):
"""Runs the workflow computing total points from a collection of matches."""
parser = argparse.ArgumentParser()
parser.add_argument('--input',
required=True,
help='Input file to process.')
parser.add_argument('--output',
required=True,
help='Output file to write results to.')
known_args, pipeline_args = parser.parse_known_args(argv)
# We use the save_main_session option because one or more DoFn's in this
# workflow rely on global context (e.g., a module imported at module level).
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
with beam.Pipeline(options=pipeline_options) as p:
(p # pylint: disable=expression-not-assigned
| 'read' >> ReadFromText(known_args.input, coder=JsonCoder())
| 'points' >> beam.FlatMap(compute_points)
| beam.CombinePerKey(sum)
| 'write' >> WriteToText(known_args.output, coder=JsonCoder()))
def run():
PROJECT_ID = 'acquired-rarity-288205'
BUCKET = 'gs://ykdb_beam/temp'
options = {'project': PROJECT_ID}
opts = beam.pipeline.PipelineOptions(flags=[], **options)
p = beam.Pipeline('DirectRunner', options=opts)
# ***************************************** REMOVE DUPLICATES ****************************************************
sql = "SELECT job_title, employer_name, employer_city, employment_start_date, employment_end_date, soc_code, soc_title, prevailing_wage_YR, pw_wage_level, pw_wage_source, pw_wage_source_year, pw_wage_source_other, worksite_city, worksite_country, worksite_state, worksite_postal_code FROM (SELECT *, COUNT(*) AS count FROM H_1B_refined.Occupation WHERE prevailing_wage_YR > 5000 AND length(soc_code) > 5 AND soc_code NOT LIKE '%-%' GROUP BY job_title, employer_name, employer_city, employment_start_date, employment_end_date, soc_code, soc_title, prevailing_wage_YR, pw_wage_level, pw_wage_source, pw_wage_source_year, pw_wage_source_other, worksite_city, worksite_country, worksite_state, worksite_postal_code HAVING count = 1) LIMIT 50"
bq_source = ReadFromBigQuery(query=sql,
use_standard_sql=True,
gcs_location=BUCKET)
query_results = p | 'Read from BQ' >> beam.io.Read(bq_source)
out_pcoll_no_dup = query_results | 'Format prevailing_wage_YR and Remove dups' >> beam.ParDo(
NoDuplicates())
out_pcoll_fix_date = out_pcoll_no_dup | 'Format Date' >> beam.ParDo(
FormatDate())
out_pcoll = out_pcoll_fix_date | 'Format Soc' >> beam.ParDo(
FormatSocCode())
out_pcoll | 'Log output' >> WriteToText('output_occ_codeTest.txt')
# ***************************************** INSERT INTO BQ ****************************************************
dataset_id = 'H_1B_refined'
table_id = PROJECT_ID + ':' + dataset_id + '.' + 'Occ_CodeTest'
schema_id = 'job_title:STRING, employer_name:STRING, employer_city:STRING, employment_start_date:Date, employment_end_date:Date, soc_code:STRING, soc_title:STRING, prevailing_wage_YR:FLOAT, pw_wage_level:STRING, pw_wage_source:STRING, pw_wage_source_year:INTEGER, pw_wage_source_other:STRING, worksite_city:STRING, worksite_country:STRING, worksite_state:STRING, worksite_postal_code:STRING'
out_pcoll | 'Write to BQ' >> WriteToBigQuery(
table=table_id, schema=schema_id, custom_gcs_temp_location=BUCKET)
result = p.run()
result.wait_until_finish()
def run(argv=None):
import os
d = os.path.dirname(os.path.realpath(__file__))
parser = argparse.ArgumentParser()
parser.add_argument("--input",
dest="input",
default=os.path.join(d, "data", "auctions.txt"))
parser.add_argument("--output", dest="output", required=True)
known_args, pipeline_args = parser.parse_known_args(argv)
pipeline_args.extend([
"--runner=DirectRunner",
"--temp_location=/tmp/beam_tmp",
"--job_name=test-job",
])
pipeline_options = PipelineOptions(pipeline_args)
pipeline_options.view_as(SetupOptions).save_main_session = True
with beam.Pipeline(options=pipeline_options) as p:
lines = p | ReadFromText(known_args.input)
data = (
lines
| "Split" >>
(beam.Map(lambda x: tuple(x.split("\t"))).with_output_types(
beam.typehints.Tuple[str, str]))
| "Clean" >>
beam.Map(lambda x:
(AvgPrice.format_artis(x[0]), int(x[1].strip()))))
counts = AvgPrice.computeAvgPerKey(data)
def format_result(word_count):
(word, count) = word_count
return "%s: %s" % (word, count)
output = counts | "Format" >> beam.Map(format_result)
output | WriteToText(known_args.output)
def run():
# set up location
PROJECT_ID = 'trim-cistern-288221'
BUCKET = 'gs://bhnk-milestone1-data'
options = {'project': PROJECT_ID}
opts = beam.pipeline.PipelineOptions(flags=[], **options)
# executed with DirectRunner
p = beam.Pipeline('DirectRunner', options=opts)
# retrieve the data from imdb_refined dataset and save this information (location)
sql = 'SELECT * FROM imdb_refined.Primary_Professions limit 250'
bq_source = ReadFromBigQuery(query=sql,
use_standard_sql=True,
gcs_location=BUCKET)
# use the previously saved information (location) and read from BigQuery
# query results is now input P collection
query_results = p | 'Read from BQ' >> beam.io.Read(bq_source)
# Use ParDo to call function on query results
out_pcoll = query_results | 'Split Primary Professions' >> beam.ParDo(
SplitPrimaryProfessions())
out_pcoll | 'Log output' >> WriteToText('output.txt')
dataset_id = 'imdb_refined'
table_id = PROJECT_ID + ':' + dataset_id + '.' + 'Primary_Professions_Beam'
schema_id = 'nconst:STRING,primaryProfession:STRING'
# write to BigQuery using the location set above
out_pcoll | 'Write to BQ' >> WriteToBigQuery(
table=table_id, schema=schema_id, custom_gcs_temp_location=BUCKET)
# run and display results after everything is finished
result = p.run()
result.wait_until_finish()
def run(argv=None): # pylint: disable=missing-docstring
parser = argparse.ArgumentParser()
parser.add_argument('--grid_size',
dest='grid_size',
default=1000,
help='Size of the NxN matrix')
parser.add_argument(
'--coordinate_output',
dest='coordinate_output',
required=True,
help='Output file to write the color coordinates of the image to.')
parser.add_argument('--image_output',
dest='image_output',
default=None,
help='Output file to write the resulting image to.')
known_args, pipeline_args = parser.parse_known_args(argv)
with beam.Pipeline(argv=pipeline_args) as p:
n = int(known_args.grid_size)
coordinates = generate_julia_set_colors(p, complex(-.62772, .42193), n,
100)
def x_coord_key(x_y_i):
(x, y, i) = x_y_i
return (x, (x, y, i))
# Group each coordinate triplet by its x value, then write the coordinates
# to the output file with an x-coordinate grouping per line.
# pylint: disable=expression-not-assigned
(coordinates
| 'x coord key' >> beam.Map(x_coord_key)
| 'x coord' >> beam.GroupByKey()
|
'format' >> beam.Map(lambda k_coords: ' '.join('(%s, %s, %s)' % c
for c in k_coords[1]))
| WriteToText(known_args.coordinate_output))
def run():
PROJECT_ID = 'cs327e-sp2020' # change to your project id
# Project ID is required when using the BQ source
options = {'project': PROJECT_ID}
opts = beam.pipeline.PipelineOptions(flags=[], **options)
# Create beam pipeline using local runner
p = beam.Pipeline('DirectRunner', options=opts)
sql = 'SELECT * FROM covid_19_modeled.Event'
bq_source = beam.io.BigQuerySource(query=sql, use_standard_sql=True)
query_results = p | 'Read from BigQuery' >> beam.io.Read(bq_source)
# format timestamp
ts_pcoll = query_results | 'Format Timestamp' >> beam.ParDo(
FormatTimestampFn())
# write new PCollection to log file
ts_pcoll | 'Write log' >> WriteToText('ts_pcoll.txt')
dataset_id = 'covid_19_modeled'
table_id = 'Event_Beam'
schema_id = '''location_id:INTEGER,last_update:DATETIME,
confirmed:INTEGER,deaths:INTEGER,recovered:INTEGER'''
# write new PCollection to BQ table
ts_pcoll | 'Write BQ table' >> beam.io.WriteToBigQuery(
dataset=dataset_id,
table=table_id,
schema=schema_id,
project=PROJECT_ID,
create_disposition=beam.io.BigQueryDisposition.CREATE_IF_NEEDED,
write_disposition=beam.io.BigQueryDisposition.WRITE_TRUNCATE)
result = p.run()
result.wait_until_finish()
def run(p, input_file, output_file):
# Read the text file[pattern] into a PCollection.
lines = p | 'read' >> ReadFromText(input_file)
counts = (lines
| 'split' >>
(beam.ParDo(WordExtractingDoFn()).with_output_types(bytes))
| 'count' >> beam.ExternalTransform(
'beam:transforms:xlang:count', None, EXPANSION_SERVICE_ADDR))
# Format the counts into a PCollection of strings.
def format_result(word_count):
(word, count) = word_count
return '%s: %d' % (word, count)
output = counts | 'format' >> beam.Map(format_result)
# Write the output using a "Write" transform that has side effects.
# pylint: disable=expression-not-assigned
output | 'write' >> WriteToText(output_file)
result = p.run()
result.wait_until_finish()
