]
pprint(kt.schema)
for field_name in transcript_annotations_to_keep:
new_field_name = field_name.split("_")[0] + "".join(map(lambda word: word.capitalize(), field_name.split("_")[1:]))
kt = kt.annotate("%(new_field_name)s = mainTranscript.%(field_name)s" % locals())
# pprint(kt.schema)
kt = kt.drop(["mainTranscript"])
pprint(kt.schema)
DISABLE_INDEX_AND_DOC_VALUES_FOR_FIELDS = ("sortedTranscriptConsequences", )
print("======== Export to elasticsearch ======")
export_kt_to_elasticsearch(
kt,
host=args.host,
port=args.port,
index_name=args.index,
index_type_name=args.index_type,
block_size=args.block_size,
num_shards=args.num_shards,
delete_index_before_exporting=True,
disable_doc_values_for_fields=DISABLE_INDEX_AND_DOC_VALUES_FOR_FIELDS,
disable_index_for_fields=DISABLE_INDEX_AND_DOC_VALUES_FOR_FIELDS,
verbose=True,
)
if args.coverage_type == 'test':
# x chromosome only
COVERAGE_PATHS = EXOME_COVERAGE_CSV_PATHS[-1]
kt_coverage = hc.import_table(COVERAGE_PATHS, types=types)
kt_coverage = kt_coverage.rename({
'#chrom': 'chrom',
'1': 'over1',
'5': 'over5',
'10': 'over10',
'15': 'over15',
'20': 'over20',
'25': 'over25',
'30': 'over30',
'50': 'over50',
'100': 'over100',
})
print(kt_coverage.schema)
print("======== Export exome coverage to elasticsearch ======")
export_kt_to_elasticsearch(
kt_coverage,
host=args.host,
port=args.port,
index_name=args.index,
index_type_name=args.index_type,
num_shards=args.num_shards,
block_size=args.block_size,
delete_index_before_exporting=True,
verbose=True
)