ENH: str.replace accepts a compiled expression

.str.replace now accepts a compiled regular expression for `pat`.

See #15446

Author: rouzazari

doc/source/whatsnew/v0.20.0.txt

@@ -28,6 +28,7 @@ New features
 
 - Integration with the ``feather-format``, including a new top-level ``pd.read_feather()`` and ``DataFrame.to_feather()`` method, see :ref:`here <io.feather>`.
 - ``.str.replace`` now accepts a callable, as replacement, which is passed to ``re.sub`` (:issue:`15055`)
+- ``.str.replace`` now accepts a compiled regular expression as pattern (:issue:`15446`)
 
 
 

pandas/core/strings.py

@@ -311,8 +311,12 @@ def str_replace(arr, pat, repl, n=-1, case=True, flags=0):
 
     Parameters
     ----------
-    pat : string
-        Character sequence or regular expression
+    pat : string or compiled regex
+        String can be a character sequence or regular expression.
+
+        .. versionadded:: 0.20.0
+            `pat` also accepts a compiled regex.
+
     repl : string or callable
         Replacement string or a callable. The callable is passed the regex
         match object and must return a replacement string to be used.
@@ -324,9 +328,10 @@ def str_replace(arr, pat, repl, n=-1, case=True, flags=0):
     n : int, default -1 (all)
         Number of replacements to make from start
     case : boolean, default True
-        If True, case sensitive
+        If True, case sensitive. Raises if `pat` is a compiled regex.
     flags : int, default 0 (no flags)
-        re module flags, e.g. re.IGNORECASE
+        re module flags, e.g. re.IGNORECASE. Raises if `pat` is a compiled
+        regex.
 
     Returns
     -------
@@ -372,21 +377,33 @@ def str_replace(arr, pat, repl, n=-1, case=True, flags=0):
     0    tWO
     1    bAR
     dtype: object
+
+    When `pat` is a compiled regex, all flags should be included in the
+    compiled regex. Use of `case` and `flags` with a compiled regex will
+    raise an error.
+
+    >>> regex_pat = re.compile(r'FUZ', flags=re.IGNORECASE)
+    >>> pd.Series(['foo', 'fuz', np.nan]).str.replace(regex_pat, 'bar')
+    0    foo
+    1    bar
+    2    NaN
+    dtype: object
     """
 
     # Check whether repl is valid (GH 13438, GH 15055)
     if not (is_string_like(repl) or callable(repl)):
         raise TypeError("repl must be a string or callable")
-    use_re = not case or len(pat) > 1 or flags or callable(repl)
+    # Check whether pat is a compiled regex or should be compiled
+    is_compiled_re = isinstance(pat, type(re.compile("")))
+    use_re = (is_compiled_re or not case or
+              len(pat) > 1 or flags or callable(repl))
 
     if use_re:
         if not case:
             flags |= re.IGNORECASE
-        regex = re.compile(pat, flags=flags)
         n = n if n >= 0 else 0
-
-        def f(x):
-            return regex.sub(repl, x, count=n)
+        f = lambda x: re.sub(pattern=pat, repl=repl, string=x,
+                             count=n, flags=flags)
     else:
         f = lambda x: x.replace(pat, repl, n)
 

pandas/tests/test_strings.py

@@ -469,6 +469,62 @@ def test_replace_callable(self):
         exp = Series(['bAR', NA])
         tm.assert_series_equal(result, exp)
 
+    def test_replace_compiled_regex(self):
+        # GH 15446
+        values = Series(['fooBAD__barBAD', NA])
+
+        # test with compiled regex
+        pat = re.compile(r'BAD[_]*')
+        result = values.str.replace(pat, '')
+        exp = Series(['foobar', NA])
+        tm.assert_series_equal(result, exp)
+
+        # mixed
+        mixed = Series(['aBAD', NA, 'bBAD', True, datetime.today(), 'fooBAD',
+                        None, 1, 2.])
+
+        rs = Series(mixed).str.replace(pat, '')
+        xp = Series(['a', NA, 'b', NA, NA, 'foo', NA, NA, NA])
+        tm.assertIsInstance(rs, Series)
+        tm.assert_almost_equal(rs, xp)
+
+        # unicode
+        values = Series([u('fooBAD__barBAD'), NA])
+
+        result = values.str.replace(pat, '')
+        exp = Series([u('foobar'), NA])
+        tm.assert_series_equal(result, exp)
+
+        result = values.str.replace(pat, '', n=1)
+        exp = Series([u('foobarBAD'), NA])
+        tm.assert_series_equal(result, exp)
+
+        # flags + unicode
+        values = Series([b"abcd,\xc3\xa0".decode("utf-8")])
+        exp = Series([b"abcd, \xc3\xa0".decode("utf-8")])
+        pat = re.compile(r"(?<=\w),(?=\w)", flags=re.UNICODE)
+        result = values.str.replace(pat, ", ")
+        tm.assert_series_equal(result, exp)
+
+        # case and flags provided to str.replace will have no effect
+        # and will produce warnings
+        values = Series(['fooBAD__barBAD__bad', NA])
+        pat = re.compile(r'BAD[_]*')
+
+        with tm.assertRaisesRegexp(ValueError, "process flags argument"):
+            result = values.str.replace(pat, '', flags=re.IGNORECASE)
+
+        with tm.assertRaisesRegexp(ValueError, "process flags argument"):
+            result = values.str.replace(pat, '', case=False)
+
+        # test with callable
+        values = Series(['fooBAD__barBAD', NA])
+        repl = lambda m: m.group(0).swapcase()
+        pat = re.compile('[a-z][A-Z]{2}')
+        result = values.str.replace(pat, repl, n=2)
+        exp = Series(['foObaD__baRbaD', NA])
+        tm.assert_series_equal(result, exp)
+
     def test_repeat(self):
         values = Series(['a', 'b', NA, 'c', NA, 'd'])