From 70de586b590e824d7bcc3777830fda323a0e7983 Mon Sep 17 00:00:00 2001
From: Frederick Muriuki Muriithi
Date: Tue, 3 Jun 2025 07:00:40 -0500
Subject: Memory saving: Don't reload saved data

We already have all the data in memory, so we do not need to reload it
and keep yet another copy.
---
 scripts/load_phenotypes_to_db.py | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

(limited to 'scripts')

diff --git a/scripts/load_phenotypes_to_db.py b/scripts/load_phenotypes_to_db.py
index fdfab4c..d3d9f5a 100644
--- a/scripts/load_phenotypes_to_db.py
+++ b/scripts/load_phenotypes_to_db.py
@@ -242,12 +242,12 @@ def load_data(conn: mysqldb.Connection, job: dict) -> int:
                 conn, _species["SpeciesId"], _population["Id"])}
     #    b. Save all the data items (DataIds are vibes), return new IDs
     logger.info("Saving new phenotypes data.")
-    data = save_pheno_data(conn=conn,
-                           dataidmap=dataidmap,
-                           pheno_name2id=pheno_name2id,
-                           samples=samples,
-                           control_data=_control_data,
-                           filesdir=_outdir)
+    _num_data_rows = save_pheno_data(conn=conn,
+                                     dataidmap=dataidmap,
+                                     pheno_name2id=pheno_name2id,
+                                     samples=samples,
+                                     control_data=_control_data,
+                                     filesdir=_outdir)
     # 4. Cross-reference Phenotype, Publication, and PublishData in PublishXRef
     logger.info("Cross-referencing new phenotypes to their data and publications.")
     xrefs = cross_reference_phenotypes_publications_and_data(
@@ -255,19 +255,19 @@ def load_data(conn: mysqldb.Connection, job: dict) -> int:
     # 5. If standard errors and N exist, save them too
     #    (use IDs returned in `3. b.` above).
     logger.info("Saving new phenotypes standard errors.")
-    _data_se = save_phenotypes_se(conn=conn,
-                                  dataidmap=dataidmap,
-                                  pheno_name2id=pheno_name2id,
-                                  samples=samples,
-                                  control_data=_control_data,
-                                  filesdir=_outdir)
+    _num_se_rows = save_phenotypes_se(conn=conn,
+                                      dataidmap=dataidmap,
+                                      pheno_name2id=pheno_name2id,
+                                      samples=samples,
+                                      control_data=_control_data,
+                                      filesdir=_outdir)
     logger.info("Saving new phenotypes sample counts.")
-    _data_n = save_phenotypes_n(conn=conn,
-                                dataidmap=dataidmap,
-                                pheno_name2id=pheno_name2id,
-                                samples=samples,
-                                control_data=_control_data,
-                                filesdir=_outdir)
+    _num_n_rows = save_phenotypes_n(conn=conn,
+                                    dataidmap=dataidmap,
+                                    pheno_name2id=pheno_name2id,
+                                    samples=samples,
+                                    control_data=_control_data,
+                                    filesdir=_outdir)
     # 6. If entirely new data, update authorisations (break this down)
     logger.info("Updating authorisation.")
     update_auth(_token, _species, _population, _dataset, _phenos)
-- 
cgit v1.2.3