diff options
Diffstat (limited to 'scripts/insert_data.py')
| -rw-r--r-- | scripts/insert_data.py | 13 |
1 files changed, 10 insertions, 3 deletions
diff --git a/scripts/insert_data.py b/scripts/insert_data.py index 7d3c1c6..23ae108 100644 --- a/scripts/insert_data.py +++ b/scripts/insert_data.py @@ -107,8 +107,12 @@ def check_strains(headings_strains, db_strains): file=sys.stderr) sys.exit(1) + def annotationinfo( - dbconn: mdb.Connection, platformid: int, datasetid: int) -> dict: + dbconn: mdb.Connection, + platformid: int, + datasetid: int +) -> dict[str, dict]: "Get annotation information from the database." # This is somewhat slow. Look into optimising the behaviour def __organise_annotations__(accm, item): @@ -277,8 +281,11 @@ def insert_se(# pylint: disable = [too-many-arguments] return 1 se_values = ( - {"DataId": annotations[str(item["ProbeSetId"])]["DataId"], **item} - for item in read_datavalues(filepath, headings, strains)) + {"DataId": annotations[str(item["ProbeSetName"])]["DataId"], **item} + for item in ( + row for psrows in + read_datavalues(filepath, headings, strains).values() + for row in psrows)) with dbconn.cursor(cursorclass=DictCursor) as cursor: while True: serrors = tuple(take(se_values, 1000)) |