From 044104811dad5176459466059e07a9d998cc2838 Mon Sep 17 00:00:00 2001 From: Matthew McDermott Date: Sun, 19 May 2024 13:55:38 -0400 Subject: [PATCH] Make the final directory be a named subdirectory of the cohort --- scripts/extraction/merge_to_MEDS_cohort.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/extraction/merge_to_MEDS_cohort.py b/scripts/extraction/merge_to_MEDS_cohort.py index d9c5ad4..68362d0 100755 --- a/scripts/extraction/merge_to_MEDS_cohort.py +++ b/scripts/extraction/merge_to_MEDS_cohort.py @@ -51,7 +51,7 @@ def main(cfg: DictConfig): for sp in patient_splits: in_dir = patient_subsharded_dir / sp - out_fp = MEDS_cohort_dir / f"{sp}.parquet" + out_fp = MEDS_cohort_dir / "final_cohort" / f"{sp}.parquet" shard_fps = sorted(list(in_dir.glob("**/*.parquet"))) shard_fp_strs = [f" * {str(fp.resolve())}" for fp in shard_fps]