def load_individuals_into_database():
"""launch the various scripts to insert data into the HGDP database."""
from schema.connection import session, metadata
from schema.connection import Individual, Population, SNP, RefSeqGene
# session.flush()
print "now we are connected to the database:", metadata
metadata.bind.echo = True
samples_file = file('../../data/Annotations/samples_subset.csv', 'r')
session.flush()
parsers.samples_parser(samples_file)
session.commit()
print 'upload of tables finished'
def update_individuals(genotypesfile, ):
"""
upload individuals from the rosenberg files.
"""
from schema.connection import session, metadata # is session necessary?
logging.basicConfig(level=logging.DEBUG)
print metadata
# metadata.bind = 'sqlite:///:memory:'
metadata.bind.echo = True
parsers.individuals_genotypesindex_parser(open(genotypesfile, 'r'))
session.commit()
# rosenberg_file = open(rosenberg_path, 'r')
# parsers.rosenberg_parser(rosenberg_file)
print 'fixed individuals.genotypes_index to database %s completed' % metadata
def upload_genotypes(genotypes_by_chr_dir, ):
"""
upload individuals from the rosenberg files.
"""
from schema.connection import session, metadata # is session necessary?
logging.basicConfig(level=logging.DEBUG)
print metadata
# metadata.bind = 'sqlite:///:memory:'
metadata.bind.echo = True
genotypes_by_chr_dir = '/home/gioby/Data/HGDP/Genotypes_by_chr'
for filename in glob.glob(genotypes_by_chr_dir + '/*.geno'):
print filename
parsers.genotypes_parser(open(filename, 'r'))
session.commit()
# rosenberg_file = open(rosenberg_path, 'r')
# parsers.rosenberg_parser(rosenberg_file)
print 'upload of Genotypes to database %s completed' % metadata