correct col name

Sage-Bionetworks · Jan 24, 2025 · 0cd8f8c · 0cd8f8c
1 parent 91e4fab
commit 0cd8f8c
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 11 deletions.
diff --git a/genie/database_to_staging.py b/genie/database_to_staging.py
@@ -732,7 +732,6 @@ def store_sv_files(
     # sv_df["ENTREZ_GENE_ID"].mask(
     #     sv_df["ENTREZ_GENE_ID"] == 0, float("nan"), inplace=True
     # )
-
     if not current_release_staging:
         sv_staging_df = sv_df[
             sv_df["SAMPLE_ID"].isin(keep_for_center_consortium_samples)
@@ -751,7 +750,7 @@ def store_sv_files(
                 )
 
     sv_df = sv_df[sv_df["SAMPLE_ID"].isin(keep_for_merged_consortium_samples)]
-    sv_df = filter_out_germline_variants(input_data=sv_df, status_col="SV_Status")
+    sv_df = filter_out_germline_variants(input_data=sv_df, status_col="SV_STATUS")
     sv_df.rename(columns=transform._col_name_to_titlecase, inplace=True)
     sv_text = process_functions.removePandasDfFloat(sv_df)
     sv_path = os.path.join(GENIE_RELEASE_DIR, "data_sv.txt")

diff --git a/tests/test_database_to_staging.py b/tests/test_database_to_staging.py
@@ -116,28 +116,28 @@ def test_store_assay_info_files(syn):
         (
             pd.DataFrame(
                 dict(
-                    SV_Status=["GERMLINE", "GERMLINE"], Sample_ID=["GENIE-1", "GENIE-2"]
+                    SV_STATUS=["GERMLINE", "GERMLINE"], Sample_ID=["GENIE-1", "GENIE-2"]
                 )
             ),
-            "SV_Status",
-            pd.DataFrame(columns=["SV_Status", "Sample_ID"]),
+            "SV_STATUS",
+            pd.DataFrame(columns=["SV_STATUS", "Sample_ID"]),
         ),
         (
             pd.DataFrame(
                 dict(
-                    SV_Status=["GERMLINE", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"]
+                    SV_STATUS=["GERMLINE", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"]
                 )
             ),
-            "SV_Status",
-            pd.DataFrame(dict(SV_Status=["SOMATIC"], Sample_ID=["GENIE-2"])),
+            "SV_STATUS",
+            pd.DataFrame(dict(SV_STATUS=["SOMATIC"], Sample_ID=["GENIE-2"])),
         ),
         (
             pd.DataFrame(
-                dict(SV_Status=["SOMATIC", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"])
+                dict(SV_STATUS=["SOMATIC", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"])
             ),
-            "SV_Status",
+            "SV_STATUS",
             pd.DataFrame(
-                dict(SV_Status=["SOMATIC", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"])
+                dict(SV_STATUS=["SOMATIC", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"])
             ),
         ),
     ],