parser.add_argument('-mapper_name', type=str, help='Mapper name')
parser.add_argument("-o", "--out", type=str, required=True, help="path to save result folder")
parser.add_argument("-save_name", type=str, required=True, help="merge study name")
parser.add_argument('-study_name', type=str, required=True,nargs='+', help=' Name for saved genotype data, without ext')
parser.add_argument('-cluster', type=str, default='n', choices=['y','n'], help=' Is it parallel cluster job, default no')
parser.add_argument('-node', nargs='+',help='number of nodes / this node number, example: 10 2 ')
parser.add_argument('-split',type=int,help='Split size for merge genotypes')
args = parser.parse_args()
print args
if __name__ == '__main__':
mapper=Mapper(args.mapper_name)
mapper.load(args.mapper)
mapper.chunk_size=args.split
hdf5_iter=0
h5_name=args.save_name
pytable_filter=tables.Filters(complevel=9, complib='zlib')
gen=[]
for i,j in enumerate(args.genotype):
gen.append(Reader('genotype'))
gen[i].start(j,hdf5=True, study_name=args.study_name[i], ID=False)
RSID=[]
SUB_ID=[]
for i in gen:
G.split_size = CONVERTER_SPLIT_SIZE
G.VCF2hdf5(args.out)
else:
raise ValueError(
'Genotype data should be in PLINK/MINIMAC/VCF format and alone in folder'
)
check_converter(args.out, args.study_name[0])
print('Time to convert all data: {} sec'.format(t.secs))
################################### ENCODING ##############################
elif args.mode == 'encoding':
#ARG_CHECKER.check(args,mode='encoding')
mapper = Mapper()
mapper.genotype_names = args.study_name
mapper.chunk_size = MAPPER_CHUNK_SIZE
mapper.reference_name = args.ref_name
mapper.load_flip(args.mapper)
mapper.load(args.mapper)
phen = Reader('phenotype')
phen.start(args.phenotype[0])
gen = Reader('genotype')
gen.start(args.genotype[0],
hdf5=args.hdf5,
study_name=args.study_name[0],
ID=False)
elif R.format=='VCF':
G = GenotypeVCF(args.study_name[0], reader=R)
if args.cluster=='y':
G.cluster=True
G.split_size=CONVERTER_SPLIT_SIZE
G.VCF2hdf5(args.out)
else:
raise ValueError('Genotype data should be in PLINK/MINIMAC/VCF format and alone in folder')
print ('Time to convert all data: {} sec'.format(t.secs))
################################### ENCODING ##############################
elif args.mode=='encoding':
#ARG_CHECKER.check(args,mode='encoding')
mapper=Mapper()
mapper.genotype_names=args.study_name
mapper.chunk_size=MAPPER_CHUNK_SIZE
mapper.reference_name=args.ref_name
mapper.load_flip(args.mapper)
mapper.load(args.mapper)
phen=Reader('phenotype')
phen.start(args.phenotype[0])
gen=Reader('genotype')
gen.start(args.genotype[0], hdf5=args.hdf5, study_name=args.study_name[0], ID=False)
e=Encoder(args.out)
e.study_name=args.study_name[0]
