diff --git a/python/src/spark_rapids_ml/knn.py b/python/src/spark_rapids_ml/knn.py
index fc55f59f..07d11c1c 100644
--- a/python/src/spark_rapids_ml/knn.py
+++ b/python/src/spark_rapids_ml/knn.py
@@ -151,7 +151,7 @@ def _ensureIdCol(self, df: DataFrame) -> DataFrame:
         id_col_name = self.getIdCol()
         df_withid = (
             df
-            if self.isSet("idCol")
+            if id_col_name in df.columns
             else df.select(monotonically_increasing_id().alias(id_col_name), "*")
         )
         return df_withid
diff --git a/python/tests/test_nearest_neighbors.py b/python/tests/test_nearest_neighbors.py
index c50d605b..034b2042 100644
--- a/python/tests/test_nearest_neighbors.py
+++ b/python/tests/test_nearest_neighbors.py
@@ -234,6 +234,17 @@ def assert_knn_metadata_equal(knn_metadata: List[List[str]]) -> None:
                 assert knnjoin_queries[i]["features"] == query[i][0]
             assert knnjoin_queries[i]["metadata"] == query[i][1]
 
+        # Test fit(dataset, ParamMap) that copies existing estimator
+        # After copy, self.isSet("idCol") becomes true. But the added id column does not exist in the dataframe
+        paramMap = gpu_knn.extractParamMap()
+        gpu_model_v2 = gpu_knn.fit(item_df_withid, paramMap)
+
+        assert gpu_knn.isSet("idCol") is False
+        assert gpu_model_v2.isSet("idCol") is True
+
+        (_, _, knn_df_v2) = gpu_model_v2.kneighbors(query_df)
+        assert knn_df_v2.collect() == knn_df.collect()
+
         return gpu_knn, gpu_model