coorectly infer boolean stypes

CHANGELOG.md

@@ -8,6 +8,8 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ### Added
 
+- Added support for inferring `stype.categorical` from boolean columns in `utils.infer_series_stype` ([#421](https://github.com/pyg-team/pytorch-frame/pull/421))
+
 ### Changed
 
 ### Deprecated

test/utils/test_infer_stype.py

@@ -41,7 +41,7 @@ def test_infer_df_stype(with_nan):
     assert col_to_stype_inferred == dataset.col_to_stype
 
 
-def test_infer_multicategorical_stype():
+def test_infer_stypes():
     # Test when multicategoricals are lists
     df = pd.DataFrame({
         'category': [['Books', 'Mystery, Thriller'],
@@ -52,3 +52,8 @@ def test_infer_multicategorical_stype():
     })
     col_to_stype_inferred = infer_df_stype(df)
     assert col_to_stype_inferred['category'] == torch_frame.multicategorical
+
+    df = pd.DataFrame({'bool': [True] * 50 + [False] * 50})
+
+    col_to_stype_inferred = infer_df_stype(df)
+    assert col_to_stype_inferred['bool'] == torch_frame.categorical

torch_frame/utils/infer_stype.py

@@ -109,6 +109,9 @@ def infer_series_stype(ser: Series) -> stype | None:
         # text_(embedded/tokenized)
 
         if ptypes.is_numeric_dtype(ser):
+
+            if ptypes.is_bool_dtype(ser):
+                return stype.categorical
             # Candidates: numerical, categorical
             if ptypes.is_float_dtype(ser) and not (has_nan and
                                                    (ser % 1 == 0).all()):