示例#1
0
文件: hase.py 项目: urmovosa/hase
    elif args.mode == 'meta-stage':

        #ARG_CHECKER.check(args,mode='meta-stage')

        ##### Init data readers #####
        if args.derivatives is None:
            raise ValueError(
                'For meta-stage analysis partial derivatives data are required!'
            )
        mapper = Mapper()
        mapper.chunk_size = MAPPER_CHUNK_SIZE
        mapper.genotype_names = args.study_name
        mapper.reference_name = args.ref_name  # Reference dataset
        if args.snp_id_inc is not None:  # If this is not none the argument contains a table of snps to include
            mapper.include = pd.DataFrame.from_csv(args.snp_id_inc,
                                                   index_col=None)
            print 'Include:'
            print mapper.include.head()
            if 'ID' not in mapper.include.columns and (
                    'CHR' not in mapper.include.columns
                    or 'bp' not in mapper.include.columns):
                raise ValueError(
                    '{} table does not have ID or CHR,bp columns'.format(
                        args.snp_id_inc))
        if args.snp_id_exc is not None:  # If this is not None the argument contains a table of snps to exclude
            mapper.exclude = pd.DataFrame.from_csv(args.snp_id_exc,
                                                   index_col=None)
            print 'Exclude:'
            print mapper.exclude.head()
            if 'ID' not in mapper.exclude.columns and (
                    'CHR' not in mapper.exclude.columns
示例#2
0
文件: hase.py 项目: roshchupkin/hase
		if (cov.folder.n_files>1 and cov.folder.format!='.npy') or (cov.folder.n_files>2 and cov.folder.format=='.npy'): #TODO (middle) test
			raise ValueError('In covariates folder should be only one file!')

		gen=[]
		for i,j in enumerate(args.genotype):
			gen.append(Reader('genotype'))
			gen[i].start(j,hdf5=args.hdf5, study_name=args.study_name[i], ID=False)


		if args.mapper is not None:
			mapper=Mapper()
			mapper.chunk_size=MAPPER_CHUNK_SIZE
			mapper.genotype_names=args.study_name
			mapper.reference_name=args.ref_name
			if args.snp_id_inc is not None:
				mapper.include=pd.DataFrame.from_csv(args.snp_id_inc,index_col=None)
				print 'Include:'
				print mapper.include.head()
				if 'ID' not in mapper.include.columns and ('CHR' not in mapper.include.columns or 'bp' not in mapper.include.columns):
					raise ValueError('{} table does not have ID or CHR,bp columns'.format(args.snp_id_inc))
			if args.snp_id_exc is not None:
				mapper.exclude=pd.DataFrame.from_csv(args.snp_id_exc,index_col=None)
				print 'Exclude:'
				print mapper.exclude.head()
				if 'ID' not in mapper.exclude.columns and ('CHR' not in mapper.exclude.columns or 'bp' not in mapper.exclude.columns):
					raise ValueError('{} table does not have ID or CHR,bp columns'.format(args.snp_id_exc))
			mapper.load(args.mapper)
			mapper.load_flip(args.mapper)
			mapper.cluster=args.cluster
			mapper.node=args.node
		else: