covariates=tuple(i.folder._data.metadata for i in pard))
if row_index[2].shape[0] != np.sum(
[i.folder._data.metadata['id'].shape[0] for i in pard]):
raise ValueError(
'Partial Derivatives covariates have different number of subjects {} than genotype and phenotype {}'
.format(
row_index[2].shape[0],
np.sum([
i.folder._data.metadata['id'].shape[0]
for i in pard
])))
while True:
if mapper.cluster == 'n':
SNPs_index, keys = mapper.get()
else:
ch = mapper.chunk_pop()
if ch is None:
SNPs_index = None
break
SNPs_index, keys = mapper.get(chunk_number=ch)
if isinstance(SNPs_index, type(None)):
break
Analyser.rsid = keys
if np.sum(PD) == 0:
genotype = np.array([])
with Timer() as t_g:
genotype = merge_genotype(gen, SNPs_index, mapper)
genotype = genotype[:, row_index[0]]
print "Time to get G {}s".format(t_g.secs)
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:
SUB_ID.append(i.folder._data.get_id())
mapper.cluster=args.cluster
mapper.node=args.node
while True:
if args.cluster=='n':
SNPs_index, keys=mapper.get_next()
else:
chunk=mapper.chunk_pop()
if chunk is None:
SNPs_index=None
break
print chunk
SNPs_index, keys=mapper.get_chunk(chunk)
if SNPs_index is None:
break
RSID.append(keys)
data=merge_genotype(gen, SNPs_index) #TODO (high) add mapper
print data.shape
if args.cluster=='n':
h5_gen_file = tables.openFile(
os.path.join(args.out,str(hdf5_iter)+'_'+h5_name+'.h5'), 'w', title=args.save_name)
