def generate_multi_backend(args, variant_key):
logging.info("Processing Genotype")
dosage_conversion = GenotypeUtilities.impute_to_mean_conversion if args.impute_to_mean else None
dosage_filter = get_filter(args, variant_key)
metadata = []
for genotype, individual_ids in ModelTraining.load_genotype_file_by_chromosome(
args.input_genotype_file, variant_key, dosage_conversion,
dosage_filter):
if args.simplify_individual_id:
logging.info("simplifying individual id")
individual_ids = [x.split("_")[0] for x in individual_ids]
_m = genotype.get_variants_metadata()
metadata.append(_m)
_chr = _m.chromosome.values[0]
logging.log(9, "Processing {}".format(_chr))
_o = args.output_prefix + ".chr{}".format(_chr) + ".variants.parquet"
Parquet.save_variants(_o, genotype, individual_ids)
logging.info("Saving metadata")
metadata = pandas.concat(metadata)
path_metadata_variant = args.output_prefix + ".variants_metadata.parquet"
Parquet._save_metadata(path_metadata_variant, metadata)
def generate_single_backend(args, variant_key):
logging.info("Loading Genotype")
dosage_conversion = GenotypeUtilities.impute_to_mean_conversion if args.impute_to_mean else None
dosage_filter = get_filter(args, variant_key)
genotype, individual_ids = ModelTraining.load_genotype_file(
args.input_genotype_file, variant_key, dosage_conversion,
dosage_filter)
if args.simplify_individual_id:
logging.info("simplifying individual id")
individual_ids = [x.split("_")[0] for x in individual_ids]
logging.info("Saving Genotype")
path_variant = args.output_prefix + ".variants.parquet"
Parquet.save_variants(path_variant, genotype, individual_ids)
logging.info("Saving metadata")
path_metadata_variant = args.output_prefix + ".variants_metadata.parquet"
Parquet._save_metadata(path_metadata_variant,
genotype.get_variants_metadata())