ENH: Add dtype argument to StringMethods get_dummies()

pandas/core/arrays/arrow/array.py

@@ -41,6 +41,7 @@
     is_list_like,
     is_numeric_dtype,
     is_scalar,
+    pandas_dtype,
 )
 from pandas.core.dtypes.dtypes import DatetimeTZDtype
 from pandas.core.dtypes.missing import isna
@@ -2513,7 +2514,9 @@ def _str_findall(self, pat: str, flags: int = 0) -> Self:
         result = self._apply_elementwise(predicate)
         return type(self)(pa.chunked_array(result))
 
-    def _str_get_dummies(self, sep: str = "|"):
+    def _str_get_dummies(self, sep: str = "|", dtype: NpDtype | None = None):
+        if dtype is None:
+            dtype = np.bool_
         split = pc.split_pattern(self._pa_array, sep)
         flattened_values = pc.list_flatten(split)
         uniques = flattened_values.unique()
@@ -2523,7 +2526,13 @@ def _str_get_dummies(self, sep: str = "|"):
         n_cols = len(uniques)
         indices = pc.index_in(flattened_values, uniques_sorted).to_numpy()
         indices = indices + np.arange(n_rows).repeat(lengths) * n_cols
-        dummies = np.zeros(n_rows * n_cols, dtype=np.bool_)
+        _dtype = pandas_dtype(dtype)
+        dummy_dtype: NpDtype
+        if isinstance(_dtype, np.dtype):
+            dummy_dtype = _dtype
+        else:
+            dummy_dtype = np.bool_
+        dummies = np.zeros(n_rows * n_cols, dtype=dummy_dtype)
         dummies[indices] = True
         dummies = dummies.reshape((n_rows, n_cols))
         result = type(self)(pa.array(list(dummies)))

pandas/core/arrays/categorical.py

@@ -2681,11 +2681,11 @@ def _str_map(
         result = NumpyExtensionArray(categories.to_numpy())._str_map(f, na_value, dtype)
         return take_nd(result, codes, fill_value=na_value)
 
-    def _str_get_dummies(self, sep: str = "|"):
+    def _str_get_dummies(self, sep: str = "|", dtype: NpDtype | None = None):
         # sep may not be in categories. Just bail on this.
         from pandas.core.arrays import NumpyExtensionArray
 
-        return NumpyExtensionArray(self.astype(str))._str_get_dummies(sep)
+        return NumpyExtensionArray(self.astype(str))._str_get_dummies(sep, dtype)
 
     # ------------------------------------------------------------------------
     # GroupBy Methods

pandas/core/arrays/string_arrow.py

@@ -56,6 +56,7 @@
         ArrayLike,
         AxisInt,
         Dtype,
+        NpDtype,
         Scalar,
         Self,
         npt,
@@ -435,12 +436,22 @@ def _str_find(self, sub: str, start: int = 0, end: int | None = None):
             return super()._str_find(sub, start, end)
         return self._convert_int_result(result)
 
-    def _str_get_dummies(self, sep: str = "|"):
-        dummies_pa, labels = ArrowExtensionArray(self._pa_array)._str_get_dummies(sep)
+    def _str_get_dummies(self, sep: str = "|", dtype: NpDtype | None = None):
+        if dtype is None:
+            dtype = np.int64
+        dummies_pa, labels = ArrowExtensionArray(self._pa_array)._str_get_dummies(
+            sep, dtype
+        )
         if len(labels) == 0:
-            return np.empty(shape=(0, 0), dtype=np.int64), labels
+            return np.empty(shape=(0, 0), dtype=dtype), labels
         dummies = np.vstack(dummies_pa.to_numpy())
-        return dummies.astype(np.int64, copy=False), labels
+        _dtype = pandas_dtype(dtype)
+        dummy_dtype: NpDtype
+        if isinstance(_dtype, np.dtype):
+            dummy_dtype = _dtype
+        else:
+            dummy_dtype = np.bool_
+        return dummies.astype(dummy_dtype, copy=False), labels
 
     def _convert_int_result(self, result):
         if self.dtype.na_value is np.nan:

pandas/core/strings/accessor.py

@@ -26,6 +26,7 @@
 from pandas.core.dtypes.common import (
     ensure_object,
     is_bool_dtype,
+    is_extension_array_dtype,
     is_integer,
     is_list_like,
     is_object_dtype,
@@ -54,6 +55,8 @@
         Iterator,
     )
 
+    from pandas._typing import NpDtype
+
     from pandas import (
         DataFrame,
         Index,
@@ -2431,7 +2434,11 @@ def wrap(
         return self._wrap_result(result)
 
     @forbid_nonstring_types(["bytes"])
-    def get_dummies(self, sep: str = "|"):
+    def get_dummies(
+        self,
+        sep: str = "|",
+        dtype: NpDtype | None = None,
+    ):
         """
         Return DataFrame of dummy/indicator variables for Series.
 
@@ -2442,6 +2449,8 @@ def get_dummies(self, sep: str = "|"):
         ----------
         sep : str, default "|"
             String to split on.
+        dtype : dtype, default np.int64
+            Data type for new columns. Only a single dtype is allowed.
 
         Returns
         -------
@@ -2466,10 +2475,30 @@ def get_dummies(self, sep: str = "|"):
         0  1  1  0
         1  0  0  0
         2  1  0  1
+
+        >>> pd.Series(["a|b", np.nan, "a|c"]).str.get_dummies(dtype=bool)
+                a      b      c
+        0   True   True    False
+        1   False  False   False
+        2   True   False   True
         """
+        from pandas.core.frame import DataFrame
+
         # we need to cast to Series of strings as only that has all
         # methods available for making the dummies...
-        result, name = self._data.array._str_get_dummies(sep)
+        result, name = self._data.array._str_get_dummies(sep, dtype)
+        if is_extension_array_dtype(dtype):
+            return self._wrap_result(
+                DataFrame(result, columns=name, dtype=dtype),
+                name=name,
+                returns_string=False,
+            )
+        if isinstance(dtype, ArrowDtype):
+            return self._wrap_result(
+                DataFrame(result, columns=name, dtype=dtype),
+                name=name,
+                returns_string=False,
+            )
         return self._wrap_result(
             result,
             name=name,

pandas/core/strings/base.py

@@ -16,6 +16,7 @@
     import re
 
     from pandas._typing import (
+        NpDtype,
         Scalar,
         Self,
     )
@@ -163,7 +164,7 @@ def _str_wrap(self, width: int, **kwargs):
         pass
 
     @abc.abstractmethod
-    def _str_get_dummies(self, sep: str = "|"):
+    def _str_get_dummies(self, sep: str = "|", dtype: NpDtype | None = None):
         pass
 
     @abc.abstractmethod

pandas/core/strings/object_array.py

@@ -18,6 +18,7 @@
 import pandas._libs.ops as libops
 from pandas.util._exceptions import find_stack_level
 
+from pandas.core.dtypes.common import pandas_dtype
 from pandas.core.dtypes.missing import isna
 
 from pandas.core.strings.base import BaseStringArrayMethods
@@ -398,9 +399,11 @@ def _str_wrap(self, width: int, **kwargs):
         tw = textwrap.TextWrapper(**kwargs)
         return self._str_map(lambda s: "\n".join(tw.wrap(s)))
 
-    def _str_get_dummies(self, sep: str = "|"):
+    def _str_get_dummies(self, sep: str = "|", dtype: NpDtype | None = None):
         from pandas import Series
 
+        if dtype is None:
+            dtype = np.int64
         arr = Series(self).fillna("")
         try:
             arr = sep + arr + sep
@@ -412,7 +415,13 @@ def _str_get_dummies(self, sep: str = "|"):
             tags.update(ts)
         tags2 = sorted(tags - {""})
 
-        dummies = np.empty((len(arr), len(tags2)), dtype=np.int64)
+        _dtype = pandas_dtype(dtype)
+        dummy_dtype: NpDtype
+        if isinstance(_dtype, np.dtype):
+            dummy_dtype = _dtype
+        else:
+            dummy_dtype = np.bool_
+        dummies = np.empty((len(arr), len(tags2)), dtype=dummy_dtype)
 
         def _isin(test_elements: str, element: str) -> bool:
             return element in test_elements

pandas/tests/strings/test_get_dummies.py

@@ -1,13 +1,22 @@
 import numpy as np
+import pytest
+
+import pandas.util._test_decorators as td
 
 from pandas import (
+    ArrowDtype,
     DataFrame,
     Index,
     MultiIndex,
     Series,
     _testing as tm,
 )
 
+try:
+    import pyarrow as pa
+except ImportError:
+    pa = None
+
 
 def test_get_dummies(any_string_dtype):
     s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
@@ -32,22 +41,136 @@ def test_get_dummies_index():
     tm.assert_index_equal(result, expected)
 
 
-def test_get_dummies_with_name_dummy(any_string_dtype):
-    # GH 12180
-    # Dummies named 'name' should work as expected
-    s = Series(["a", "b,name", "b"], dtype=any_string_dtype)
-    result = s.str.get_dummies(",")
-    expected = DataFrame([[1, 0, 0], [0, 1, 1], [0, 1, 0]], columns=["a", "b", "name"])
+@pytest.mark.parametrize(
+    "dtype",
+    [
+        np.uint8,
+        np.int16,
+        np.uint16,
+        np.int32,
+        np.uint32,
+        np.int64,
+        np.uint64,
+        bool,
+        "Int8",
+        "Int16",
+        "Int32",
+        "Int64",
+        "boolean",
+    ],
+)
+def test_get_dummies_with_dtype(any_string_dtype, dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=dtype)
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]], columns=list("abc"), dtype=dtype
+    )
     tm.assert_frame_equal(result, expected)
 
 
-def test_get_dummies_with_name_dummy_index():
-    # GH 12180
-    # Dummies named 'name' should work as expected
-    idx = Index(["a|b", "name|c", "b|name"])
-    result = idx.str.get_dummies("|")
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_int8(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.int8()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.int8()),
+    )
+    tm.assert_frame_equal(result, expected)
 
-    expected = MultiIndex.from_tuples(
-        [(1, 1, 0, 0), (0, 0, 1, 1), (0, 1, 0, 1)], names=("a", "b", "c", "name")
+
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_uint8(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.uint8()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.uint8()),
     )
-    tm.assert_index_equal(result, expected)
+    tm.assert_frame_equal(result, expected)
+
+
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_int16(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.int16()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.int16()),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_uint16(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.uint16()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.uint16()),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_int32(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.int32()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.int32()),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_uint32(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.uint32()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.uint32()),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_int64(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.int64()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.int64()),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_uint64(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.uint64()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.uint64()),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@td.skip_if_no("pyarrow")
+def test_get_dummies_with_pyarrow_dtype_bool(any_string_dtype):
+    s = Series(["a|b", "a|c", np.nan], dtype=any_string_dtype)
+    result = s.str.get_dummies("|", dtype=ArrowDtype(pa.bool_()))
+    expected = DataFrame(
+        [[1, 1, 0], [1, 0, 1], [0, 0, 0]],
+        columns=list("abc"),
+        dtype=ArrowDtype(pa.bool_()),
+    )
+    tm.assert_frame_equal(result, expected)