REF: PandasColumn.describe_categorical returns categores instead of mapping (pandas-dev#47886)

Author: mroeschke

pandas/core/interchange/column.py

@@ -146,15 +146,18 @@ def describe_categorical(self):
         """
         If the dtype is categorical, there are two options:
         - There are only values in the data buffer.
-        - There is a separate dictionary-style encoding for categorical values.
-        Raises RuntimeError if the dtype is not categorical
+        - There is a separate non-categorical Column encoding for categorical values.
+
+        Raises TypeError if the dtype is not categorical
+
         Content of returned dict:
             - "is_ordered" : bool, whether the ordering of dictionary indices is
                              semantically meaningful.
             - "is_dictionary" : bool, whether a dictionary-style mapping of
                                 categorical values to other objects exists
-            - "mapping" : dict, Python-level only (e.g. ``{int: str}``).
-                          None if not a dictionary-style categorical.
+            - "categories" : Column representing the (implicit) mapping of indices to
+                             category values (e.g. an array of cat1, cat2, ...).
+                             None if not a dictionary-style categorical.
         """
         if not self.dtype[0] == DtypeKind.CATEGORICAL:
             raise TypeError(
@@ -164,7 +167,7 @@ def describe_categorical(self):
         return {
             "is_ordered": self._col.cat.ordered,
             "is_dictionary": True,
-            "mapping": dict(enumerate(self._col.cat.categories)),
+            "categories": PandasColumn(pd.Series(self._col.cat.categories)),
         }
 
     @property

pandas/core/interchange/dataframe_protocol.py

@@ -110,7 +110,7 @@ class CategoricalDescription(TypedDict):
     is_dictionary: bool
     # Python-level only (e.g. ``{int: str}``).
     # None if not a dictionary-style categorical.
-    mapping: dict | None
+    categories: Column | None
 
 
 class Buffer(ABC):
@@ -274,17 +274,18 @@ def describe_categorical(self) -> CategoricalDescription:
         """
         If the dtype is categorical, there are two options:
         - There are only values in the data buffer.
-        - There is a separate dictionary-style encoding for categorical values.
+        - There is a separate non-categorical Column encoding for categorical values.
 
         Raises TypeError if the dtype is not categorical
 
         Returns the dictionary with description on how to interpret the data buffer:
             - "is_ordered" : bool, whether the ordering of dictionary indices is
                              semantically meaningful.
-            - "is_dictionary" : bool, whether a dictionary-style mapping of
+            - "is_dictionary" : bool, whether a mapping of
                                 categorical values to other objects exists
-            - "mapping" : dict, Python-level only (e.g. ``{int: str}``).
-                          None if not a dictionary-style categorical.
+            - "categories" : Column representing the (implicit) mapping of indices to
+                             category values (e.g. an array of cat1, cat2, ...).
+                             None if not a dictionary-style categorical.
 
         TBD: are there any other in-memory representations that are needed?
         """

pandas/core/interchange/from_dataframe.py

@@ -7,6 +7,7 @@
 import numpy as np
 
 import pandas as pd
+from pandas.core.interchange.column import PandasColumn
 from pandas.core.interchange.dataframe_protocol import (
     Buffer,
     Column,
@@ -179,9 +180,10 @@ def categorical_column_to_series(col: Column) -> tuple[pd.Series, Any]:
     if not categorical["is_dictionary"]:
         raise NotImplementedError("Non-dictionary categoricals not supported yet")
 
-    mapping = categorical["mapping"]
-    assert isinstance(mapping, dict), "Categorical mapping must be a dict"
-    categories = np.array(tuple(mapping[k] for k in sorted(mapping)))
+    cat_column = categorical["categories"]
+    # for mypy/pyright
+    assert isinstance(cat_column, PandasColumn), "categories must be a PandasColumn"
+    categories = np.array(cat_column._col)
     buffers = col.get_buffers()
 
     codes_buff, codes_dtype = buffers["data"]

pandas/tests/interchange/test_impl.py

@@ -8,6 +8,7 @@
 
 import pandas as pd
 import pandas._testing as tm
+from pandas.core.interchange.column import PandasColumn
 from pandas.core.interchange.dataframe_protocol import (
     ColumnNullType,
     DtypeKind,
@@ -61,11 +62,13 @@ def test_categorical_dtype(data):
     assert col.null_count == 0
     assert col.describe_null == (ColumnNullType.USE_SENTINEL, -1)
     assert col.num_chunks() == 1
-    assert col.describe_categorical == {
-        "is_ordered": data[1],
-        "is_dictionary": True,
-        "mapping": {0: "a", 1: "d", 2: "e", 3: "s", 4: "t"},
-    }
+    desc_cat = col.describe_categorical
+    assert desc_cat["is_ordered"] == data[1]
+    assert desc_cat["is_dictionary"] is True
+    assert isinstance(desc_cat["categories"], PandasColumn)
+    tm.assert_series_equal(
+        desc_cat["categories"]._col, pd.Series(["a", "d", "e", "s", "t"])
+    )
 
     tm.assert_frame_equal(df, from_dataframe(df.__dataframe__()))