TST(string dtype): Resolve xfails in test_from_dummies

Author: rhshadrach

pandas/core/reshape/encoding.py

@@ -17,12 +17,14 @@
     is_integer_dtype,
     is_list_like,
     is_object_dtype,
+    is_string_dtype,
     pandas_dtype,
 )
 from pandas.core.dtypes.dtypes import (
     ArrowDtype,
     CategoricalDtype,
 )
+from pandas.core.dtypes.missing import isna
 
 from pandas.core.arrays import SparseArray
 from pandas.core.arrays.categorical import factorize_from_iterable
@@ -554,9 +556,20 @@ def from_dummies(
                 "Dummy DataFrame contains multi-assignment(s); "
                 f"First instance in row: {assigned.idxmax()}"
             )
+        dtype = data.columns.dtype
         if any(assigned == 0):
             if isinstance(default_category, dict):
-                cats.append(default_category[prefix])
+                value = default_category[prefix]
+                if (
+                    is_string_dtype(data.columns.dtype)
+                    and not isinstance(value, str)
+                    and (is_list_like(value) or not isna(value))
+                ):
+                    # GH#???
+                    # `value` is not a string or NA.
+                    # Using data.columns.dtype would coerce `value` into a string.
+                    dtype = "object"
+                cats.append(value)
             else:
                 raise ValueError(
                     "Dummy DataFrame contains unassigned value(s); "
@@ -567,7 +580,7 @@ def from_dummies(
             )
         else:
             data_slice = data_to_decode.loc[:, prefix_slice]
-        cats_array = data._constructor_sliced(cats, dtype=data.columns.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 +1,7 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
+import pandas as pd
 from pandas import (
     DataFrame,
     Series,
@@ -336,8 +335,6 @@ def test_no_prefix_string_cats_default_category(
     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 +361,6 @@ 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",
     [
@@ -450,3 +446,32 @@ def test_maintain_original_index():
     result = from_dummies(df)
     expected = DataFrame({"": list("abca")}, index=list("abcd"))
     tm.assert_frame_equal(result, expected)
+
+
+def test_int_columns_with_float_default():
+    # GH#???
+    df = DataFrame(
+        {
+            3: [1, 0, 0],
+            4: [0, 1, 0],
+        },
+    )
+    with pytest.raises(ValueError, match="Trying to coerce float values to integers"):
+        from_dummies(df, default_category=0.5)
+
+
+def test_object_dtype_preserved():
+    # GH#???
+    # When the input has object dtype, the result should as
+    # well even when infer_string is True.
+    df = DataFrame(
+        {
+            "x": [1, 0, 0],
+            "y": [0, 1, 0],
+        },
+    )
+    df.columns = df.columns.astype("object")
+    with pd.option_context("future.infer_string", True):
+        result = from_dummies(df, default_category="z")
+        expected = DataFrame({"": ["x", "y", "z"]}, dtype="object")
+        tm.assert_frame_equal(result, expected)