def main():
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
print('job started')
#
# First thing is to load the configuration:
#
params, filters, bq_filters, steps, retain_cols, extra_cols, retain_platform_ref_fields = load_config(
yaml_config)
if params is None:
print("Bad YAML load")
return
#
# Use the filter set to get a manifest from GDC using their API. Note that if a pull list is
# provided, these steps can be omitted:
#
if 'build_manifest_from_filters' in steps:
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
if params['USE_GDC_API_FOR_MANIFEST']:
manifest_filter = build_manifest_filter(filters)
manifest_success = get_the_manifest(manifest_filter,
params['API_URL'],
params['MANIFEST_FILE'],
max_files)
else:
manifest_success = get_the_bq_manifest(
params['FILE_TABLE'], bq_filters, max_files,
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_MANIFEST_TSV'], params['MANIFEST_FILE'],
params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# Best practice is to clear out the directory where the files are going. Don't want anything left over:
#
if 'clear_target_directory' in steps:
create_clean_target(params['LOCAL_FILES_DIR'])
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, you can do it using IndexD calls on a manifest file, OR using BQ as long as you have
# built the manifest using BQ (that route uses the BQ Manifest table that was created).
#
if 'build_pull_list' in steps:
if params['USE_INDEXD_FOR_PULL']:
build_pull_list_with_indexd(params['MANIFEST_FILE'],
params['INDEXD_IDS_PER_CALL'],
params['INDEXD_URL'],
params['LOCAL_PULL_LIST'])
else:
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'])
build_pull_list_with_bq(
full_manifest, params['INDEXD_BQ_TABLE'],
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_PULL_LIST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_PULL_LIST'], params['LOCAL_PULL_LIST'],
params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets, not "downloading". Get the files in the pull list:
#
if 'download_from_gdc' in steps:
with open(params['LOCAL_PULL_LIST'], mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preparing to download %s files from buckets\n" % len(pull_list))
bp = BucketPuller(10)
bp.pull_from_buckets(pull_list, params['LOCAL_FILES_DIR'])
#
# Traverse the tree of downloaded files and create a flat list of all files:
#
if 'build_traversal_list' in steps:
all_files = build_file_list(params['LOCAL_FILES_DIR'])
with open(params['FILE_TRAVERSAL_LIST'], mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
#
# Take all the files and make one BIG TSV file to upload:
#
print("fix me have to toss out NA rows!")
if 'concat_all_files' in steps:
with open(params['FILE_TRAVERSAL_LIST'],
mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files_selected_cols(all_files, params['ONE_BIG_TSV'],
params['PROGRAM_PREFIX'], retain_cols,
extra_cols, file_info, None,
"Beta_value", "NA")
#
# Build the platform reference table
#
if 'build_plat_ref' in steps:
with open(params['FILE_TRAVERSAL_LIST'],
mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files_selected_cols(all_files, params['ONE_BIG_REF_TSV'],
params['PROGRAM_PREFIX'],
retain_platform_ref_fields, [],
file_info, None, None, None)
set_from_file(params['ONE_BIG_REF_TSV'],
params['ONE_BIG_DISTINCT_REF_TSV'])
#
# For the legacy table, the descriptions had lots of analysis tidbits. Very nice, but hard to maintain.
# We just use hardwired schema descriptions now, most directly pulled from the GDC website:
#
if 'build_the_schema' in steps:
typing_tups = build_schema(params['ONE_BIG_TSV'],
params['SCHEMA_SAMPLE_SKIPS'])
build_combined_schema(None, params['AUGMENTED_SCHEMA_FILE'],
typing_tups, params['HOLD_SCHEMA_LIST'],
params['HOLD_SCHEMA_DICT'])
#
# Upload the giant TSV into a cloud bucket:
#
if 'upload_to_bucket' in steps:
upload_to_bucket(params['WORKING_BUCKET'], params['BUCKET_SKEL_TSV'],
params['ONE_BIG_TSV'])
#
# Create the BQ table from the TSV:
#
if 'create_bq_from_tsv' in steps:
bucket_src_url = 'gs://{}/{}'.format(params['WORKING_BUCKET'],
params['BUCKET_SKEL_TSV'])
with open(params['HOLD_SCHEMA_LIST'], mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq(typed_schema, bucket_src_url, params['TARGET_DATASET'],
params['SKELETON_TABLE'], params['BQ_AS_BATCH'])
#
# Need to merge in aliquot and sample barcodes from other tables:
#
if 'collect_barcodes' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['SKELETON_TABLE'])
success = attach_aliquot_ids(skel_table, params['FILE_TABLE'],
params['TARGET_DATASET'],
params['BARCODE_STEP_1_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("attach_aliquot_ids job failed")
return
step_1_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BARCODE_STEP_1_TABLE'])
success = attach_barcodes(step_1_table, params['ALIQUOT_TABLE'],
params['TARGET_DATASET'],
params['BARCODE_STEP_2_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("attach_barcodes job failed")
return
#
# Merge the barcode info into the final table we are building:
#
if 'create_final_table' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['SKELETON_TABLE'])
barcodes_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BARCODE_STEP_2_TABLE'])
success = final_merge(skel_table, barcodes_table,
params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("Join job failed")
return
#
# The derived table we generate has no field descriptions. Add them from the scraped page:
#
if 'update_final_schema' in steps:
success = update_schema(params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
params['HOLD_SCHEMA_DICT'])
if not success:
print("Schema update failed")
return
#
# Add the table description:
#
if 'add_table_description' in steps:
update_description(params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
params['TABLE_DESCRIPTION'])
#
# Clear out working temp tables:
#
if 'dump_working_tables' in steps:
dump_table_tags = [
'SKELETON_TABLE', 'BARCODE_STEP_1_TABLE', 'BARCODE_STEP_2_TABLE',
'BQ_MANIFEST_TABLE', 'BQ_PULL_LIST_TABLE'
]
dump_tables = [params[x] for x in dump_table_tags]
for table in dump_tables:
delete_table_bq_job(params['TARGET_DATASET'], table)
#
# Done!
#
print('job completed')
def main(args):
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, filters, bq_filters, steps, callers, update_schema_tables, schema_tags = load_config(
yaml_file.read())
if params is None:
print("Bad YAML load")
return
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
# Which table are we building?
release = "".join(["r", str(params['RELEASE'])])
use_schema = params['VER_SCHEMA_FILE_NAME']
if 'current' in steps:
print('This workflow will update the schema for the "current" table')
release = 'current'
use_schema = params['SCHEMA_FILE_NAME']
# Create table names
concat_table = '_'.join([params['PROGRAM'], params['DATA_TYPE'], 'concat'])
barcode_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'barcode'])
draft_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], params['BUILD'], 'gdc', '{}'])
publication_table = '_'.join(
[params['DATA_TYPE'], params['BUILD'], 'gdc', '{}'])
manifest_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'manifest'])
if params['RELEASE'] < 21 and 'METADATA_REL' not in params:
print("The input release is before new metadata process, "
"please specify which release of the metadata to use.")
metadata_rel = "".join(["r", str(params['METADATA_REL'])
]) if 'METADATA_REL' in params else release
if 'build_manifest_from_filters' in steps:
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(
params['FILE_TABLE'].format(metadata_rel), bq_filters, max_files,
params['WORKING_PROJECT'], params['SCRATCH_DATASET'],
manifest_table, params['WORKING_BUCKET'],
params['BUCKET_MANIFEST_TSV'], manifest_file,
params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# Best practice is to clear out the directory where the files are going. Don't want anything left over:
#
if 'clear_target_directory' in steps:
create_clean_target(local_files_dir)
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, you can do it using IndexD calls on a manifest file, OR using BQ as long as you have
# built the manifest using BQ (that route uses the BQ Manifest table that was created).
#
if 'build_pull_list' in steps:
build_pull_list_with_bq(
"{}.{}.{}".format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'], manifest_table),
params['INDEXD_BQ_TABLE'].format(metadata_rel),
params['WORKING_PROJECT'], params['SCRATCH_DATASET'],
"_".join([params['PROGRAM'], params['DATA_TYPE'], 'pull',
'list']), params['WORKING_BUCKET'],
params['BUCKET_PULL_LIST'], local_pull_list, params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets, not "downloading". Get the files in the pull list:
#
if 'download_from_gdc' in steps:
with open(local_pull_list, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
pull_from_buckets(pull_list, local_files_dir)
#
# Traverse the tree of downloaded files and create a flat list of all files:
#
if 'build_traversal_list' in steps:
all_files = build_file_list(local_files_dir)
with open(file_traversal_list, mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
if 'concat_all_files' in steps:
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files(all_files, one_big_tsv, params['PROGRAM'],
callers, params['FIELDS_TO_FIX'])
#
# Schemas and table descriptions are maintained in the github repo:
#
if 'pull_table_info_from_git' in steps:
print('pull_table_info_from_git')
try:
create_clean_target(params['SCHEMA_REPO_LOCAL'])
repo = Repo.clone_from(params['SCHEMA_REPO_URL'],
params['SCHEMA_REPO_LOCAL'])
repo.git.checkout(params['SCHEMA_REPO_BRANCH'])
except Exception as ex:
print("pull_table_info_from_git failed: {}".format(str(ex)))
return
for table in update_schema_tables:
if table == 'current':
use_schema = params['SCHEMA_FILE_NAME']
schema_release = 'current'
else:
use_schema = params['VER_SCHEMA_FILE_NAME']
schema_release = release
if 'process_git_schemas' in steps:
print('process_git_schema')
# Where do we dump the schema git repository?
schema_file = "{}/{}/{}".format(params['SCHEMA_REPO_LOCAL'],
params['RAW_SCHEMA_DIR'],
use_schema)
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'], draft_table.format(schema_release))
# Write out the details
success = generate_table_detail_files(schema_file,
full_file_prefix)
if not success:
print("process_git_schemas failed")
return
# Customize generic schema to this data program:
if 'replace_schema_tags' in steps:
print('replace_schema_tags')
pn = params['PROGRAM']
dataset_tuple = (pn, pn.replace(".", "_"))
tag_map_list = []
for tag_pair in schema_tags:
for tag in tag_pair:
val = tag_pair[tag]
use_pair = {}
tag_map_list.append(use_pair)
if val.find('~-') == 0 or val.find(
'~lc-') == 0 or val.find('~lcbqs-') == 0:
chunks = val.split('-', 1)
if chunks[1] == 'programs':
if val.find('~lcbqs-') == 0:
rep_val = dataset_tuple[1].lower(
) # can't have "." in a tag...
else:
rep_val = dataset_tuple[0]
elif chunks[1] == 'builds':
rep_val = params['BUILD']
else:
raise Exception()
if val.find('~lc-') == 0:
rep_val = rep_val.lower()
use_pair[tag] = rep_val
else:
use_pair[tag] = val
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'], draft_table.format(schema_release))
# Write out the details
success = customize_labels_and_desc(full_file_prefix, tag_map_list)
if not success:
print("replace_schema_tags failed")
return False
if 'analyze_the_schema' in steps:
print('analyze_the_schema')
typing_tups = build_schema(one_big_tsv,
params['SCHEMA_SAMPLE_SKIPS'])
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'], draft_table.format(schema_release))
schema_dict_loc = "{}_schema.json".format(full_file_prefix)
build_combined_schema(None, schema_dict_loc, typing_tups,
hold_schema_list, hold_schema_dict)
bucket_target_blob = '{}/{}-{}-{}.tsv'.format(params['WORKING_BUCKET_DIR'],
params['DATE'],
params['PROGRAM'],
params['DATA_TYPE'])
if 'upload_to_bucket' in steps:
print('upload_to_bucket')
upload_to_bucket(params['WORKING_BUCKET'], bucket_target_blob,
one_big_tsv)
#
# Create the BQ table from the TSV:
#
if 'create_bq_from_tsv' in steps:
print('create_bq_from_tsv')
bucket_src_url = 'gs://{}/{}'.format(params['WORKING_BUCKET'],
bucket_target_blob)
with open(hold_schema_list, mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq(typed_schema, bucket_src_url, params['SCRATCH_DATASET'],
concat_table, params['BQ_AS_BATCH'])
#
# Need to merge in aliquot and sample barcodes from other tables:
#
if 'collect_barcodes' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'], concat_table)
if params['RELEASE'] < 25:
case_table = params['CASE_TABLE'].format('25')
else:
case_table = params['CASE_TABLE'].format(release)
if params['PROGRAM'] == 'TCGA':
success = attach_aliquot_ids(skel_table,
params['FILE_TABLE'].format(release),
params['SCRATCH_DATASET'],
'_'.join([barcode_table, 'pre']),
params['BQ_AS_BATCH'])
if not success:
print("attach_aliquot_ids job failed")
return
step_1_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
'_'.join([barcode_table, 'pre']))
else:
step_1_table = skel_table
success = attach_barcodes(step_1_table,
params['ALIQUOT_TABLE'].format(release),
params['SCRATCH_DATASET'], barcode_table,
params['BQ_AS_BATCH'], params['PROGRAM'],
case_table)
if not success:
print("attach_barcodes job failed")
return
#
# Merge the barcode info into the final table we are building:
#
if 'create_final_table' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'], concat_table)
barcodes_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
barcode_table)
success = final_merge(skel_table, barcodes_table,
params['SCRATCH_DATASET'],
draft_table.format(release),
params['BQ_AS_BATCH'], params['PROGRAM'])
if not success:
print("Join job failed")
return
#
# Create second table
#
if 'create_current_table' in steps:
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
draft_table.format(release))
current_dest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
draft_table.format('current'))
success = publish_table(source_table, current_dest)
if not success:
print("create current table failed")
return
#
# The derived table we generate has no field descriptions. Add them from the github json files:
#
for table in update_schema_tables:
schema_release = 'current' if table == 'current' else release
if 'update_final_schema' in steps:
success = update_schema(params['SCRATCH_DATASET'],
draft_table.format(schema_release),
hold_schema_dict)
if not success:
print("Schema update failed")
return
#
# Add the table description:
#
if 'add_table_description' in steps:
print('update_table_description')
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'], draft_table.format(schema_release))
success = install_labels_and_desc(
params['SCRATCH_DATASET'], draft_table.format(schema_release),
full_file_prefix)
if not success:
print("update_table_description failed")
return
#
# compare and remove old current table
#
# compare the two tables
if 'compare_remove_old_current' in steps:
old_current_table = '{}.{}.{}'.format(
params['PUBLICATION_PROJECT'], params['PUBLICATION_DATASET'],
publication_table.format('current'))
previous_ver_table = '{}.{}.{}'.format(
params['PUBLICATION_PROJECT'],
"_".join([params['PUBLICATION_DATASET'], 'versioned']),
publication_table.format("".join(
["r", str(params['PREVIOUS_RELEASE'])])))
table_temp = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['SCRATCH_DATASET'], "_".join([
params['PROGRAM'],
publication_table.format("".join(
["r", str(params['PREVIOUS_RELEASE'])])), 'backup'
]))
print('Compare {} to {}'.format(old_current_table, previous_ver_table))
compare = compare_two_tables(old_current_table, previous_ver_table,
params['BQ_AS_BATCH'])
num_rows = compare.total_rows
if num_rows == 0:
print('the tables are the same')
else:
print('the tables are NOT the same and differ by {} rows'.format(
num_rows))
if not compare:
print('compare_tables failed')
return
# move old table to a temporary location
elif compare and num_rows == 0:
print('Move old table to temp location')
table_moved = publish_table(old_current_table, table_temp)
if not table_moved:
print('Old Table was not moved and will not be deleted')
# remove old table
elif table_moved:
print('Deleting old table: {}'.format(old_current_table))
delete_table = delete_table_bq_job(
params['PUBLICATION_DATASET'],
publication_table.format('current'))
if not delete_table:
print('delete table failed')
return
#
# publish table:
#
if 'publish' in steps:
tables = ['versioned', 'current']
for table in tables:
if table == 'versioned':
print(table)
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
draft_table.format(release))
publication_dest = '{}.{}.{}'.format(
params['PUBLICATION_PROJECT'],
"_".join([params['PUBLICATION_DATASET'], 'versioned']),
publication_table.format(release))
elif table == 'current':
print(table)
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
draft_table.format('current'))
publication_dest = '{}.{}.{}'.format(
params['PUBLICATION_PROJECT'],
params['PUBLICATION_DATASET'],
publication_table.format('current'))
success = publish_table(source_table, publication_dest)
if not success:
print("publish table failed")
return
#
# Update previous versioned table with archived tag
#
if 'update_status_tag' in steps:
print('Update previous table')
success = update_status_tag(
"_".join([params['PUBLICATION_DATASET'], 'versioned']),
publication_table.format("".join(
["r", str(params['PREVIOUS_RELEASE'])])), 'archived')
if not success:
print("update status tag table failed")
return
#
# Clear out working temp tables:
#
if 'dump_working_tables' in steps:
dump_tables = [
concat_table, barcode_table,
draft_table.format('current'),
draft_table.format(release), manifest_table
]
for table in dump_tables:
delete_table_bq_job(params['SCRATCH_DATASET'], table)
#
# Done!
#
print('job completed')
if 'archive' in steps:
print('archive files from VM')
archive_file_prefix = "{}_{}".format(date.today(),
params['PUBLICATION_DATASET'])
if params['ARCHIVE_YAML']:
yaml_file = re.search(r"\/(\w*.yaml)$", args[1])
archive_yaml = "{}/{}/{}_{}".format(params['ARCHIVE_BUCKET_DIR'],
params['ARCHIVE_CONFIG'],
archive_file_prefix,
yaml_file.group(1))
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_yaml, args[1])
archive_pull_file = "{}/{}_{}".format(params['ARCHIVE_BUCKET_DIR'],
archive_file_prefix,
params['LOCAL_PULL_LIST'])
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_pull_file,
params['LOCAL_PULL_LIST'])
archive_manifest_file = "{}/{}_{}".format(params['ARCHIVE_BUCKET_DIR'],
archive_file_prefix,
params['MANIFEST_FILE'])
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_manifest_file,
params['MANIFEST_FILE'])
def main(args):
if not confirm_google_vm():
print('This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]')
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, bq_filters, na_values, steps = load_config(yaml_file.read())
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
#
# Actual fields have brackets:
#
na_set = set()
for val in na_values:
na_set.add("[{}]".format(val))
if 'clear_target_directory' in steps:
print('clear_target_directory')
create_clean_target(local_files_dir)
#
# Use the filter set to build a manifest. Note that if a pull list is
# provided, these steps can be omitted:
#
if 'build_manifest_from_filters' in steps:
print('build_manifest_from_filters')
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(params['FILE_TABLE'], bq_filters, max_files,
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_MANIFEST_TSV'], manifest_file,
params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, uses BQ as long as you have built the manifest using BQ (that route uses the BQ Manifest
# table that was created).
#
if 'build_pull_list' in steps:
print('build_pull_list')
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'])
success = build_pull_list_with_bq_public(full_manifest, params['INDEXD_BQ_TABLE'],
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_PULL_LIST_TABLE'],
params['WORKING_BUCKET'],
params['BUCKET_PULL_LIST'],
local_pull_list, params['BQ_AS_BATCH'])
if not success:
print("Build pull list failed")
return;
#
# Now hitting GDC cloud buckets. Get the files in the pull list:
#
if 'download_from_gdc' in steps:
print('download_from_gdc')
with open(local_pull_list, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preparing to download %s files from buckets\n" % len(pull_list))
bp = BucketPuller(10)
bp.pull_from_buckets(pull_list, local_files_dir)
if 'build_file_list' in steps:
print('build_file_list')
all_files = build_file_list(local_files_dir)
with open(file_traversal_list, mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
if 'group_by_type' in steps:
print('group_by_type')
print(file_traversal_list)
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
group_dict = group_by_suffixes(all_files) # WRITE OUT AS JSON!!
if 'convert_excel_to_csv' in steps:
print('convert_excel_to_csv')
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
convert_excel_to_csv(all_files, local_files_dir)
if 'concat_all_files' in steps:
print('concat_all_files')
for k, v in group_dict.items():
concat_all_files(v, one_big_tsv.format(k), na_set)
#
# Schemas and table descriptions are maintained in the github repo:
#
if 'pull_table_info_from_git' in steps:
print('pull_table_info_from_git')
try:
create_clean_target(params['SCHEMA_REPO_LOCAL'])
repo = Repo.clone_from(params['SCHEMA_REPO_URL'], params['SCHEMA_REPO_LOCAL'])
repo.git.checkout(params['SCHEMA_REPO_BRANCH'])
except Exception as ex:
print("pull_table_info_from_git failed: {}".format(str(ex)))
return
if 'process_git_schemas' in steps:
print('process_git_schema')
# Where do we dump the schema git repository?
schema_file = "{}/{}/{}".format(params['SCHEMA_REPO_LOCAL'], params['RAW_SCHEMA_DIR'], params['SCHEMA_FILE_NAME'])
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'], params['FINAL_TARGET_TABLE'])
# Write out the details
success = generate_table_detail_files(schema_file, full_file_prefix)
if not success:
print("process_git_schemas failed")
return
if 'analyze_the_schema' in steps:
print('analyze_the_schema')
for k in group_dict:
typing_tups = build_schema(one_big_tsv.format(k), params['SCHEMA_SAMPLE_SKIPS'])
#full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'], params['FINAL_TARGET_TABLE'])
#schema_dict_loc = "{}_schema.json".format(full_file_prefix)
hold_schema_dict_for_group = hold_schema_dict.format(k)
hold_schema_list_for_group = hold_schema_list.format(k)
build_combined_schema(None, None,
typing_tups, hold_schema_list_for_group, hold_schema_dict_for_group)
bucket_target_blob = '{}/{}'.format(params['WORKING_BUCKET_DIR'], params['BUCKET_TSV'])
if 'upload_to_bucket' in steps:
print('upload_to_bucket')
for k in group_dict:
upload_to_bucket(params['WORKING_BUCKET'], bucket_target_blob.format(k), one_big_tsv.format(k))
if 'create_bq_from_tsv' in steps:
print('create_bq_from_tsv')
for k in group_dict:
bucket_src_url = 'gs://{}/{}'.format(params['WORKING_BUCKET'], bucket_target_blob.format(k))
with open(hold_schema_list.format(k), mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq(typed_schema, bucket_src_url, params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'].format(k.replace(".", "_").replace("-", "_")), params['BQ_AS_BATCH'])
if 'add_aliquot_fields' in steps:
print('add_aliquot_fields')
full_target_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['TARGET_TABLE'])
success = join_with_aliquot_table(full_target_table, params['ALIQUOT_TABLE'],
params['TARGET_DATASET'], params['FINAL_TARGET_TABLE'], params['BQ_AS_BATCH'])
if not success:
print("Join job failed")
#
# Update the per-field descriptions:
#
if 'update_field_descriptions' in steps:
print('update_field_descriptions')
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'], params['FINAL_TARGET_TABLE'])
schema_dict_loc = "{}_schema.json".format(full_file_prefix)
schema_dict = {}
with open(schema_dict_loc, mode='r') as schema_hold_dict:
full_schema_list = json_loads(schema_hold_dict.read())
for entry in full_schema_list:
schema_dict[entry['name']] = {'description': entry['description']}
success = update_schema_with_dict(params['TARGET_DATASET'], params['FINAL_TARGET_TABLE'], schema_dict)
if not success:
print("update_field_descriptions failed")
return
#
# Add description and labels to the target table:
#
if 'update_table_description' in steps:
print('update_table_description')
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'], params['FINAL_TARGET_TABLE'])
success = install_labels_and_desc(params['TARGET_DATASET'], params['FINAL_TARGET_TABLE'], full_file_prefix)
if not success:
print("update_table_description failed")
return
#
# publish table:
#
if 'publish' in steps:
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'])
publication_dest = '{}.{}.{}'.format(params['PUBLICATION_PROJECT'], params['PUBLICATION_DATASET'],
params['PUBLICATION_TABLE'])
success = publish_table(source_table, publication_dest)
if not success:
print("publish table failed")
return
#
# Clear out working temp tables:
#
if 'dump_working_tables' in steps:
dump_table_tags = ['TARGET_TABLE']
dump_tables = [params[x] for x in dump_table_tags]
for table in dump_tables:
delete_table_bq_job(params['TARGET_DATASET'], table)
print('job completed')
def main(args):
if not confirm_google_vm():
print('This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]')
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, bq_filters, steps, extra_cols = load_config(yaml_file.read())
if params is None:
print("Bad YAML load")
return
# Schema that describes table columns:
AUGMENTED_SCHEMA_FILE = "SchemaFiles/mirna_augmented_schema_list.json"
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
#
# Best practice is to clear out the directory where the files are going. Don't want anything left over.
# Also creates the destination directory
#
if 'clear_target_directory' in steps:
create_clean_target(local_files_dir)
#
# Use the filter set to get a manifest. Note that is a pull list is
# provided, these steps can be omitted:
#
if 'build_manifest_from_filters' in steps:
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(params['FILE_TABLE'], bq_filters, max_files,
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_MANIFEST_TSV'], manifest_file,
params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# If you have already created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step.
#
if 'build_pull_list' in steps:
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'])
build_pull_list_with_bq(full_manifest, params['INDEXD_BQ_TABLE'],
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_PULL_LIST_TABLE'],
params['WORKING_BUCKET'],
params['BUCKET_PULL_LIST'],
local_pull_list, params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets, not "downloading". Get the files in the pull list:
#
if 'download_from_gdc' in steps:
with open(local_pull_list, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preparing to download %s files from buckets\n" % len(pull_list))
bp = BucketPuller(10)
bp.pull_from_buckets(pull_list, local_files_dir)
#
# Traverse the tree of downloaded files and create a flat list of all files:
#
if 'build_traversal_list' in steps:
all_files = build_file_list(local_files_dir)
with open(file_traversal_list, mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
#
# Take all the files and make one BIG TSV file to upload:
#
if 'concat_all_files' in steps:
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files(all_files, one_big_tsv,
params['PROGRAM_PREFIX'], extra_cols, file_info, None)
#
# For the legacy table, the descriptions had lots of analysis tidbits. Very nice, but hard to maintain.
# We just use hardwired schema descriptions now, most directly pulled from the GDC website:
#
if 'build_the_schema' in steps:
typing_tups = build_schema(one_big_tsv, params['SCHEMA_SAMPLE_SKIPS'])
build_combined_schema(None, AUGMENTED_SCHEMA_FILE,
typing_tups, hold_schema_list, hold_schema_dict)
#
# Upload the giant TSV into a cloud bucket:
#
if 'upload_to_bucket' in steps:
upload_to_bucket(params['WORKING_BUCKET'], params['BUCKET_SKEL_TSV'], one_big_tsv)
#
# Create the BQ table from the TSV:
#
if 'create_bq_from_tsv' in steps:
bucket_src_url = 'gs://{}/{}'.format(params['WORKING_BUCKET'], params['BUCKET_SKEL_TSV'])
with open(hold_schema_list, mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq(typed_schema, bucket_src_url, params['TARGET_DATASET'], params['SKELETON_TABLE'], params['BQ_AS_BATCH'])
#
# Need to merge in aliquot and sample barcodes from other tables:
#
if 'collect_barcodes' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['SKELETON_TABLE'])
success = attach_aliquot_ids(skel_table, params['FILE_TABLE'],
params['TARGET_DATASET'],
params['BARCODE_STEP_1_TABLE'], params['BQ_AS_BATCH'])
if not success:
print("attach_aliquot_ids job failed")
return
step_1_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BARCODE_STEP_1_TABLE'])
success = attach_barcodes(step_1_table, params['ALIQUOT_TABLE'],
params['TARGET_DATASET'], params['BARCODE_STEP_2_TABLE'], params['BQ_AS_BATCH'])
if not success:
print("attach_barcodes job failed")
return
#
# Merge the barcode info into the final table we are building:
#
if 'create_final_table' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['SKELETON_TABLE'])
barcodes_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BARCODE_STEP_2_TABLE'])
success = final_merge(skel_table, barcodes_table,
params['TARGET_DATASET'], params['FINAL_TARGET_TABLE'], params['BQ_AS_BATCH'])
if not success:
print("Join job failed")
return
#
# Schemas and table descriptions are maintained in the github repo:
#
if 'pull_table_info_from_git' in steps:
print('pull_table_info_from_git')
try:
create_clean_target(params['SCHEMA_REPO_LOCAL'])
repo = Repo.clone_from(params['SCHEMA_REPO_URL'], params['SCHEMA_REPO_LOCAL'])
repo.git.checkout(params['SCHEMA_REPO_BRANCH'])
except Exception as ex:
print("pull_table_info_from_git failed: {}".format(str(ex)))
return
if 'process_git_schemas' in steps:
print('process_git_schema')
# Where do we dump the schema git repository?
schema_file = "{}/{}/{}".format(params['SCHEMA_REPO_LOCAL'], params['RAW_SCHEMA_DIR'], params['SCHEMA_FILE_NAME'])
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'], params['FINAL_TARGET_TABLE'])
# Write out the details
success = generate_table_detail_files(schema_file, full_file_prefix)
if not success:
print("process_git_schemas failed")
return
if 'analyze_the_schema' in steps:
print('analyze_the_schema')
typing_tups = build_schema(one_big_tsv, params['SCHEMA_SAMPLE_SKIPS'])
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'], params['FINAL_TARGET_TABLE'])
schema_dict_loc = "{}_schema.json".format(full_file_prefix)
build_combined_schema(None, schema_dict_loc,
typing_tups, hold_schema_list, hold_schema_dict)
#
# Update the per-field descriptions:
#
if 'update_field_descriptions' in steps:
print('update_field_descriptions')
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'], params['FINAL_TARGET_TABLE'])
schema_dict_loc = "{}_schema.json".format(full_file_prefix)
schema_dict = {}
with open(schema_dict_loc, mode='r') as schema_hold_dict:
full_schema_list = json_loads(schema_hold_dict.read())
for entry in full_schema_list:
schema_dict[entry['name']] = {'description': entry['description']}
success = update_schema_with_dict(params['TARGET_DATASET'], params['FINAL_TARGET_TABLE'], schema_dict)
if not success:
print("update_field_descriptions failed")
return
#
# Add description and labels to the target table:
#
if 'update_table_description' in steps:
print('update_table_description')
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'], params['FINAL_TARGET_TABLE'])
success = install_labels_and_desc(params['TARGET_DATASET'], params['FINAL_TARGET_TABLE'], full_file_prefix)
if not success:
print("update_table_description failed")
return
#
# Clear out working temp tables:
#
if 'dump_working_tables' in steps:
dump_table_tags = ['SKELETON_TABLE', 'BARCODE_STEP_1_TABLE', 'BARCODE_STEP_2_TABLE',
'BQ_MANIFEST_TABLE', 'BQ_PULL_LIST_TABLE']
dump_tables = [params[x] for x in dump_table_tags]
for table in dump_tables:
delete_table_bq_job(params['TARGET_DATASET'], table)
#
# publish table:
#
if 'publish' in steps:
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'])
publication_dest = '{}.{}.{}'.format(params['PUBLICATION_PROJECT'], params['PUBLICATION_DATASET'],
params['PUBLICATION_TABLE'])
success = publish_table(source_table, publication_dest)
if not success:
print("publish table failed")
return
print('job completed')
def main(args):
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, file_sets, update_schema_tables, schema_tags, steps = load_config(
yaml_file.read())
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
# Which release is the workflow running on?
release = "".join(["r", str(params['RELEASE'])])
# Create table names
upload_table = '_'.join([params['PROGRAM'], params['DATA_TYPE'], '{}'])
manifest_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'manifest', '{}'])
pull_list_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'pull', 'list', '{}'])
files_to_case_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'files_to_case'])
files_to_case_w_plat_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'files_to_case_with_plat'])
barcodes_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'barcodes'])
counts_w_metadata_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'counts_and_meta', '{}'])
merged_counts_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], 'merged_counts'])
draft_table = '_'.join(
[params['PROGRAM'], params['DATA_TYPE'], params['BUILD'], 'gdc', '{}'])
publication_table = '_'.join(
[params['DATA_TYPE'], params['BUILD'], 'gdc', '{}'])
if params['RELEASE'] < 21 and 'METADATA_REL' not in params:
print("The input release is before new metadata process, "
"please specify which release of the metadata to use.")
metadata_rel = "".join(["r", str(params['METADATA_REL'])
]) if 'METADATA_REL' in params else release
if 'clear_target_directory' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
create_clean_target(local_files_dir.format(count_name))
if 'build_manifest_from_filters' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
mani_for_count = manifest_file.format(count_name)
table_for_count = manifest_table.format(count_name)
tsv_for_count = params['BUCKET_MANIFEST_TSV'].format(count_name)
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(
params['FILE_TABLE'].format(metadata_rel),
count_dict['filters'], max_files, params['WORKING_PROJECT'],
params['SCRATCH_DATASET'], table_for_count,
params['WORKING_BUCKET'], tsv_for_count, mani_for_count,
params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, uses BQ as long as you have built the manifest using BQ (that route uses the BQ Manifest
# table that was created).
#
if 'build_pull_list' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
table_for_count = manifest_table.format(count_name)
local_pull_for_count = local_pull_list.format(count_name)
pull_table_for_count = pull_list_table.format(count_name)
bucket_pull_list_for_count = params['BUCKET_PULL_LIST'].format(
count_name)
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
table_for_count)
build_pull_list_with_bq(
full_manifest, params['INDEXD_BQ_TABLE'].format(metadata_rel),
params['WORKING_PROJECT'], params['SCRATCH_DATASET'],
pull_table_for_count, params['WORKING_BUCKET'],
bucket_pull_list_for_count, local_pull_for_count,
params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets. Get the files in the pull list:
#
if 'download_from_gdc' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
pull_for_count = local_pull_list.format(count_name)
with open(pull_for_count, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preparing to download %s files from buckets\n" %
len(pull_list))
bp = BucketPuller(10)
local_files_dir_for_count = local_files_dir.format(count_name)
bp.pull_from_buckets(pull_list, local_files_dir_for_count)
if 'build_file_list' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
local_files_dir_for_count = local_files_dir.format(count_name)
all_files = build_file_list(local_files_dir_for_count)
file_traversal_list_for_count = file_traversal_list.format(
count_name)
with open(file_traversal_list_for_count,
mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
if 'concat_all_files' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
header = count_dict['header'] if 'header' in count_dict else None
file_traversal_list_for_count = file_traversal_list.format(
count_name)
with open(file_traversal_list_for_count,
mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files(all_files, one_big_tsv.format(count_name),
header)
#
# Schemas and table descriptions are maintained in the github repo:
#
if 'pull_table_info_from_git' in steps:
print('pull_table_info_from_git')
try:
create_clean_target(params['SCHEMA_REPO_LOCAL'])
repo = Repo.clone_from(params['SCHEMA_REPO_URL'],
params['SCHEMA_REPO_LOCAL'])
repo.git.checkout(params['SCHEMA_REPO_BRANCH'])
except Exception as ex:
print("pull_table_info_from_git failed: {}".format(str(ex)))
return
for table in update_schema_tables:
if table == 'current':
use_schema = params['SCHEMA_FILE_NAME']
schema_release = 'current'
else:
use_schema = params['VER_SCHEMA_FILE_NAME']
schema_release = release
if 'process_git_schemas' in steps:
print('process_git_schema')
# Where do we dump the schema git repository?
schema_file = "{}/{}/{}".format(params['SCHEMA_REPO_LOCAL'],
params['RAW_SCHEMA_DIR'],
use_schema)
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'], draft_table.format(schema_release))
# Write out the details
success = generate_table_detail_files(schema_file,
full_file_prefix)
if not success:
print("process_git_schemas failed")
return
# Customize generic schema to this data program:
if 'replace_schema_tags' in steps:
print('replace_schema_tags')
pn = params['PROGRAM']
dataset_tuple = (pn, pn.replace(".", "_"))
tag_map_list = []
for tag_pair in schema_tags:
for tag in tag_pair:
val = tag_pair[tag]
use_pair = {}
tag_map_list.append(use_pair)
if val.find('~-') == 0 or val.find(
'~lc-') == 0 or val.find('~lcbqs-') == 0:
chunks = val.split('-', 1)
if chunks[1] == 'programs':
if val.find('~lcbqs-') == 0:
rep_val = dataset_tuple[1].lower(
) # can't have "." in a tag...
else:
rep_val = dataset_tuple[0]
elif chunks[1] == 'builds':
rep_val = params['BUILD']
else:
raise Exception()
if val.find('~lc-') == 0:
rep_val = rep_val.lower()
use_pair[tag] = rep_val
else:
use_pair[tag] = val
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'], draft_table.format(schema_release))
# Write out the details
success = customize_labels_and_desc(full_file_prefix, tag_map_list)
if not success:
print("replace_schema_tags failed")
return False
if 'analyze_the_schema' in steps:
print('analyze_the_schema')
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
typing_tups = build_schema(one_big_tsv.format(count_name),
params['SCHEMA_SAMPLE_SKIPS'])
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'],
draft_table.format(schema_release))
schema_dict_loc = "{}_schema.json".format(full_file_prefix)
build_combined_schema(None, schema_dict_loc, typing_tups,
hold_schema_list.format(count_name),
hold_schema_dict.format(count_name))
bucket_target_blob_sets = {}
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
bucket_target_blob_sets[count_name] = '{}/{}-{}-{}-{}.tsv'.format(
params['WORKING_BUCKET_DIR'], params['DATE'], params['PROGRAM'],
params['DATA_TYPE'], count_name)
if 'upload_to_bucket' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
upload_to_bucket(params['WORKING_BUCKET'],
bucket_target_blob_sets[count_name],
one_big_tsv.format(count_name))
if 'delete_all_bq' in steps:
table_cleaner(params, file_sets, True)
if 'create_bq_from_tsv' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
bucket_src_url = 'gs://{}/{}'.format(
params['WORKING_BUCKET'], bucket_target_blob_sets[count_name])
hold_schema_list_for_count = hold_schema_list.format(count_name)
with open(hold_schema_list_for_count,
mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq_write_depo(typed_schema, bucket_src_url,
params['SCRATCH_DATASET'],
upload_table.format(count_name),
params['BQ_AS_BATCH'], None)
if 'attach_ids_to_files' in steps:
count = 0
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
write_depo = "WRITE_TRUNCATE" if (count == 0) else "WRITE_APPEND"
gexp_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
upload_table.format(count_name))
success = build_aliquot_and_case(
gexp_table, params['FILEDATA_TABLE'].format(release),
params['SCRATCH_DATASET'], files_to_case_table, write_depo, {},
params['BQ_AS_BATCH'])
count += 1
if not success:
print("attach_ids_to_files failed")
return
if 'extract_platform' in steps:
step2_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
files_to_case_table)
success = extract_platform_for_files(
step2_table, params['FILEDATA_TABLE'].format(release),
params['SCRATCH_DATASET'], files_to_case_w_plat_table, True, {},
params['BQ_AS_BATCH'])
if not success:
print("extract_platform failed")
return
if 'attach_barcodes_to_ids' in steps:
step2_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
files_to_case_w_plat_table)
if params['RELEASE'] < 25:
case_table = params['CASE_TABLE'].format("r25")
else:
case_table = params['CASE_TABLE'].format(release)
success = attach_barcodes(step2_table,
params['ALIQUOT_TABLE'].format(metadata_rel),
case_table, params['SCRATCH_DATASET'],
barcodes_table, True, params['BQ_AS_BATCH'])
if not success:
print("attach_barcodes_to_ids failed")
return
if 'merge_counts_and_metadata' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
if 'header' not in count_dict:
print("must have defined headers to work")
break
header = count_dict['header']
print(header)
sql_dict = {}
sql_dict['count_column'] = header.split(',')[1].strip()
sql_dict['file_column'] = 'file_gdc_id_{}'.format(count_name)
step3_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
barcodes_table)
counts_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
upload_table.format(count_name))
success = merge_counts_and_metadata(
step3_table, counts_table, params['SCRATCH_DATASET'],
counts_w_metadata_table.format(count_name), True, sql_dict,
params['BQ_AS_BATCH'])
if not success:
print("merge_counts_and_metadata failed")
return
if 'merge_all' in steps:
sql_dict = {}
count = 0
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
dict_for_set = {}
sql_dict['table_{}'.format(count)] = dict_for_set
count += 1
if 'header' not in count_dict:
print("must have defined headers to work")
return
header = count_dict['header']
dict_for_set['count_column'] = header.split(',')[1].strip()
dict_for_set['file_column'] = 'file_gdc_id_{}'.format(count_name)
dict_for_set['table'] = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['SCRATCH_DATASET'],
counts_w_metadata_table.format(count_name))
success = all_counts_to_one_table(params['SCRATCH_DATASET'],
merged_counts_table, True, sql_dict,
params['BQ_AS_BATCH'])
if not success:
print("merge_counts_and_metadata failed")
return
if 'glue_gene_names' in steps:
sql_dict = {}
count = 0
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
dict_for_set = {}
sql_dict['table_{}'.format(count)] = dict_for_set
count += 1
if 'header' not in count_dict:
print("must have defined headers to work")
return
header = count_dict['header']
dict_for_set['count_column'] = header.split(',')[1].strip()
dict_for_set['file_column'] = 'file_gdc_id_{}'.format(count_name)
three_counts_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
merged_counts_table)
success = glue_in_gene_names(three_counts_table,
params['GENE_NAMES_TABLE'],
params['SCRATCH_DATASET'],
draft_table.format(release), True,
sql_dict, params['BQ_AS_BATCH'])
if not success:
print("glue_gene_names failed")
return
#
# Create second table
#
if 'create_current_table' in steps:
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
draft_table.format(release))
current_dest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
draft_table.format('current'))
success = publish_table(source_table, current_dest)
if not success:
print("create current table failed")
return
#
# The derived table we generate has no field descriptions. Add them from the github json files:
#
for table in update_schema_tables:
schema_release = 'current' if table == 'current' else release
if 'update_final_schema' in steps:
success = update_schema(params['SCRATCH_DATASET'],
draft_table.format(schema_release),
hold_schema_dict.format('counts'))
if not success:
print("Schema update failed")
return
#
# Add description and labels to the target table:
#
if 'add_table_description' in steps:
print('update_table_description')
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'], draft_table.format(schema_release))
success = install_labels_and_desc(
params['SCRATCH_DATASET'], draft_table.format(schema_release),
full_file_prefix)
if not success:
print("update_table_description failed")
return
#
# compare and remove old current table
#
# compare the two tables
if 'compare_remove_old_current' in steps:
old_current_table = '{}.{}.{}'.format(
params['PUBLICATION_PROJECT'], params['PUBLICATION_DATASET'],
publication_table.format('current'))
previous_ver_table = '{}.{}.{}'.format(
params['PUBLICATION_PROJECT'],
"_".join([params['PUBLICATION_DATASET'], 'versioned']),
publication_table.format("".join(
["r", str(params['PREVIOUS_RELEASE'])])))
table_temp = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['SCRATCH_DATASET'], "_".join([
params['PROGRAM'],
publication_table.format("".join(
["r", str(params['PREVIOUS_RELEASE'])])), 'backup'
]))
print('Compare {} to {}'.format(old_current_table, previous_ver_table))
compare = compare_two_tables(old_current_table, previous_ver_table,
params['BQ_AS_BATCH'])
num_rows = compare.total_rows
if num_rows == 0:
print('the tables are the same')
else:
print('the tables are NOT the same and differ by {} rows'.format(
num_rows))
if not compare:
print('compare_tables failed')
return
# move old table to a temporary location
elif compare and num_rows == 0:
print('Move old table to temp location')
table_moved = publish_table(old_current_table, table_temp)
if not table_moved:
print('Old Table was not moved and will not be deleted')
# remove old table
elif table_moved:
print('Deleting old table: {}'.format(old_current_table))
delete_table = delete_table_bq_job(
params['PUBLICATION_DATASET'],
publication_table.format('current'))
if not delete_table:
print('delete table failed')
return
#
# publish table:
#
if 'publish' in steps:
print('publish tables')
tables = ['versioned', 'current']
for table in tables:
if table == 'versioned':
print(table)
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
draft_table.format(release))
publication_dest = '{}.{}.{}'.format(
params['PUBLICATION_PROJECT'],
"_".join([params['PUBLICATION_DATASET'], 'versioned']),
publication_table.format(release))
elif table == 'current':
print(table)
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['SCRATCH_DATASET'],
draft_table.format('current'))
publication_dest = '{}.{}.{}'.format(
params['PUBLICATION_PROJECT'],
params['PUBLICATION_DATASET'],
publication_table.format('current'))
success = publish_table(source_table, publication_dest)
if not success:
print("publish table failed")
return
#
# Update previous versioned table with archived tag
#
if 'update_status_tag' in steps:
print('Update previous table')
success = update_status_tag(
"_".join([params['PUBLICATION_DATASET'], 'versioned']),
publication_table.format("".join(
["r", str(params['PREVIOUS_RELEASE'])])), 'archived')
if not success:
print("update status tag table failed")
return
if 'dump_working_tables' in steps:
dump_tables = [
files_to_case_table, files_to_case_w_plat_table, barcodes_table,
counts_w_metadata_table, merge_counts_and_metadata,
merged_counts_table, draft_table
]
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
dump_tables.append(upload_table.format(count_name))
dump_tables.append(counts_w_metadata_table.format(count_name))
dump_tables.append(manifest_table.format(count_name))
dump_tables.append(pull_list_table.format(count_name))
table_cleaner(dump_tables, False)
#
# archive files on VM:
#
bucket_archive_blob_sets = {}
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
bucket_target_blob_sets[count_name] = '{}/{}-{}-{}-{}'.format(
params['ARCHIVE_BUCKET_DIR'], params['DATE'], params['PROGRAM'],
params['DATA_TYPE'], release, count_name)
if 'archive' in steps:
print('archive files from VM')
archive_file_prefix = "{}_{}".format(date.today(),
params['PUBLICATION_DATASET'])
if params['ARCHIVE_YAML']:
yaml_file = re.search(r"\/(\w*.yaml)$", args[1])
archive_yaml = "{}/{}/{}_{}".format(params['ARCHIVE_BUCKET_DIR'],
params['ARCHIVE_CONFIG'],
archive_file_prefix,
yaml_file.group(1))
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_yaml, args[1])
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
pull_file_name = params['LOCAL_PULL_LIST']
archive_pull_file = "{}/{}_{}".format(
params['ARCHIVE_BUCKET_DIR'], archive_file_prefix,
pull_file_name.format(count_name))
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_pull_file,
local_pull_list.format(count_name))
manifest_file_name = params['MANIFEST_FILE']
archive_manifest_file = "{}/{}_{}".format(
params['ARCHIVE_BUCKET_DIR'], archive_file_prefix,
manifest_file_name.format(count_name))
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_manifest_file,
manifest_file.format(count_name))
print('job completed')
def main(args):
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, filters, bq_filters, steps, extra_cols, key_fields, callers = load_config(
yaml_file.read())
if params is None:
print("Bad YAML load")
return
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
hold_scraped_dict = "{}/{}".format(home, params['HOLD_SCRAPED_DICT'])
AUGMENTED_SCHEMA_FILE = "SchemaFiles/augmented_schema_list.json"
#
# Empirical evidence suggests this workflow is going to be very memory hungry if you are doing
# merging, and requires at least 26 GB to be safe. Confirm that before starting!
#
do_merging = params['DO_MERGED_OUTPUT']
if do_merging:
meminfo = dict((i.split()[0].rstrip(':'), int(i.split()[1]))
for i in open('/proc/meminfo').readlines())
mem_kib = meminfo['MemTotal']
print("Machine memory: {}".format(mem_kib))
if int(mem_kib) < 26000000:
print("Job requires at least 26 GB physical memory to complete")
return
#
# Next, use the filter set to get a manifest from GDC using their API. Note that is a pull list is
# provided, these steps can be omitted:
#
if 'build_manifest_from_filters' in steps:
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(
params['FILE_TABLE'], bq_filters, max_files,
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_MANIFEST_TSV'], manifest_file,
params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# Best practice is to clear out the directory where the files are going. Don't want anything left over:
#
if 'clear_target_directory' in steps:
create_clean_target(local_files_dir)
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, you can do it using IndexD calls on a manifest file, OR using BQ as long as you have
# built the manifest using BQ (that route uses the BQ Manifest table that was created).
#
if 'build_pull_list' in steps:
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'])
build_pull_list_with_bq(
full_manifest, params['INDEXD_BQ_TABLE'],
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_PULL_LIST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_PULL_LIST'], local_pull_list, params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets, not "downloading". Get the files in the pull list:
#
if 'download_from_gdc' in steps:
with open(local_pull_list, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
pull_from_buckets(pull_list, local_files_dir)
#
# Traverse the tree of downloaded files and create a flat list of all files:
#
if 'build_traversal_list' in steps:
all_files = build_file_list(local_files_dir)
program_list = build_program_list(all_files)
if not check_caller_list(all_files, callers):
print("Unexpected caller mismatch! Expecting {}".format(callers))
return
with open(file_traversal_list, mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
#
# We can create either a table that merges identical mutations from the different callers into
# one row, or keep them separate:
#
if do_merging:
do_debug = params['DO_DEBUG_LOGGING']
target_count = int(params['EXPECTED_COLUMNS'])
for program in program_list:
print("Look at MAFS for {}".format(program))
if 'run_maf_reader' in steps:
with open(file_traversal_list,
mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
print("Start reading MAFS for {}".format(program))
mut_calls, hdr_pick = read_MAFs(program, all_files,
params['PROGRAM_PREFIX'],
extra_cols, target_count,
do_debug, key_fields,
params['FIRST_MAF_COL'],
file_info)
print("Finish reading MAFS for {}".format(program))
if 'run_maf_writer' in steps:
print("Start writing MAFS for {}".format(program))
hist_count = write_MAFs(program, mut_calls, hdr_pick, callers,
do_debug)
for ii in range(len(hist_count)):
if hist_count[ii] > 0:
print(" %6d %9d " % (ii, hist_count[ii]))
print("Finish writing MAFS for {}".format(program))
#
# Take all the files and make one BIG TSV file to upload:
#
if 'concat_all_files' in steps:
if do_merging:
maf_list = ["mergeA." + tumor + ".maf" for tumor in program_list]
concat_all_merged_files(maf_list, one_big_tsv)
else:
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files(all_files, one_big_tsv, params['PROGRAM_PREFIX'],
extra_cols, file_info)
#
# Scrape the column descriptions from the GDC web page
#
if 'scrape_schema' in steps:
scrape_list = scrape_schema(params['MAF_URL'], params['FIRST_MAF_COL'])
with open(hold_scraped_dict, mode='w') as scraped_hold_list:
scraped_hold_list.write(json_dumps(scrape_list))
#
# For the legacy table, the descriptions had lots of analysis tidbits. Very nice, but hard to maintain.
# We just use hardwired schema descriptions now, most directly pulled from the GDC website:
#
if 'build_the_schema' in steps:
typing_tups = build_schema(one_big_tsv, params['SCHEMA_SAMPLE_SKIPS'])
build_combined_schema(hold_scraped_dict, AUGMENTED_SCHEMA_FILE,
typing_tups, hold_schema_list, hold_schema_dict)
#
# Upload the giant TSV into a cloud bucket:
#
if 'upload_to_bucket' in steps:
upload_to_bucket(params['WORKING_BUCKET'], params['BUCKET_SKEL_TSV'],
one_big_tsv)
#
# Create the BQ table from the TSV:
#
if 'create_bq_from_tsv' in steps:
bucket_src_url = 'gs://{}/{}'.format(params['WORKING_BUCKET'],
params['BUCKET_SKEL_TSV'])
with open(hold_schema_list, mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq(typed_schema, bucket_src_url, params['TARGET_DATASET'],
params['SKELETON_TABLE'], params['BQ_AS_BATCH'])
#
# Need to merge in aliquot and sample barcodes from other tables:
#
if 'collect_barcodes' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['SKELETON_TABLE'])
success = attach_aliquot_ids(skel_table, params['FILE_TABLE'],
params['TARGET_DATASET'],
params['BARCODE_STEP_1_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("attach_aliquot_ids job failed")
return
step_1_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BARCODE_STEP_1_TABLE'])
success = attach_barcodes(step_1_table, params['ALIQUOT_TABLE'],
params['TARGET_DATASET'],
params['BARCODE_STEP_2_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("attach_barcodes job failed")
return
#
# Merge the barcode info into the final table we are building:
#
if 'create_final_table' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['SKELETON_TABLE'])
barcodes_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BARCODE_STEP_2_TABLE'])
success = final_merge(skel_table, barcodes_table,
params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("Join job failed")
return
#
# The derived table we generate has no field descriptions. Add them from the scraped page:
#
if 'update_final_schema' in steps:
success = update_schema(params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'], hold_schema_dict)
if not success:
print("Schema update failed")
return
#
# Add the table description:
#
if 'add_table_description' in steps:
desc = params['TABLE_DESCRIPTION'].format(params['MAF_URL'])
update_description(params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'], desc)
#
# Clear out working temp tables:
#
if 'dump_working_tables' in steps:
dump_table_tags = [
'SKELETON_TABLE', 'BARCODE_STEP_1_TABLE', 'BARCODE_STEP_2_TABLE',
'BQ_MANIFEST_TABLE', 'BQ_PULL_LIST_TABLE'
]
dump_tables = [params[x] for x in dump_table_tags]
for table in dump_tables:
delete_table_bq_job(params['TARGET_DATASET'], table)
#
# Done!
#
print('job completed')
def main(args):
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, file_sets, steps = load_config(yaml_file.read())
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
if 'clear_target_directory' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
create_clean_target(local_files_dir.format(count_name))
if 'build_manifest_from_filters' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
mani_for_count = manifest_file.format(count_name)
table_for_count = params['BQ_MANIFEST_TABLE'].format(count_name)
tsv_for_count = params['BUCKET_MANIFEST_TSV'].format(count_name)
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(
params['FILE_TABLE'], count_dict['filters'], max_files,
params['WORKING_PROJECT'], params['TARGET_DATASET'],
table_for_count, params['WORKING_BUCKET'], tsv_for_count,
mani_for_count, params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, uses BQ as long as you have built the manifest using BQ (that route uses the BQ Manifest
# table that was created).
#
if 'build_pull_list' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
table_for_count = params['BQ_MANIFEST_TABLE'].format(count_name)
local_pull_for_count = local_pull_list.format(count_name)
pull_table_for_count = params['BQ_PULL_LIST_TABLE'].format(
count_name)
bucket_pull_list_for_count = params['BUCKET_PULL_LIST'].format(
count_name)
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
table_for_count)
build_pull_list_with_bq(
full_manifest, params['INDEXD_BQ_TABLE'],
params['WORKING_PROJECT'], params['TARGET_DATASET'],
pull_table_for_count, params['WORKING_BUCKET'],
bucket_pull_list_for_count, local_pull_for_count,
params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets. Get the files in the pull list:
#
if 'download_from_gdc' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
pull_for_count = local_pull_list.format(count_name)
with open(pull_for_count, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preparing to download %s files from buckets\n" %
len(pull_list))
bp = BucketPuller(10)
local_files_dir_for_count = local_files_dir.format(count_name)
bp.pull_from_buckets(pull_list, local_files_dir_for_count)
if 'build_file_list' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
local_files_dir_for_count = local_files_dir.format(count_name)
all_files = build_file_list(local_files_dir_for_count)
file_traversal_list_for_count = file_traversal_list.format(
count_name)
with open(file_traversal_list_for_count,
mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
if 'concat_all_files' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
header = count_dict['header'] if 'header' in count_dict else None
file_traversal_list_for_count = file_traversal_list.format(
count_name)
with open(file_traversal_list_for_count,
mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files(all_files, one_big_tsv.format(count_name),
header)
#
# Schemas and table descriptions are maintained in the github repo:
#
if 'pull_table_info_from_git' in steps:
print('pull_table_info_from_git')
try:
create_clean_target(params['SCHEMA_REPO_LOCAL'])
repo = Repo.clone_from(params['SCHEMA_REPO_URL'],
params['SCHEMA_REPO_LOCAL'])
repo.git.checkout(params['SCHEMA_REPO_BRANCH'])
except Exception as ex:
print("pull_table_info_from_git failed: {}".format(str(ex)))
return
if 'process_git_schemas' in steps:
print('process_git_schema')
# Where do we dump the schema git repository?
schema_file = "{}/{}/{}".format(params['SCHEMA_REPO_LOCAL'],
params['RAW_SCHEMA_DIR'],
params['SCHEMA_FILE_NAME'])
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'],
params['FINAL_TARGET_TABLE'])
# Write out the details
success = generate_table_detail_files(schema_file, full_file_prefix)
if not success:
print("process_git_schemas failed")
return
if 'analyze_the_schema' in steps:
print('analyze_the_schema')
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
typing_tups = build_schema(one_big_tsv.format(count_name),
params['SCHEMA_SAMPLE_SKIPS'])
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'],
params['FINAL_TARGET_TABLE'])
schema_dict_loc = "{}_schema.json".format(full_file_prefix)
build_combined_schema(None, schema_dict_loc, typing_tups,
hold_schema_list.format(count_name),
hold_schema_dict.format(count_name))
bucket_target_blob_sets = {}
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
bucket_target_blob_sets[count_name] = '{}/{}'.format(
params['WORKING_BUCKET_DIR'],
params['BUCKET_TSV'].format(count_name))
if 'upload_to_bucket' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
upload_to_bucket(params['WORKING_BUCKET'],
bucket_target_blob_sets[count_name],
one_big_tsv.format(count_name))
if 'delete_all_bq' in steps:
table_cleaner(params, file_sets, True)
if 'create_bq_from_tsv' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
bucket_src_url = 'gs://{}/{}'.format(
params['WORKING_BUCKET'], bucket_target_blob_sets[count_name])
hold_schema_list_for_count = hold_schema_list.format(count_name)
with open(hold_schema_list_for_count,
mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq_write_depo(typed_schema, bucket_src_url,
params['TARGET_DATASET'],
params['TARGET_TABLE'].format(count_name),
params['BQ_AS_BATCH'], None)
if 'attach_ids_to_files' in steps:
count = 0
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
write_depo = "WRITE_TRUNCATE" if (count == 0) else "WRITE_APPEND"
gexp_table = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['TARGET_TABLE'].format(count_name))
success = build_aliquot_and_case(
gexp_table, params['FILEDATA_TABLE'], params['TARGET_DATASET'],
params['STEP_2_TABLE'], write_depo, {}, params['BQ_AS_BATCH'])
count += 1
if not success:
print("attach_ids_to_files failed")
return
if 'extract_platform' in steps:
step2_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['STEP_2_TABLE'])
success = extract_platform_for_files(step2_table,
params['FILEDATA_TABLE'],
params['TARGET_DATASET'],
params['STEP_2A_TABLE'], True, {},
params['BQ_AS_BATCH'])
if not success:
print("extract_platform failed")
return
if 'attach_barcodes_to_ids' in steps:
step2_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['STEP_2A_TABLE'])
success = attach_barcodes(step2_table, params['ALIQUOT_TABLE'],
params['TARGET_DATASET'],
params['STEP_3_TABLE'], True, {},
params['BQ_AS_BATCH'])
if not success:
print("attach_barcodes_to_ids failed")
return
if 'merge_counts_and_metadata' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
if 'header' not in count_dict:
print("must have defined headers to work")
break
header = count_dict['header']
print(header)
sql_dict = {}
sql_dict['count_column'] = header.split(',')[1].strip()
sql_dict['file_column'] = 'file_gdc_id_{}'.format(count_name)
step3_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['STEP_3_TABLE'])
counts_table = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['TARGET_TABLE'].format(count_name))
success = merge_counts_and_metadata(
step3_table, counts_table, params['TARGET_DATASET'],
params['COUNTS_WITH_METADATA_TABLE'].format(count_name), True,
sql_dict, params['BQ_AS_BATCH'])
if not success:
print("merge_counts_and_metadata failed")
return
if 'merge_all' in steps:
sql_dict = {}
count = 0
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
dict_for_set = {}
sql_dict['table_{}'.format(count)] = dict_for_set
count += 1
if 'header' not in count_dict:
print("must have defined headers to work")
return
header = count_dict['header']
dict_for_set['count_column'] = header.split(',')[1].strip()
dict_for_set['file_column'] = 'file_gdc_id_{}'.format(count_name)
dict_for_set['table'] = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['COUNTS_WITH_METADATA_TABLE'].format(count_name))
success = all_counts_to_one_table(params['TARGET_DATASET'],
params['THREE_COUNTS_TABLE'], True,
sql_dict, params['BQ_AS_BATCH'])
if not success:
print("merge_counts_and_metadata failed")
return
if 'glue_gene_names' in steps:
sql_dict = {}
count = 0
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
dict_for_set = {}
sql_dict['table_{}'.format(count)] = dict_for_set
count += 1
if 'header' not in count_dict:
print("must have defined headers to work")
return
header = count_dict['header']
dict_for_set['count_column'] = header.split(',')[1].strip()
dict_for_set['file_column'] = 'file_gdc_id_{}'.format(count_name)
three_counts_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['THREE_COUNTS_TABLE'])
success = glue_in_gene_names(three_counts_table,
params['GENE_NAMES_TABLE'],
params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'], True,
sql_dict, params['BQ_AS_BATCH'])
if not success:
print("glue_gene_names failed")
return
#
# Update the per-field descriptions:
#
if 'update_field_descriptions' in steps:
print('update_field_descriptions')
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'],
params['FINAL_TARGET_TABLE'])
schema_dict_loc = "{}_schema.json".format(full_file_prefix)
schema_dict = {}
with open(schema_dict_loc, mode='r') as schema_hold_dict:
full_schema_list = json_loads(schema_hold_dict.read())
for entry in full_schema_list:
schema_dict[entry['name']] = {'description': entry['description']}
success = update_schema_with_dict(params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
schema_dict)
if not success:
print("update_field_descriptions failed")
return
#
# Add description and labels to the target table:
#
if 'update_table_description' in steps:
print('update_table_description')
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'],
params['FINAL_TARGET_TABLE'])
success = install_labels_and_desc(params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
full_file_prefix)
if not success:
print("update_table_description failed")
return
if 'dump_working_tables' in steps:
table_cleaner(params, file_sets, False)
#
# archive files on VM:
#
bucket_archive_blob_sets = {}
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
bucket_target_blob_sets[count_name] = '{}/{}'.format(
params['ARCHIVE_BUCKET_DIR'],
params['BUCKET_TSV'].format(count_name))
if 'archive' in steps:
print('archive files from VM')
archive_file_prefix = "{}_{}".format(date.today(),
params['PUBLICATION_DATASET'])
yaml_file = re.search(r"\/(\w*.yaml)$", args[1])
archive_yaml = "{}/{}/{}_{}".format(params['ARCHIVE_BUCKET_DIR'],
params['ARCHIVE_CONFIG'],
archive_file_prefix,
yaml_file.group(1))
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_yaml, args[1])
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
pull_file_name = params['LOCAL_PULL_LIST']
archive_pull_file = "{}/{}_{}".format(
params['ARCHIVE_BUCKET_DIR'], archive_file_prefix,
pull_file_name.format(count_name))
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_pull_file,
local_pull_list.format(count_name))
manifest_file_name = params['MANIFEST_FILE']
archive_manifest_file = "{}/{}_{}".format(
params['ARCHIVE_BUCKET_DIR'], archive_file_prefix,
manifest_file_name.format(count_name))
upload_to_bucket(params['ARCHIVE_BUCKET'], archive_manifest_file,
manifest_file.format(count_name))
#
# publish table:
#
if 'publish' in steps:
source_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'])
publication_dest = '{}.{}.{}'.format(params['PUBLICATION_PROJECT'],
params['PUBLICATION_DATASET'],
params['PUBLICATION_TABLE'])
success = publish_table(source_table, publication_dest)
if not success:
print("publish table failed")
return
print('job completed')
def main(args):
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, bq_filters, steps = load_config(yaml_file.read())
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
# Schema that describes CNVR table:
AUGMENTED_SCHEMA_FILE = "SchemaFiles/cnvr_augmented_schema_list.json"
#
# Use the filter set to get a manifest from GDC using their API. Note that if a pull list is
# provided, these steps can be omitted:
#
if 'build_manifest_from_filters' in steps:
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(
params['FILE_TABLE'], bq_filters, max_files,
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_MANIFEST_TSV'], manifest_file,
params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
if 'clear_target_directory' in steps:
create_clean_target(local_files_dir)
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, uses BQ as long as you have built the manifest using BQ (that route uses the BQ Manifest
# table that was created).
#
if 'build_pull_list' in steps:
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'])
build_pull_list_with_bq(
full_manifest, params['INDEXD_BQ_TABLE'],
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_PULL_LIST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_PULL_LIST'], local_pull_list, params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets. Get the files in the pull list:
#
if 'download_from_gdc' in steps:
with open(local_pull_list, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preparing to download %s files from buckets\n" % len(pull_list))
bp = BucketPuller(10)
bp.pull_from_buckets(pull_list, local_files_dir)
if 'build_file_list' in steps:
all_files = build_file_list(local_files_dir)
with open(file_traversal_list, mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
if 'concat_all_files' in steps:
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files(all_files, one_big_tsv)
if 'build_the_schema' in steps:
typing_tups = build_schema(one_big_tsv, params['SCHEMA_SAMPLE_SKIPS'])
build_combined_schema(None, AUGMENTED_SCHEMA_FILE, typing_tups,
hold_schema_list, hold_schema_dict)
bucket_target_blob = '{}/{}'.format(params['WORKING_BUCKET_DIR'],
params['BUCKET_TSV'])
if 'upload_to_bucket' in steps:
upload_to_bucket(params['WORKING_BUCKET'], bucket_target_blob,
params['ONE_BIG_TSV'])
if 'create_bq_from_tsv' in steps:
bucket_src_url = 'gs://{}/{}'.format(params['WORKING_BUCKET'],
bucket_target_blob)
with open(hold_schema_list, mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq(typed_schema, bucket_src_url, params['TARGET_DATASET'],
params['TARGET_TABLE'], params['BQ_AS_BATCH'])
if 'add_aliquot_fields' in steps:
full_target_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['TARGET_TABLE'])
success = join_with_aliquot_table(full_target_table,
params['ALIQUOT_TABLE'],
params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("Join job failed")
#
# Clear out working temp tables:
#
if 'dump_working_tables' in steps:
dump_table_tags = ['TARGET_TABLE']
dump_tables = [params[x] for x in dump_table_tags]
for table in dump_tables:
delete_table_bq_job(params['TARGET_DATASET'], table)
print('job completed')
def main(args):
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, bq_filters, steps, extra_cols = load_config(yaml_file.read())
if params is None:
print("Bad YAML load")
return
# Schema that describes table columns:
AUGMENTED_SCHEMA_FILE = "SchemaFiles/isoform_augmented_schema_list.json"
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
#
# Use the filter set to get a manifest from GDC using their API. Note that is a pull list is
# provided, these steps can be omitted:
#
if 'build_manifest_from_filters' in steps:
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(
params['FILE_TABLE'], bq_filters, max_files,
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_MANIFEST_TSV'], manifest_file,
params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# Best practice is to clear out the directory where the files are going. Don't want anything left over:
#
if 'clear_target_directory' in steps:
create_clean_target(local_files_dir)
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, uses BQ as long as you have built the manifest using BQ (that route uses the BQ Manifest
# table that was created).
#
if 'build_pull_list' in steps:
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BQ_MANIFEST_TABLE'])
build_pull_list_with_bq(
full_manifest, params['INDEXD_BQ_TABLE'],
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['BQ_PULL_LIST_TABLE'], params['WORKING_BUCKET'],
params['BUCKET_PULL_LIST'], local_pull_list, params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets. Get the files in the pull list:
#
if 'download_from_gdc' in steps:
with open(local_pull_list, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preparing to download %s files from buckets\n" % len(pull_list))
bp = BucketPuller(10)
bp.pull_from_buckets(pull_list, local_files_dir)
#
# Traverse the tree of downloaded files and create a flat list of all files:
#
if 'build_traversal_list' in steps:
all_files = build_file_list(local_files_dir)
with open(file_traversal_list, mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
#
# Take all the files and make one BIG TSV file to upload:
#
if 'concat_all_files' in steps:
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files(all_files, one_big_tsv, params['PROGRAM_PREFIX'],
extra_cols, file_info, split_col_func)
#
# For the legacy table, the descriptions had lots of analysis tidbits. Very nice, but hard to maintain.
# We just use hardwired schema descriptions now, most directly pulled from the GDC website:
#
if 'build_the_schema' in steps:
typing_tups = build_schema(one_big_tsv, params['SCHEMA_SAMPLE_SKIPS'])
build_combined_schema(None, AUGMENTED_SCHEMA_FILE, typing_tups,
hold_schema_list, hold_schema_dict)
#
# Upload the giant TSV into a cloud bucket:
#
if 'upload_to_bucket' in steps:
upload_to_bucket(params['WORKING_BUCKET'], params['BUCKET_SKEL_TSV'],
one_big_tsv)
#
# Create the BQ table from the TSV:
#
if 'create_bq_from_tsv' in steps:
bucket_src_url = 'gs://{}/{}'.format(params['WORKING_BUCKET'],
params['BUCKET_SKEL_TSV'])
with open(hold_schema_list, mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq(typed_schema, bucket_src_url, params['TARGET_DATASET'],
params['SKELETON_TABLE'], params['BQ_AS_BATCH'])
#
# Need to merge in aliquot and sample barcodes from other tables:
#
if 'collect_barcodes' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['SKELETON_TABLE'])
success = attach_aliquot_ids(skel_table, params['FILE_TABLE'],
params['TARGET_DATASET'],
params['BARCODE_STEP_1_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("attach_aliquot_ids job failed")
return
step_1_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BARCODE_STEP_1_TABLE'])
success = attach_barcodes(step_1_table, params['ALIQUOT_TABLE'],
params['TARGET_DATASET'],
params['BARCODE_STEP_2_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("attach_barcodes job failed")
return
#
# Merge the barcode info into the final table we are building:
#
if 'create_final_table' in steps:
skel_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['SKELETON_TABLE'])
barcodes_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['BARCODE_STEP_2_TABLE'])
success = final_merge(skel_table, barcodes_table,
params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
params['BQ_AS_BATCH'])
if not success:
print("Join job failed")
return
#
# The derived table we generate has no field descriptions. Add them from the scraped page:
#
if 'update_final_schema' in steps:
success = update_schema(params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'], hold_schema_dict)
if not success:
print("Schema update failed")
return
#
# Add the table description:
#
if 'add_table_description' in steps:
update_description(params['TARGET_DATASET'],
params['FINAL_TARGET_TABLE'],
params['TABLE_DESCRIPTION'])
#
# Clear out working temp tables:
#
if 'dump_working_tables' in steps:
dump_table_tags = [
'SKELETON_TABLE', 'BARCODE_STEP_1_TABLE', 'BARCODE_STEP_2_TABLE',
'BQ_MANIFEST_TABLE', 'BQ_PULL_LIST_TABLE'
]
dump_tables = [params[x] for x in dump_table_tags]
for table in dump_tables:
delete_table_bq_job(params['TARGET_DATASET'], table)
#
# Done!
#
print('job completed')
def main(args):
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, steps = load_config(yaml_file.read())
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
local_file = "{}/{}".format(home, params['DOWNLOAD_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
if 'clear_target_directory' in steps:
print('clear_target_directory')
create_clean_target(local_files_dir)
if 'build_pull_list' in steps:
bucket_to_local(params['WORKING_BUCKET'], params['COSMIC_FILE'],
local_file)
print('build_pull_list')
success = build_pull_list_from_txt(local_file, local_pull_list,
params['VERSION'])
if not success:
print("Build pull list failed")
return
if 'download_from_cosmic' in steps:
print("Download from Sanger")
with open(local_pull_list, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preaparing to download {} files from AWS buckets\n".format(
len(pull_list)))
for line in pull_list:
file_name, url = line.split('\t')
file_location = ''.join([local_files_dir, "/", file_name])
with open(file_location, mode='wb') as data_file:
response = requests.get(url)
if response.status_code == 200:
data_file.write(response.content)
# add an unzip step & dump zip file
else:
print("Download failed. Problem downloading {}".format(
file_name))
return
file, ext = os.path.splitext(file_name.split('/')[-1])
new_file_location = ''.join([local_files_dir, "/", file])
if ext == ".gz":
# Unzip the file and remove zip file
print("Uncompressing {}".format(file))
with gzip.open(file_location, "rb") as gzip_in:
with open(new_file_location, "wb") as uncomp_out:
shutil.copyfileobj(gzip_in, uncomp_out)
os.remove(file_location)
else:
print("{} doesn't need to be uncompressed".format(file))
if 'build_file_list' in steps:
print('build_file_list')
all_files = build_file_list(local_files_dir)
with open(file_traversal_list, mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
#
# Schemas and table descriptions are maintained in the github repo:
#
if 'pull_table_info_from_git' in steps:
print('pull_table_info_from_git')
try:
create_clean_target(params['SCHEMA_REPO_LOCAL'])
repo = Repo.clone_from(params['SCHEMA_REPO_URL'],
params['SCHEMA_REPO_LOCAL'])
repo.git.checkout(params['SCHEMA_REPO_BRANCH'])
except Exception as ex:
print("pull_table_info_from_git failed: {}".format(str(ex)))
return
if 'process_and_create_schema' in steps:
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
for line in all_files:
file_name, ext = os.path.splitext(line.split('/')[-1])
file_components = file_name.split("_")
data_type = "_".join(file_components[0:(len(file_components) - 2)])
version = ''.join(['VERSION ', file_components[-1]])
hg = 'hg19' if file_components[-2] == 'GRCh37' else 'hg38'
schema_tags = {
'---tag-ref-genome-0---': hg,
'---tag-release---': version
}
if 'process_git_schemas' in steps:
print('process_git_schema: {}'.format(line))
# Where do we dump the schema git repository?
schema_file_name = ''.join([data_type, ".json"])
print("schema_file_name: " + schema_file_name)
schema_file = "{}/{}/{}".format(params['SCHEMA_REPO_LOCAL'],
params['RAW_SCHEMA_DIR'],
schema_file_name)
full_file_prefix = "{}/{}".format(params['PROX_DESC_PREFIX'],
schema_file_name)
print(schema_file + "\t" + full_file_prefix)
# Write out the details
success = generate_table_detail_files(schema_file,
full_file_prefix)
if not success:
print("process_git_schemas failed")
return
# Customize generic schema to this data program:
if 'replace_schema_tags' in steps:
print('replace_schema_tags')
version = ''.join(['VERSION ', file_components[-1]])
hg = 'hg19' if file_components[-2] == 'GRCh37' else 'hg38'
schema_tags = {
'---tag-ref-genome-0---': hg,
'---tag-release---': version
}
tag_map_list = []
for tag in schema_tags:
use_pair = {tag: schema_tags[tag]}
tag_map_list.append(use_pair)
full_file_prefix = "{}/{}".format(
params['PROX_DESC_PREFIX'], '_'.join(file_components[:-2]))
# Write out the details
success = customize_labels_and_desc(full_file_prefix,
tag_map_list)
if not success:
print("replace_schema_tags failed")
return
# Create BQ tables
if 'create_bq_tables' in steps:
with open(file_traversal_list, mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
for line in all_files:
file = line.split('/')[-1]
file_name, ext = os.path.splitext(file)
file_components = file_name.split("_")
data_type = "_".join(file_components[0:(len(file_components) - 2)])
bucket_target_blob = '{}/{}'.format(params['WORKING_BUCKET_DIR'],
file)
if 'upload_to_bucket' in steps:
print('upload_to_bucket')
upload_to_bucket(params['WORKING_BUCKET'], bucket_target_blob,
line)
def main(args):
if not confirm_google_vm():
print(
'This job needs to run on a Google Cloud Compute Engine to avoid storage egress charges [EXITING]'
)
return
if len(args) != 2:
print(" ")
print(" Usage : {} <configuration_yaml>".format(args[0]))
return
print('job started')
#
# Get the YAML config loaded:
#
with open(args[1], mode='r') as yaml_file:
params, file_sets, steps = load_config(yaml_file.read())
#
# BQ does not like to be given paths that have "~". So make all local paths absolute:
#
home = expanduser("~")
local_files_dir = "{}/{}".format(home, params['LOCAL_FILES_DIR'])
one_big_tsv = "{}/{}".format(home, params['ONE_BIG_TSV'])
manifest_file = "{}/{}".format(home, params['MANIFEST_FILE'])
local_pull_list = "{}/{}".format(home, params['LOCAL_PULL_LIST'])
file_traversal_list = "{}/{}".format(home, params['FILE_TRAVERSAL_LIST'])
hold_schema_dict = "{}/{}".format(home, params['HOLD_SCHEMA_DICT'])
hold_schema_list = "{}/{}".format(home, params['HOLD_SCHEMA_LIST'])
if 'clear_target_directory' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
create_clean_target(local_files_dir.format(count_name))
if 'build_manifest_from_filters' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
mani_for_count = manifest_file.format(count_name)
table_for_count = params['BQ_MANIFEST_TABLE'].format(count_name)
tsv_for_count = params['BUCKET_MANIFEST_TSV'].format(count_name)
max_files = params['MAX_FILES'] if 'MAX_FILES' in params else None
manifest_success = get_the_bq_manifest(
params['FILE_TABLE'], count_dict['filters'], max_files,
params['WORKING_PROJECT'], params['TARGET_DATASET'],
table_for_count, params['WORKING_BUCKET'], tsv_for_count,
mani_for_count, params['BQ_AS_BATCH'])
if not manifest_success:
print("Failure generating manifest")
return
#
# We need to create a "pull list" of gs:// URLs to pull from GDC buckets. If you have already
# created a pull list, just plunk it in 'LOCAL_PULL_LIST' and skip this step. If creating a pull
# list, uses BQ as long as you have built the manifest using BQ (that route uses the BQ Manifest
# table that was created).
#
if 'build_pull_list' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
table_for_count = params['BQ_MANIFEST_TABLE'].format(count_name)
local_pull_for_count = local_pull_list.format(count_name)
pull_table_for_count = params['BQ_PULL_LIST_TABLE'].format(
count_name)
bucket_pull_list_for_count = params['BUCKET_PULL_LIST'].format(
count_name)
full_manifest = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
table_for_count)
build_pull_list_with_bq(
full_manifest, params['INDEXD_BQ_TABLE'],
params['WORKING_PROJECT'], params['TARGET_DATASET'],
pull_table_for_count, params['WORKING_BUCKET'],
bucket_pull_list_for_count, local_pull_for_count,
params['BQ_AS_BATCH'])
#
# Now hitting GDC cloud buckets. Get the files in the pull list:
#
if 'download_from_gdc' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
pull_for_count = local_pull_list.format(count_name)
with open(pull_for_count, mode='r') as pull_list_file:
pull_list = pull_list_file.read().splitlines()
print("Preparing to download %s files from buckets\n" %
len(pull_list))
bp = BucketPuller(10)
local_files_dir_for_count = local_files_dir.format(count_name)
bp.pull_from_buckets(pull_list, local_files_dir_for_count)
if 'build_file_list' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
local_files_dir_for_count = local_files_dir.format(count_name)
all_files = build_file_list(local_files_dir_for_count)
file_traversal_list_for_count = file_traversal_list.format(
count_name)
with open(file_traversal_list_for_count,
mode='w') as traversal_list:
for line in all_files:
traversal_list.write("{}\n".format(line))
if 'concat_all_files' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
header = count_dict['header'] if 'header' in count_dict else None
file_traversal_list_for_count = file_traversal_list.format(
count_name)
with open(file_traversal_list_for_count,
mode='r') as traversal_list_file:
all_files = traversal_list_file.read().splitlines()
concat_all_files(all_files, one_big_tsv.format(count_name),
header)
if 'build_the_schema' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
typing_tups = build_schema(one_big_tsv.format(count_name),
params['SCHEMA_SAMPLE_SKIPS'])
for tup in typing_tups:
print(tup)
hold_schema_list_for_count = hold_schema_list.format(count_name)
typing_tups_to_schema_list(typing_tups, hold_schema_list_for_count)
#hold_schema_list_for_count = hold_schema_list.format(count_name)
#hold_schema_dict_for_count = hold_schema_dict.format(count_name)
## build_combined_schema(None, AUGMENTED_SCHEMA_FILE,
# typing_tups, hold_schema_list_for_count, hold_schema_dict_for_count)
bucket_target_blob_sets = {}
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
bucket_target_blob_sets[count_name] = '{}/{}'.format(
params['WORKING_BUCKET_DIR'],
params['BUCKET_TSV'].format(count_name))
if 'upload_to_bucket' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
upload_to_bucket(params['WORKING_BUCKET'],
bucket_target_blob_sets[count_name],
one_big_tsv.format(count_name))
if 'delete_all_bq' in steps:
table_cleaner(params, file_sets, True)
if 'create_bq_from_tsv' in steps:
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
bucket_src_url = 'gs://{}/{}'.format(
params['WORKING_BUCKET'], bucket_target_blob_sets[count_name])
hold_schema_list_for_count = hold_schema_list.format(count_name)
with open(hold_schema_list_for_count,
mode='r') as schema_hold_dict:
typed_schema = json_loads(schema_hold_dict.read())
csv_to_bq_write_depo(typed_schema, bucket_src_url,
params['TARGET_DATASET'],
params['TARGET_TABLE'].format(count_name),
params['BQ_AS_BATCH'], None)
if 'attach_ids_to_files' in steps:
count = 0
for file_set in file_sets:
count_name, _ = next(iter(file_set.items()))
write_depo = "WRITE_TRUNCATE" if (count == 0) else "WRITE_APPEND"
gexp_table = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['TARGET_TABLE'].format(count_name))
success = build_aliquot_and_case(
gexp_table, params['FILEDATA_TABLE'], params['TARGET_DATASET'],
params['STEP_2_TABLE'], write_depo, {}, params['BQ_AS_BATCH'])
count += 1
if not success:
print("attach_ids_to_files failed")
return
if 'extract_platform' in steps:
step2_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['STEP_2_TABLE'])
success = extract_platform_for_files(step2_table,
params['FILEDATA_TABLE'],
params['TARGET_DATASET'],
params['STEP_2A_TABLE'], True, {},
params['BQ_AS_BATCH'])
if not success:
print("extract_platform failed")
return
if 'attach_barcodes_to_ids' in steps:
step2_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['STEP_2A_TABLE'])
success = attach_barcodes(step2_table, params['ALIQUOT_TABLE'],
params['TARGET_DATASET'],
params['STEP_3_TABLE'], True, {},
params['BQ_AS_BATCH'])
if not success:
print("attach_barcodes_to_ids failed")
return
if 'merge_counts_and_metadata' in steps:
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
if 'header' not in count_dict:
print("must have defined headers to work")
break
header = count_dict['header']
print(header)
sql_dict = {}
sql_dict['count_column'] = header.split(',')[1].strip()
sql_dict['file_column'] = 'file_gdc_id_{}'.format(count_name)
step3_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['STEP_3_TABLE'])
counts_table = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['TARGET_TABLE'].format(count_name))
success = merge_counts_and_metadata(
step3_table, counts_table, params['TARGET_DATASET'],
params['COUNTS_WITH_METADATA_TABLE'].format(count_name), True,
sql_dict, params['BQ_AS_BATCH'])
if not success:
print("merge_counts_and_metadata failed")
return
if 'merge_all' in steps:
sql_dict = {}
count = 0
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
dict_for_set = {}
sql_dict['table_{}'.format(count)] = dict_for_set
count += 1
if 'header' not in count_dict:
print("must have defined headers to work")
return
header = count_dict['header']
dict_for_set['count_column'] = header.split(',')[1].strip()
dict_for_set['file_column'] = 'file_gdc_id_{}'.format(count_name)
dict_for_set['table'] = '{}.{}.{}'.format(
params['WORKING_PROJECT'], params['TARGET_DATASET'],
params['COUNTS_WITH_METADATA_TABLE'].format(count_name))
success = all_counts_to_one_table(params['TARGET_DATASET'],
params['THREE_COUNTS_TABLE'], True,
sql_dict, params['BQ_AS_BATCH'])
if not success:
print("merge_counts_and_metadata failed")
return
if 'glue_gene_names' in steps:
sql_dict = {}
count = 0
for file_set in file_sets:
count_name, count_dict = next(iter(file_set.items()))
dict_for_set = {}
sql_dict['table_{}'.format(count)] = dict_for_set
count += 1
if 'header' not in count_dict:
print("must have defined headers to work")
return
header = count_dict['header']
dict_for_set['count_column'] = header.split(',')[1].strip()
dict_for_set['file_column'] = 'file_gdc_id_{}'.format(count_name)
three_counts_table = '{}.{}.{}'.format(params['WORKING_PROJECT'],
params['TARGET_DATASET'],
params['THREE_COUNTS_TABLE'])
success = glue_in_gene_names(three_counts_table,
params['GENE_NAMES_TABLE'],
params['TARGET_DATASET'],
params['FINAL_FINAL_TABLE'], True,
sql_dict, params['BQ_AS_BATCH'])
if not success:
print("glue_gene_names failed")
return
if 'dump_working_tables' in steps:
table_cleaner(params, file_sets, False)
print('job completed')