def load_singlecore(args):
# create a new gemini loader and populate
# the gemini db and files from the VCF
l = GeminiLoader(args)
l.populate_from_vcf()
if not args.no_genotypes and not args.no_load_genotypes:
l.store_sample_gt_counts()
return l
def load(parser, args):
#if (args.db is None or args.vcf is None):
if args.vcf is None:
parser.print_help()
exit("ERROR: load needs both a VCF file\n")
start_time = time.time()
annos = annotations.get_anno_files( args )
# force skipping CADD and GERP if the data files have not been installed
if args.skip_cadd is False:
if 'cadd_score' not in annos:
sys.stderr.write("\nCADD scores are not being loaded because the"
" annotation file could not be found.\n"
"`Run geminicassandra update --dataonly --extra cadd_score`"
" to install the annotation file.\n\n")
args.skip_cadd = True
else:
sys.stderr.write("CADD scores are being loaded (to skip use:--skip-cadd).\n")
if args.skip_gerp_bp is False:
if 'gerp_bp' not in annos:
sys.stderr.write("\nGERP per bp is not being loaded because the annotation file"
" could not be found.\n Run `geminicassandra update --dataonly --extra gerp_bp`"
" to install the annotation file.\n\n")
args.skip_gerp_bp = True
else:
sys.stderr.write("GERP per bp is being loaded (to skip use:--skip-gerp-bp).\n")
# collect of the the add'l annotation files
annotations.load_annos( args )
time_2 = start_time
time_3 = start_time
if(args.node_num == 1):
gemini_loader = GeminiLoader(args)
gemini_loader.setup_db()
time_2 = time.time()
gemini_loader.single_core_stuff()
time_3 = time.time()
n_variants = 0
if args.cores > 1:
n_variants = load_multicore(args)
else:
n_variants = load_singlecore(args)
insert_n_variants(map(strip, args.contact_points.split(',')), args.keyspace, n_variants)
end_time = time.time()
total_time = str(end_time - start_time)
db_creation_time = str(time_2 - start_time)
single_core_time = str(time_3 - time_2)
parallel_time = str(end_time - time_3)
print "Finished loading in %s s" % total_time
if args.timing_log != None:
with open(args.timing_log, "a") as myfile:
myfile.write(",".join([args.exp_id, total_time, db_creation_time, single_core_time, parallel_time]) + "\n")
def load_singlecore(args):
# create a new gemini loader and populate
# the gemini db and files from the VCF
l = GeminiLoader(args)
l.populate_from_vcf()
if not args.no_genotypes and not args.no_load_genotypes:
l.store_sample_gt_counts()
return l
def load_singlecore(args):
# create a new gemini loader and populate
# the gemini db and files from the VCF
gemini_loader = GeminiLoader(args)
gemini_loader.store_resources()
gemini_loader.store_version()
gemini_loader.store_vcf_header()
gemini_loader.populate_from_vcf()
if not args.skip_gene_tables and not args.test_mode:
gemini_loader.update_gene_table()
if not args.test_mode:
gemini_loader.build_indices_and_disconnect()
if not args.no_genotypes and not args.no_load_genotypes:
gemini_loader.store_sample_gt_counts()
gemini_annotate.add_extras(args.db, [args.db])
def load_singlecore(args):
# create a new gemini loader and populate
# the gemini db and files from the VCF
gemini_loader = GeminiLoader(args)
gemini_loader.store_resources()
gemini_loader.store_version()
gemini_loader.populate_from_vcf()
gemini_loader.build_indices_and_disconnect()
if not args.no_genotypes and not args.no_load_genotypes:
gemini_loader.store_sample_gt_counts()
def load_singlecore(args):
# create a new gemini loader and populate
# the gemini db and files from the VCF
gemini_loader = GeminiLoader(args)
gemini_loader.store_resources()
gemini_loader.store_version()
gemini_loader.populate_from_vcf()
gemini_loader.build_indices_and_disconnect()
if not args.no_genotypes and not args.no_load_genotypes:
gemini_loader.store_sample_gt_counts()
def load_singlecore(args):
# create a new gemini loader and populate
# the gemini db and files from the VCF
gemini_loader = GeminiLoader(args)
gemini_loader.store_resources()
gemini_loader.store_version()
gemini_loader.store_vcf_header()
gemini_loader.populate_from_vcf()
if not args.skip_gene_tables and not args.test_mode:
gemini_loader.update_gene_table()
if not args.test_mode:
gemini_loader.build_indices_and_disconnect()
if not args.no_genotypes and not args.no_load_genotypes:
gemini_loader.store_sample_gt_counts()
gemini_annotate.add_extras(args.db, [args.db])
def finish(args, loader=None):
"""
all things that are performed by single core, multi, ipython
should be done here
"""
if loader is None:
loader = GeminiLoader(args, prepare_db=False)
print "storing version, header, etc."
loader.store_resources()
loader.store_version()
loader.store_vcf_header()
if not args.skip_gene_tables:
print "storing gene-detailed"
loader._get_gene_detailed()
print "storing gene-summary"
loader._get_gene_summary()
if not args.test_mode:
print "updating gene-table"
loader.update_gene_table()
if not args.test_mode:
print "building indices"
loader.build_indices_and_disconnect()
else:
import database
database.close_and_commit(loader.c)
def finish(args, loader=None):
"""
all things that are performed by single core, multi, ipython
should be done here
"""
if loader is None:
loader = GeminiLoader(args, prepare_db=False)
print "storing version, header, etc."
loader.store_resources()
loader.store_version()
loader.store_vcf_header()
if not args.skip_gene_tables:
print "storing gene-detailed"
loader._get_gene_detailed()
print "storing gene-summary"
loader._get_gene_summary()
if not args.test_mode:
print "updating gene-table"
loader.update_gene_table()
if not args.test_mode:
print "building indices"
loader.build_indices_and_disconnect()
else:
import database
database.close_and_commit(loader.c)
def load_singlecore(args):
# create a new geminicassandra loader and populate
# the geminicassandra db and files from the VCF
gemini_loader = GeminiLoader(args)
gemini_loader.connect_to_db()
if not args.no_genotypes and not args.no_load_genotypes:
gemini_loader._init_sample_gt_counts()
gemini_loader.populate_from_vcf()
'''if not args.skip_gene_tables and not args.test_mode:
gemini_loader.update_gene_table()'''
if not args.no_genotypes and not args.no_load_genotypes:
gemini_loader.store_sample_gt_counts()
if not args.test_mode:
gemini_loader.disconnect()
def load_singlecore(args):
# create a new geminicassandra loader and populate
# the geminicassandra db and files from the VCF
gemini_loader = GeminiLoader(args)
gemini_loader.connect_to_db()
if not args.no_genotypes and not args.no_load_genotypes:
gemini_loader._init_sample_gt_counts()
gemini_loader.populate_from_vcf()
'''if not args.skip_gene_tables and not args.test_mode:
gemini_loader.update_gene_table()'''
if not args.no_genotypes and not args.no_load_genotypes:
gemini_loader.store_sample_gt_counts()
if not args.test_mode:
gemini_loader.disconnect()
def load(parser, args):
#if (args.db is None or args.vcf is None):
if args.vcf is None:
parser.print_help()
exit("ERROR: load needs both a VCF file\n")
start_time = time.time()
annos = annotations.get_anno_files(args)
# force skipping CADD and GERP if the data files have not been installed
if args.skip_cadd is False:
if 'cadd_score' not in annos:
sys.stderr.write(
"\nCADD scores are not being loaded because the"
" annotation file could not be found.\n"
"`Run geminicassandra update --dataonly --extra cadd_score`"
" to install the annotation file.\n\n")
args.skip_cadd = True
else:
sys.stderr.write(
"CADD scores are being loaded (to skip use:--skip-cadd).\n")
if args.skip_gerp_bp is False:
if 'gerp_bp' not in annos:
sys.stderr.write(
"\nGERP per bp is not being loaded because the annotation file"
" could not be found.\n Run `geminicassandra update --dataonly --extra gerp_bp`"
" to install the annotation file.\n\n")
args.skip_gerp_bp = True
else:
sys.stderr.write(
"GERP per bp is being loaded (to skip use:--skip-gerp-bp).\n")
# collect of the the add'l annotation files
annotations.load_annos(args)
time_2 = start_time
time_3 = start_time
if (args.node_num == 1):
gemini_loader = GeminiLoader(args)
gemini_loader.setup_db()
time_2 = time.time()
gemini_loader.single_core_stuff()
time_3 = time.time()
n_variants = 0
if args.cores > 1:
n_variants = load_multicore(args)
else:
n_variants = load_singlecore(args)
insert_n_variants(map(strip, args.contact_points.split(',')),
args.keyspace, n_variants)
end_time = time.time()
total_time = str(end_time - start_time)
db_creation_time = str(time_2 - start_time)
single_core_time = str(time_3 - time_2)
parallel_time = str(end_time - time_3)
print "Finished loading in %s s" % total_time
if args.timing_log != None:
with open(args.timing_log, "a") as myfile:
myfile.write(",".join([
args.exp_id, total_time, db_creation_time, single_core_time,
parallel_time
]) + "\n")
