fix to the drug_info routine where the removal of improve_drug_ids broke the script

ymahlich · ymahlich · commit 08ca2ba476f6 · 2025-04-22T11:18:49.000-07:00
diff --git a/scripts/prepare_data_for_improve.py b/scripts/prepare_data_for_improve.py
@@ -470,7 +470,7 @@ def process_datasets(args):
         logger.info(
             f"Removing all chemical compunds with ids: '{args.EXCL_DRUGS_LIST}'"
         )
-        out_df = out_df[~out_df['improve_drug_id'].isin(args.EXCL_DRUGS_LIST)]
+        out_df = out_df[~out_df['improve_chem_id'].isin(args.EXCL_DRUGS_LIST)]
 
     outfile_path = args.WORKDIR.joinpath(
         "data_out",

Original file line number	Diff line number	Diff line change
`@@ -470,7 +470,7 @@ def process_datasets(args):`
`470`	`470`	`logger.info(`
`471`	`471`	`f"Removing all chemical compunds with ids: '{args.EXCL_DRUGS_LIST}'"`
`472`	`472`	`)`
`473`		`- out_df = out_df[~out_df['improve_drug_id'].isin(args.EXCL_DRUGS_LIST)]`
	`473`	`+ out_df = out_df[~out_df['improve_chem_id'].isin(args.EXCL_DRUGS_LIST)]`
`474`	`474`
`475`	`475`	`outfile_path = args.WORKDIR.joinpath(`
`476`	`476`	`"data_out",`