def parse_protein(project_id, bucket_name, filename, outfilename, metadata):
"""Download and convert blob into dataframe
Transform the file: includes data cleaning
Add Metadata information
"""
# setup logging
configure_logging('protein', "logs/" + metadata['AliquotBarcode'] + '.log')
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
#main steps: download, convert to df, cleanup, transform, add metadata
data_df = gcutils.convert_blob_to_dataframe(gcs,
project_id,
bucket_name,
filename,
skiprows=1)
data_df = additional_changes(data_df)
data_df = add_metadata(data_df, metadata)
# validation
tests.assert_notnull_property(data_df, columns_list=['Protein_Name'])
# upload the contents of the dataframe in njson format
status = gcs.convert_df_to_njson_and_upload(data_df,
outfilename,
metadata=metadata)
return status
def parse_protein(project_id, bucket_name, filename, outfilename, metadata):
"""Download and convert blob into dataframe
Transform the file: includes data cleaning
Add Metadata information
"""
# setup logging
configure_logging("protein", "logs/" + metadata["AliquotBarcode"] + ".log")
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
# main steps: download, convert to df, cleanup, transform, add metadata
data_df = gcutils.convert_blob_to_dataframe(gcs, project_id, bucket_name, filename, skiprows=1)
data_df = additional_changes(data_df)
data_df = add_metadata(data_df, metadata)
# validation
tests.assert_notnull_property(data_df, columns_list=["Protein_Name"])
# upload the contents of the dataframe in njson format
status = gcs.convert_df_to_njson_and_upload(data_df, outfilename, metadata=metadata)
return status
def parse_protein(project_id, bucket_name, filename, outfilename, metadata):
"""Download and convert blob into dataframe
Transform the file: includes data cleaning
Add Metadata information
"""
# setup logging
log = configure_logging(
'protein',
"logs/protein_transform_" + metadata['AliquotBarcode'] + '.log')
try:
log.info('start transform of %s' % (metadata['AliquotBarcode']))
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
#main steps: download, convert to df, cleanup, transform, add metadata
data_df = gcutils.convert_blob_to_dataframe(gcs,
project_id,
bucket_name,
filename,
skiprows=1,
log=log)
log.info('\tadd changes and metadata for %s' %
(metadata['AliquotBarcode']))
data_df = additional_changes(data_df)
data_df = add_metadata(data_df, metadata)
# validation
tests.assert_notnull_property(data_df, columns_list=['Protein_Name'])
# upload the contents of the dataframe in njson format
status = gcs.convert_df_to_njson_and_upload(data_df,
outfilename,
metadata=metadata)
log.info('finished transform of %s' % (metadata['AliquotBarcode']))
except Exception as e:
log.exception('problem transforming %s' % (metadata['AliquotBarcode']))
raise e
return status
def main(datatype, config_file, max_workers, dry_run, create_new, debug):
"""
Pipeline
"""
# config params
config = json.load(open(config_file))
project_id = config['project_id']
bucket_name = config['buckets']['open']
table_task_queue = 'task_queue'
table_task_queue_status = 'task_queue_status'
db_filename = 'etl-{0}.db'.format(datatype)
log_filename = 'etl_{0}.log'.format(datatype)
log_name = 'etl_{0}'.format(datatype)
log.info('start pipeline for %s' % (datatype))
# check if the table exists and issue warning
if os.path.exists(db_filename):
log.warning('Using the already available database file - {0}'.format(db_filename))
time.sleep(2)
# connect to the database
conn = sqlite3.connect(db_filename, check_same_thread=False)
#-------------------------------
# Submit to task queue
#-------------------------------
print "="*30 + "\nQuerying Google Cloud SQL metadata_data table"
queue_df = extract_functions[datatype](config)
submit_to_queue(queue_df, conn, table_task_queue)
#--------------
# Tests
#--------------
tests.assert_notnull_property(queue_df, columns_list=['SampleTypeCode', 'SampleTypeLetterCode',\
'Study', 'Platform', 'SampleBarcode', 'OutDatafileNameKey',\
'ParticipantBarcode', 'DatafileNameKey', 'AliquotBarcode'])
if create_new:
# delete the old queue(task_queue_status) and re-run
conn.execute('DROP TABLE IF EXISTS {0}'.format(table_task_queue_status))
# Validate and get diff ; restart ETL; also takes care of errors
queue_df = validate_and_get_diff(conn, queue_df, table_task_queue_status)
if debug:
# debug mode runs top 30 rows
log.debug('Running in debug mode (first 30 records)')
queue_df = queue_df.head(30)
if dry_run:
log.info('finished dry run for %s' % (datatype))
sys.exit()
#--------------------------------------------
# Execution
#------------------------------------------------------
pmr = process_manager.ProcessManager(max_workers=max_workers, db=db_filename, table=table_task_queue_status, log=log)
for index, row in queue_df.iterrows():
metadata = row.to_dict()
inputfilename = metadata['DatafileNameKey']
outputfilename = metadata['OutDatafileNameKey']
# transform
#transform_functions[datatype]( project_id, bucket_name,\
# inputfilename, outputfilename, metadata)
future = pmr.submit(transform_functions[datatype], project_id, bucket_name,\
inputfilename, outputfilename, metadata)
time.sleep(0.1 + 0.5 * random.random())
if index % 100 == 0:
time.sleep(5)
pmr.start()
log.info('finished pipeline for %s' % (datatype))
def main(datatype, config_file, max_workers, dry_run, create_new, debug):
"""
Pipeline
"""
# config params
config = json.load(open(config_file))
project_id = config['project_id']
bucket_name = config['buckets']['open']
table_task_queue = 'task_queue'
table_task_queue_status = 'task_queue_status'
db_filename = 'etl-{0}.db'.format(datatype)
log_filename = 'etl_{0}.log'.format(datatype)
log_name = 'etl_{0}'.format(datatype)
# check if the table exists and issue warning
if os.path.exists(db_filename):
log.warning('Using the already available database file - {0}'.format(db_filename))
time.sleep(2)
# connect to the database
conn = sqlite3.connect(db_filename, check_same_thread=False)
#-------------------------------
# Submit to task queue
#-------------------------------
print "="*30 + "\nQuerying Google Cloud SQL metadata_data table"
queue_df = extract_functions[datatype](config)
submit_to_queue(queue_df, conn, table_task_queue)
#--------------
# Tests
#--------------
tests.assert_notnull_property(queue_df, columns_list=['SampleTypeCode', 'SampleTypeLetterCode',\
'Study', 'Platform', 'SampleBarcode', 'OutDatafileNameKey',\
'ParticipantBarcode', 'DatafileNameKey', 'AliquotBarcode'])
if create_new:
# delete the old queue(task_queue_status) and re-run
conn.execute('DROP TABLE IF EXISTS {0}'.format(table_task_queue_status))
# Validate and get diff ; restart ETL; also takes care of errors
queue_df = validate_and_get_diff(conn, queue_df, table_task_queue_status)
if debug:
# debug mode runs top 30 rows
log.debug('Running in debug mode (first 30 records)')
queue_df = queue_df.head(30)
if dry_run:
sys.exit()
#--------------------------------------------
# Execution
#------------------------------------------------------
pmr = process_manager.ProcessManager(max_workers=max_workers, db=db_filename, table=table_task_queue_status)
for index, row in queue_df.iterrows():
metadata = row.to_dict()
inputfilename = metadata['DatafileNameKey']
outputfilename = metadata['OutDatafileNameKey']
# transform
#transform_functions[datatype]( project_id, bucket_name,\
# inputfilename, outputfilename, metadata)
future = pmr.submit(transform_functions[datatype], project_id, bucket_name,\
inputfilename, outputfilename, metadata)
time.sleep(0.1 + 0.5 * random.random())
if index % 100 == 0:
time.sleep(5)
pmr.start()
