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)
e = Encoder(args.out)
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]
row_index, ids = study_indexes(phenotype=phen.folder._data,genotype=gen.folder._data)
