test_with_prefix_default_category

Author: simonjayhawkins

pandas/core/reshape/encoding.py

@@ -13,6 +13,10 @@
 from pandas._libs import missing as libmissing
 from pandas._libs.sparse import IntIndex
 
+from pandas.core.dtypes.cast import (
+    find_common_type,
+    infer_dtype_from_scalar,
+)
 from pandas.core.dtypes.common import (
     is_integer_dtype,
     is_list_like,
@@ -567,7 +571,13 @@ def from_dummies(
             )
         else:
             data_slice = data_to_decode.loc[:, prefix_slice]
-        cats_array = data._constructor_sliced(cats, dtype=data.columns.dtype)
+        dtype = data.columns.dtype
+        if default_category:
+            default_category_dtype = infer_dtype_from_scalar(default_category[prefix])[
+                0
+            ]
+            dtype = find_common_type([dtype, default_category_dtype])
+        cats_array = data._constructor_sliced(cats, dtype=dtype)
         # get indices of True entries along axis=1
         true_values = data_slice.idxmax(axis=1)
         indexer = data_slice.columns.get_indexer_for(true_values)

pandas/tests/reshape/test_from_dummies.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas import (
     DataFrame,
     Series,
@@ -330,14 +328,10 @@ def test_no_prefix_string_cats_contains_get_dummies_NaN_column():
         ),
     ],
 )
-def test_no_prefix_string_cats_default_category(
-    default_category, expected, using_infer_string
-):
+def test_no_prefix_string_cats_default_category(default_category, expected):
     dummies = DataFrame({"a": [1, 0, 0], "b": [0, 1, 0]})
     result = from_dummies(dummies, default_category=default_category)
     expected = DataFrame(expected)
-    if using_infer_string:
-        expected[""] = expected[""].astype("str")
     tm.assert_frame_equal(result, expected)
 
 
@@ -364,7 +358,6 @@ def test_with_prefix_contains_get_dummies_NaN_column():
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "default_category, expected",
     [
@@ -390,7 +383,7 @@ def test_with_prefix_contains_get_dummies_NaN_column():
         ),
         pytest.param(
             {"col2": None, "col1": False},
-            {"col1": ["a", "b", False], "col2": [None, "a", "c"]},
+            {"col1": ["a", "b", False], "col2": Series([None, "a", "c"], dtype=object)},
             id="default_category is a dict with bool and None values",
         ),
         pytest.param(