Remove automatic sort order of categorical data if a non-ordinal type is specified

joelostblom · joelostblom · commit 9ad570b841e0 · 2023-01-19T14:41:47.000+01:00
diff --git a/altair/utils/schemapi.py b/altair/utils/schemapi.py
@@ -364,6 +364,14 @@ def to_dict(self, validate=True, ignore=None, context=None):
             # parsed_shorthand is removed from context if it exists so that it is
             # not passed to child to_dict function calls
             parsed_shorthand = context.pop("parsed_shorthand", {})
+            # Prevent that pandas categorical data is automatically sorted
+            # when a non-ordinal data type is specifed manually
+            if "sort" in parsed_shorthand and kwds["type"] not in [
+                "ordinal",
+                Undefined,
+            ]:
+                parsed_shorthand.pop("sort")
+
             kwds.update(
                 {
                     k: v
diff --git a/tests/vegalite/v5/tests/test_api.py b/tests/vegalite/v5/tests/test_api.py
@@ -166,14 +166,14 @@ def _check_encodings(chart):
         .encode(
             alt.X("x", type="nominal"),
             alt.Y("y", type="ordinal"),
-            alt.Size("s", type="nominal", sort=None),
+            alt.Size("s", type="nominal"),
         )
     )
     dct = chart.to_dict()
     assert dct["encoding"]["x"]["type"] == "nominal"
     assert dct["encoding"]["y"]["type"] == "ordinal"
     assert dct["encoding"]["size"]["type"] == "nominal"
-    assert dct["encoding"]["size"]["sort"] is None
+    assert "sort" not in dct["encoding"]["size"]
 
 
 @pytest.mark.parametrize(
diff --git a/tools/schemapi/schemapi.py b/tools/schemapi/schemapi.py
@@ -362,6 +362,14 @@ def to_dict(self, validate=True, ignore=None, context=None):
             # parsed_shorthand is removed from context if it exists so that it is
             # not passed to child to_dict function calls
             parsed_shorthand = context.pop("parsed_shorthand", {})
+            # Prevent that pandas categorical data is automatically sorted
+            # when a non-ordinal data type is specifed manually
+            if "sort" in parsed_shorthand and kwds["type"] not in [
+                "ordinal",
+                Undefined,
+            ]:
+                parsed_shorthand.pop("sort")
+
             kwds.update(
                 {
                     k: v
