def main():
args = argparser.parse_args()
logger = logging.getLogger('redundancy_tables')
logger.addHandler(logging.StreamHandler())
logger.setLevel(logging.INFO)
# Check that taxon ids or taxon id file were provided.
if not (args.taxon_ids or args.taxon_id_file):
raise Exception("Must provide --taxon-ids or --taxon-id-file option")
# Get taxons.
if args.taxon_ids:
taxon_ids = args.taxon_ids
else:
with open(args.taxon_id_file, 'r') as f:
taxon_ids = [row[0] for row in csv.reader(f)]
logger.info("Taxon Ids: %s" % (taxon_ids))
cur = db.get_psycopg2_cursor()
cur.execute(
"select * from taxon_digest td where td.taxon_id in (select t.id from taxon t where t.id = any(%s));",
(taxon_ids, ))
taxon_digests = []
for record in cur:
td = TaxonDigest(id=record[0], taxon=record[1], digest=record[2])
logger.info("Taxon Digest: %s" % (td.id))
taxon_digests.append(td)
db.psycopg2_connection.commit()
# Generate the redundancy tables.
tables = redundancy.generate_redundancy_tables(taxon_digests,
logger=logger)
# Create output dir if it does not exist.
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
# Output tables.
for table_id, table in list(tables.items()):
table_file = os.path.join(args.output_dir, table_id + '.csv')
logger.info("Writing '%s'..." % table_file)
with open(table_file, 'w', newline='') as f:
w = csv.writer(f)
for row in table:
w.writerow(row)
logger.info("Done.")
def main():
args = argparser.parse_args()
logger = logging.getLogger('redundancy_tables')
logger.addHandler(logging.StreamHandler())
logger.setLevel(logging.INFO)
# Check that taxon ids or taxon id file were provided.
if not (args.taxon_ids or args.taxon_id_file):
raise Exception("Must provide --taxon-ids or --taxon-id-file option")
session = db.get_session()
# Get taxons.
if args.taxon_ids:
taxon_ids = args.taxon_ids
else:
with open(args.taxon_id_file, 'rb') as f:
taxon_ids = [row[0] for row in csv.reader(f)]
# Get the digest.
digest = get_digest(logger, config.DEFAULT_DIGEST_DEFINITION, session)
# Get the TaxonDigests.
taxon_digests = (
session.query(TaxonDigest)
.filter(TaxonDigest.digest == digest)
.join(Taxon)
.filter(Taxon.id.in_(taxon_ids))
).all()
# Generate the redundancy tables.
tables = redundancy.generate_redundancy_tables(
session, taxon_digests, logger=logger)
# Create output dir if it does not exist.
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
# Output tables.
for table_id, table in tables.items():
table_file = os.path.join(args.output_dir, table_id + '.csv')
logger.info("Writing '%s'..." % table_file)
with open(table_file, 'wb') as f:
w = csv.writer(f)
for row in table:
w.writerow(row)
logger.info("Done.")
def main():
args = argparser.parse_args()
logger = logging.getLogger('redundancy_tables')
logger.addHandler(logging.StreamHandler())
logger.setLevel(logging.INFO)
# Check that taxon ids or taxon id file were provided.
if not (args.taxon_ids or args.taxon_id_file):
raise Exception("Must provide --taxon-ids or --taxon-id-file option")
session = db.get_session()
# Get taxons.
if args.taxon_ids:
taxon_ids = args.taxon_ids
else:
with open(args.taxon_id_file, 'rb') as f:
taxon_ids = [row[0] for row in csv.reader(f)]
# Get the digest.
digest = get_digest(logger, config.DEFAULT_DIGEST_DEFINITION, session)
# Get the TaxonDigests.
taxon_digests = (session.query(TaxonDigest).filter(
TaxonDigest.digest == digest).join(Taxon).filter(
Taxon.id.in_(taxon_ids))).all()
# Generate the redundancy tables.
tables = redundancy.generate_redundancy_tables(session,
taxon_digests,
logger=logger)
# Create output dir if it does not exist.
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
# Output tables.
for table_id, table in tables.items():
table_file = os.path.join(args.output_dir, table_id + '.csv')
logger.info("Writing '%s'..." % table_file)
with open(table_file, 'wb') as f:
w = csv.writer(f)
for row in table:
w.writerow(row)
logger.info("Done.")
def test_generate_redundancy_tables(self):
taxon_digests = self.session.query(TaxonDigest).all()
actual = redundancy.generate_redundancy_tables(
session=self.session, taxon_digests=taxon_digests)