Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update RKI data processing #476

Merged
merged 5 commits into from
Sep 13, 2024
Merged

Update RKI data processing #476

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a587f18
Update RKI_INDEX_COL since SEQUENCE.ID renamed to igs_id
j23414 Sep 12, 2024
f86c4fa
Update COLUMN_MAP for RKI data
j23414 Sep 12, 2024
2df0af9
Add new RKI date format %Y-%m-%dT%H:%M:%S to expected date_formats
j23414 Sep 12, 2024
7767c76
Parse new RKI JSON blob for pango_lineage
j23414 Sep 12, 2024
e57f3c0
fixup: Parse new RKI JSON blob for pango_lineage
j23414 Sep 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions bin/transform-rki
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,12 +29,12 @@ from lib.utils.transformpipeline.transforms import (AddHardcodedMetadataRki,
UserProvidedAnnotations)

COLUMN_MAP = {
"SEQUENCE.DATE_OF_SAMPLING": "date",
"SEQUENCE.PUSHED_TO_DWH": "date_submitted",
"DL.ID": "originating_lab",
"SL.ID": "submitting_lab",
"PANGOLIN.LINEAGE_LATEST": "pango_lineage",
"SEQUENCE.SEQUENCING_REASON": "sampling_strategy",
"date_of_sampling": "date",
"date_of_submission": "date_submitted",
"prime_diagnostic_lab.demis_lab_id": "originating_lab",
"sequencing_lab.demis_lab_id": "submitting_lab",
"lineages": "pango_lineage",
"sequencing_reason": "sampling_strategy",
}


Expand Down
2 changes: 1 addition & 1 deletion bin/transform-rki-data-to-ndjson
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ Turn RKI files into ndjson format

import typer

RKI_INDEX_COL = "SEQUENCE.ID"
RKI_INDEX_COL = "igs_id"

def main(
input_rki_sequences: str = typer.Option(..., help="Input file"),
Expand Down
10 changes: 9 additions & 1 deletion lib/utils/transformpipeline/transforms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import csv
import re
import unicodedata
import json
from collections import defaultdict
from typing import Any, Collection, List, MutableMapping, Sequence, Tuple , Dict , Union
import pandas as pd
Expand Down Expand Up @@ -288,6 +289,13 @@ def transform_value(self, entry: dict) -> dict:
entry['sequence'] = entry['sequence'].replace('\n', '')
entry['length'] = len(entry['sequence'])

# Pull out latest pango lineage from json blob
# Currently this pulls the first entry, but we've added an assert statement to see if there are ever more than one entry
# At that time, we can loop over the json blob to find the latest pango lineage assignment
lineage_json_blob = json.loads(entry['pango_lineage'])
entry['pango_lineage'] = lineage_json_blob[0]['lineage']
assert len(lineage_json_blob)==1, f"RKI pango_lineage unexpectedly had more than one entry. rki_accession: {entry['rki_accession']}"

# Normalize all string data to Unicode Normalization Form C, for
# consistent, predictable string comparisons.
str_kvs = {
Expand All @@ -299,7 +307,7 @@ def transform_value(self, entry: dict) -> dict:

# Standardize date format to ISO 8601 date
date_columns = {'date', 'date_submitted'}
date_formats = {'%Y-%m-%d', '%Y-%m-%dT%H:%M:%SZ', '%Y-%m-%d %H:%M:%S %z'}
date_formats = {'%Y-%m-%d', '%Y-%m-%dT%H:%M:%SZ', '%Y-%m-%d %H:%M:%S %z', '%Y-%m-%dT%H:%M:%S'}
for column in date_columns:
entry[column] = format_date(entry[column], date_formats)

Expand Down