Account for Jeromes' suggestions

skrub-data · Nov 30, 2023 · 7b7484c · 7b7484c
1 parent 65e7106
commit 7b7484c
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/skrub/_gap_encoder.py b/skrub/_gap_encoder.py
@@ -397,9 +397,9 @@ def get_feature_names_out(
             label = ", ".join(labels)
             # Avoid having twice the same name for the different features
             if label in topic_labels:
-                label += ", {:}".format(i)
+                label += " ({:})".format(i)
+            label = prefix + label
             topic_labels.append(label)
-        topic_labels = [prefix + label for label in topic_labels]
         return topic_labels
 
     def score(self, X: ArrayLike) -> float:

diff --git a/skrub/tests/test_gap_encoder.py b/skrub/tests/test_gap_encoder.py
@@ -217,7 +217,7 @@ def test_get_feature_names_out_no_words():
 
 
 def test_get_feature_names_out_redundent():
-    # With the following dataframe, the GapEncoder produces feature names
+    # With the following dataframe, the GapEncoder can produce feature names
     # that have the same name, which leads duplicated features names,
     # which themselves lead to errors in the TableVectorizer
     # get_feature_names_out() method.