fixed duplicated IDs, #251

zqfang · Feb 28, 2024 · 7d5dd11 · 7d5dd11
1 parent a9d1b7b
commit 7d5dd11
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/gseapy/base.py b/gseapy/base.py
@@ -240,14 +240,15 @@ def _check_data(self, exprs: pd.DataFrame) -> pd.DataFrame:
 
     def make_unique(self, rank_metric: pd.DataFrame, col_idx: int) -> pd.DataFrame:
         """
-        make gene id column unique
+        make gene id column unique by adding a digit, similar to R's make.unique
         """
         id_col = rank_metric.columns[col_idx]
         if rank_metric.duplicated(subset=id_col).sum() > 0:
             self._logger.info("Input gene rankings contains duplicated IDs")
             mask = rank_metric.duplicated(subset=id_col, keep=False)
             dups = (
                 rank_metric.loc[mask, id_col]
+                .to_frame()
                 .groupby(id_col)
                 .cumcount()
                 .map(lambda c: "_" + str(c) if c else "")