ENH: add str.removeprefix

doc/source/whatsnew/v1.3.0.rst

@@ -59,6 +59,7 @@ Other enhancements
 - :meth:`Series.loc.__getitem__` and :meth:`Series.loc.__setitem__` with :class:`MultiIndex` now raising helpful error message when indexer has too many dimensions (:issue:`35349`)
 - :meth:`pandas.read_stata` and :class:`StataReader` support reading data from compressed files.
 - Add support for parsing ``ISO 8601``-like timestamps with negative signs to :meth:`pandas.Timedelta` (:issue:`37172`)
+- Added :meth:`Series.str.removeprefix` to remove prefixes from string type Series, which has the same functionality as ``str.removeprefix`` from the Python standard library.
 
 .. ---------------------------------------------------------------------------
 

pandas/core/strings/accessor.py

@@ -2881,6 +2881,44 @@ def casefold(self):
         "isdecimal", docstring=_shared_docs["ismethods"] % _doc_args["isdecimal"]
     )
 
+    @forbid_nonstring_types(["bytes"])
+    def removeprefix(self, prefix: str = None):
+        """
+        Remove a defined prefix from an object series. If the prefix is not present,
+        the original string will be returned.
+
+        Parameters
+        ----------
+        prefix: str, default None
+            Prefix to remove.
+
+        Returns
+        -------
+        Series/Index: object
+            The Series or Index with given prefix removed.
+
+        See also
+        --------
+        Series.str.strip : Remove leading and trailing characters.
+
+        Examples
+        --------
+        >>> s = pd.Series(["str_string1", "str_string2", "no_prefix"])
+        >>> s
+        0    str_string1
+        1    str_string2
+        2      no_prefix
+        dtype: object
+
+        >>> s.str.removeprefix("str_")
+        0      string1
+        1      string2
+        2    no_prefix
+        dtype: object
+        """
+        result = self._data.array._str_removeprefix(prefix)
+        return self._wrap_result(result)
+
 
 def cat_safe(list_of_columns: List, sep: str):
     """

pandas/core/strings/base.py

@@ -223,3 +223,7 @@ def _str_split(self, pat=None, n=-1, expand=False):
     @abc.abstractmethod
     def _str_rsplit(self, pat=None, n=-1):
         pass
+
+    @abc.abstractmethod
+    def _str_removeprefix(self, prefix=None):
+        pass

pandas/core/strings/object_array.py

@@ -430,3 +430,11 @@ def _str_lstrip(self, to_strip=None):
 
     def _str_rstrip(self, to_strip=None):
         return self._str_map(lambda x: x.rstrip(to_strip))
+
+    def _str_removeprefix(self, prefix=None):
+        f_startswith = lambda x: x.startswith(prefix)
+        f_slice = lambda x: x[len(prefix) :]
+        has_prefix = self._str_map(f_startswith, dtype="object")
+        sliced = self._str_map(f_slice, dtype="object")
+
+        return np.where(has_prefix, sliced, self)

pandas/tests/strings/conftest.py

@@ -50,6 +50,7 @@
     ("translate", ({97: 100},), {}),
     ("wrap", (2,), {}),
     ("zfill", (10,), {}),
+    ("removeprefix", ("a ",), {}),
 ] + list(
     zip(
         [

pandas/tests/strings/test_strings.py

@@ -767,3 +767,15 @@ def test_str_accessor_in_apply_func():
     expected = Series(["A/D", "B/E", "C/F"])
     result = df.apply(lambda f: "/".join(f.str.upper()), axis=1)
     tm.assert_series_equal(result, expected)
+
+
+def test_str_removeprefix():
+    # https://github.com/pandas-dev/pandas/issues/36944
+
+    df = DataFrame(
+        {"A": ["str_string1", "str_string2", "str_string3", "string_no_prefix"]}
+    )
+    df["A"] = df["A"].str.removeprefix("str_")
+    result = DataFrame({"A": ["string1", "string2", "string3", "string_no_prefix"]})
+
+    tm.assert_frame_equal(df, result)