From 11fb8a4ee3615a522fc2c802adc2271b11e49cb5 Mon Sep 17 00:00:00 2001
From: Sunny Sun <38218185+sunnyosun@users.noreply.github.com>
Date: Thu, 5 Dec 2024 08:15:52 +0100
Subject: [PATCH] =?UTF-8?q?=F0=9F=90=9B=20Fix=20describing=20no=20label=20?=
 =?UTF-8?q?features=20(#2253)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 lamindb/_curate.py               | 21 ++++++++------
 lamindb/core/_feature_manager.py | 48 +++++++++++++++++++++++---------
 tests/core/test_describe_df.py   |  2 ++
 3 files changed, 49 insertions(+), 22 deletions(-)

diff --git a/lamindb/_curate.py b/lamindb/_curate.py
index 6b837a40e..a4f0575e0 100644
--- a/lamindb/_curate.py
+++ b/lamindb/_curate.py
@@ -1449,7 +1449,9 @@ def standardize(self, key: str):
 
             df = table.to_pandas()
             # map values
-            df[slot_key] = df[slot_key].map(lambda val: syn_mapper.get(val, val))  # noqa: B023
+            df[slot_key] = df[slot_key].map(
+                lambda val: syn_mapper.get(val, val)  # noqa
+            )
             # write the mapped values
             with _open_tiledbsoma(self._experiment_uri, mode="w") as experiment:
                 slot(experiment).write(pa.Table.from_pandas(df, schema=table.schema))
@@ -2044,16 +2046,17 @@ def _add_labels(
             )
             if len(labels) == 0:
                 continue
+            label_ref_is_name = None
             if hasattr(registry, "_name_field"):
                 label_ref_is_name = field.field.name == registry._name_field
-                add_labels(
-                    artifact,
-                    records=labels,
-                    feature=feature,
-                    feature_ref_is_name=feature_ref_is_name,
-                    label_ref_is_name=label_ref_is_name,
-                    from_curator=True,
-                )
+            add_labels(
+                artifact,
+                records=labels,
+                feature=feature,
+                feature_ref_is_name=feature_ref_is_name,
+                label_ref_is_name=label_ref_is_name,
+                from_curator=True,
+            )
 
     if artifact._accessor == "MuData":
         for modality, modality_fields in fields.items():
diff --git a/lamindb/core/_feature_manager.py b/lamindb/core/_feature_manager.py
index b5b485632..541dc8509 100644
--- a/lamindb/core/_feature_manager.py
+++ b/lamindb/core/_feature_manager.py
@@ -347,15 +347,15 @@ def describe_features(
                 for feature_name in feature_names:
                     feature_data[feature_name] = (slot, feature_set.registry)
 
-    internal_feature_names: set[str] = {}  # type: ignore
+    internal_feature_names: dict[str, str] = {}
     if isinstance(self, Artifact):
         feature_sets = self.feature_sets.filter(registry="Feature").all()
-        internal_feature_names = set()  # type: ignore
+        internal_feature_names = {}
         if len(feature_sets) > 0:
             for feature_set in feature_sets:
-                internal_feature_names = internal_feature_names.union(
-                    set(feature_set.members.values_list("name", flat=True))
-                )  # type: ignore
+                internal_feature_names.update(
+                    dict(feature_set.members.values_list("name", "dtype"))
+                )
 
     # categorical feature values
     # Get the categorical data using the appropriate method
@@ -410,20 +410,42 @@ def describe_features(
         return dictionary
 
     # Internal features section
-    internal_features_slot: dict[
-        str, list
-    ] = {}  # internal features from the `Feature` registry that contain labels
+    # internal features that contain labels (only `Feature` features contain labels)
+    internal_feature_labels_slot: dict[str, list] = {}
     for feature_name, feature_row in internal_feature_labels.items():
         slot, _ = feature_data.get(feature_name)
-        internal_features_slot.setdefault(slot, []).append(feature_row)
-    int_features_tree_children = []
+        internal_feature_labels_slot.setdefault(slot, []).append(feature_row)
 
+    int_features_tree_children = []
     for slot, (feature_set, feature_names) in feature_set_data.items():
-        if slot in internal_features_slot:
-            feature_rows = internal_features_slot[slot]
+        if slot in internal_feature_labels_slot:
+            # add internal Feature features with labels
+            feature_rows = internal_feature_labels_slot[slot]
+            # add internal Feature features without labels
+            feature_rows += [
+                (
+                    feature_name,
+                    Text(str(internal_feature_names.get(feature_name)), style="dim"),
+                    "",
+                )
+                for feature_name in feature_names
+                if feature_name and feature_name not in internal_feature_labels
+            ]
         else:
+            # add internal non-Feature features without labels
             feature_rows = [
-                (feature_name, Text(str(feature_set.dtype), style="dim"), "")
+                (
+                    feature_name,
+                    Text(
+                        str(
+                            internal_feature_names.get(feature_name)
+                            if feature_name in internal_feature_names
+                            else feature_set.dtype
+                        ),
+                        style="dim",
+                    ),
+                    "",
+                )
                 for feature_name in feature_names
                 if feature_name
             ]
diff --git a/tests/core/test_describe_df.py b/tests/core/test_describe_df.py
index d334a197b..39f7f069c 100644
--- a/tests/core/test_describe_df.py
+++ b/tests/core/test_describe_df.py
@@ -179,6 +179,7 @@ def test_curate_df():
         "cell_medium",
         "cell_type_by_expert",
         "cell_type_by_model",
+        "sample_note",
     ]
     assert int_features_node.children[1].label.columns[1].header.plain == "[Feature]"
     assert (
@@ -196,6 +197,7 @@ def test_curate_df():
         "DMSO, IFNG",
         "B cell, T cell",
         "B cell, T cell",
+        "",
     ]
 
     # external features section