get_dummies to select string dtype in addition to object and categorical (#45516)

Author: lukemanley

doc/source/whatsnew/v1.5.0.rst

@@ -309,6 +309,7 @@ Groupby/resample/rolling
 Reshaping
 ^^^^^^^^^
 - Bug in :func:`concat` between a :class:`Series` with integer dtype and another with :class:`CategoricalDtype` with integer categories and containing ``NaN`` values casting to object dtype instead of ``float64`` (:issue:`45359`)
+- Bug in :func:`get_dummies` that selected object and categorical dtypes but not string (:issue:`44965`)
 -
 
 Sparse

pandas/core/reshape/reshape.py

@@ -838,7 +838,7 @@ def get_dummies(
     columns : list-like, default None
         Column names in the DataFrame to be encoded.
         If `columns` is None then all the columns with
-        `object` or `category` dtype will be converted.
+        `object`, `string`, or `category` dtype will be converted.
     sparse : bool, default False
         Whether the dummy-encoded columns should be backed by
         a :class:`SparseArray` (True) or a regular NumPy array (False).
@@ -919,7 +919,7 @@ def get_dummies(
     """
     from pandas.core.reshape.concat import concat
 
-    dtypes_to_encode = ["object", "category"]
+    dtypes_to_encode = ["object", "string", "category"]
 
     if isinstance(data, DataFrame):
         # determine columns being encoded

pandas/tests/reshape/test_get_dummies.py

@@ -196,6 +196,22 @@ def test_dataframe_dummies_all_obj(self, df, sparse):
 
         tm.assert_frame_equal(result, expected)
 
+    def test_dataframe_dummies_string_dtype(self, df):
+        # GH44965
+        df = df[["A", "B"]]
+        df = df.astype({"A": "object", "B": "string"})
+        result = get_dummies(df)
+        expected = DataFrame(
+            {
+                "A_a": [1, 0, 1],
+                "A_b": [0, 1, 0],
+                "B_b": [1, 1, 0],
+                "B_c": [0, 0, 1],
+            },
+            dtype=np.uint8,
+        )
+        tm.assert_frame_equal(result, expected)
+
     def test_dataframe_dummies_mix_default(self, df, sparse, dtype):
         result = get_dummies(df, sparse=sparse, dtype=dtype)
         if sparse: