Series string repeat

python/cudf/cudf/_lib/cpp/strings/repeat.pxd

@@ -0,0 +1,19 @@
+# Copyright (c) 2021, NVIDIA CORPORATION.
+
+from libcpp.memory cimport unique_ptr
+
+from cudf._lib.cpp.column.column cimport column
+from cudf._lib.cpp.column.column_view cimport column_view
+from cudf._lib.cpp.types cimport size_type
+
+
+cdef extern from "cudf/strings/repeat_strings.hpp" namespace "cudf::strings" \
+        nogil:
+
+    cdef unique_ptr[column] repeat_strings(
+        column_view strings,
+        size_type repeat) except +
+
+    cdef unique_ptr[column] repeat_strings(
+        column_view strings,
+        column_view repeats) except +

python/cudf/cudf/_lib/strings/__init__.py

@@ -64,6 +64,7 @@
 from cudf._lib.strings.findall import findall
 from cudf._lib.strings.json import get_json_object
 from cudf._lib.strings.padding import PadSide, center, ljust, pad, rjust, zfill
+from cudf._lib.strings.repeat import repeat_scalar, repeat_sequence
 from cudf._lib.strings.replace import (
     insert,
     replace,

python/cudf/cudf/_lib/strings/repeat.pyx

@@ -0,0 +1,49 @@
+# Copyright (c) 2021, NVIDIA CORPORATION.
+
+from libcpp.memory cimport unique_ptr
+from libcpp.utility cimport move
+
+from cudf._lib.column cimport Column
+from cudf._lib.cpp.column.column cimport column
+from cudf._lib.cpp.column.column_view cimport column_view
+from cudf._lib.cpp.strings cimport repeat as cpp_repeat
+from cudf._lib.cpp.types cimport size_type
+
+
+def repeat_scalar(Column source_strings,
+                  size_type repeats):
+    """
+    Returns a Column after repeating
+    each string in `source_strings`
+    `repeats` number of times.
+    """
+    cdef unique_ptr[column] c_result
+    cdef column_view source_view = source_strings.view()
+
+    with nogil:
+        c_result = move(cpp_repeat.repeat_strings(
+            source_view,
+            repeats
+        ))
+
+    return Column.from_unique_ptr(move(c_result))
+
+
+def repeat_sequence(Column source_strings,
+                    Column repeats):
+    """
+    Returns a Column after repeating
+    each string in `source_strings`
+    `repeats` number of times.
+    """
+    cdef unique_ptr[column] c_result
+    cdef column_view source_view = source_strings.view()
+    cdef column_view repeats_view = repeats.view()
+
+    with nogil:
+        c_result = move(cpp_repeat.repeat_strings(
+            source_view,
+            repeats_view
+        ))
+
+    return Column.from_unique_ptr(move(c_result))

python/cudf/cudf/core/column/string.py

@@ -749,6 +749,65 @@ def contains(
             )
         return self._return_or_inplace(result_col)
 
+    def repeat(self, repeats: Union[int, Sequence],) -> SeriesOrIndex:
+        """
+        Duplicate each string in the Series or Index.
+        Equivalent to `str.repeat()
+        <https://pandas.pydata.org/docs/reference/api/pandas.Series.str.repeat.html>`_.
+
+        Parameters
+        ----------
+        repeats : int or sequence of int
+            Same value for all (int) or different value per (sequence).
+
+        Returns
+        -------
+        Series or Index of object
+            Series or Index of repeated string objects specified by
+            input parameter repeats.
+
+        Examples
+        --------
+        >>> s = cudf.Series(['a', 'b', 'c'])
+        >>> s
+        0    a
+        1    b
+        2    c
+        dtype: object
+
+        Single int repeats string in Series
+
+        >>> s.str.repeat(repeats=2)
+        0    aa
+        1    bb
+        2    cc
+        dtype: object
+
+        Sequence of int repeats corresponding string in Series
+
+        >>> s.str.repeat(repeats=[1, 2, 3])
+        0      a
+        1     bb
+        2    ccc
+        dtype: object
+        """
+        none_flag = False
+        if repeats is None:
+            none_flag = True
+            repeats = [None] * len(self._column)
+
+        if can_convert_to_column(repeats):
+            result = self._return_or_inplace(
+                libstrings.repeat_sequence(
+                    self._column, column.as_column(repeats, dtype="int"),
+                ),
+            )
+            return result.astype("float64") if none_flag else result
+
+        return self._return_or_inplace(
+            libstrings.repeat_scalar(self._column, repeats)
+        )
+
     def replace(
         self,
         pat: Union[str, Sequence],

python/cudf/cudf/tests/test_string.py

@@ -852,6 +852,33 @@ def test_string_contains(ps_gs, pat, regex, flags, flags_raise, na, na_raise):
         assert_eq(expect, got)
 
 
+@pytest.mark.parametrize(
+    "data", [["hello", "world", None, "", "!"]],
+)
+@pytest.mark.parametrize(
+    "repeats",
+    [
+        2,
+        0,
+        -3,
+        None,
+        [5, 4, 3, 2, 6],
+        [5, None, 3, 2, 6],
+        [0, 0, 0, 0, 0],
+        [-1, -2, -3, -4, -5],
+        [None, None, None, None, None],
+    ],
+)
+def test_string_repeat(data, repeats):
+    ps = pd.Series(data)
+    gs = cudf.from_pandas(ps)
+
+    expect = ps.str.repeat(repeats)
+    got = gs.str.repeat(repeats)
+
+    assert_eq(expect, got)
+
+
 # Pandas isn't respect the `n` parameter so ignoring it in test parameters
 @pytest.mark.parametrize(
     "pat,regex",