Fixed issue 18657

Author: axel-d-one

pandas/core/strings.py

@@ -35,10 +35,23 @@
 _shared_docs = dict()
 
 
-def _get_array_list(arr, others):
+def _get_array_list(arr, others, align=True):
     from pandas.core.series import Series
-
-    if len(others) and isinstance(com._values_from_object(others)[0],
+    
+    if (len(arr) and isinstance(arr, Series)
+            and len(others) and isinstance(others, Series)):
+        if align is None:
+            align = False
+            warnings.warn("A future version of pandas will perform alignment "
+                          "when others is a series. To disable alignment (the "
+                          "previous behavior) and silence this warning, pass "
+                          "'align=False'. To enable alignment (the future "
+                          "behavior) and silence this warning, pass "
+                          "'align=True'")
+        if align:
+            arr, others = arr.align(others, join = 'left')
+        arrays = [list(arr), list(others)]
+    elif len(others) and isinstance(com._values_from_object(others)[0],
                                   (list, np.ndarray, Series)):
         arrays = [arr] + list(others)
     else:
@@ -47,7 +60,7 @@ def _get_array_list(arr, others):
     return [np.asarray(x, dtype=object) for x in arrays]
 
 
-def str_cat(arr, others=None, sep=None, na_rep=None):
+def str_cat(arr, others=None, sep=None, na_rep=None, align=None):
     """
     Concatenate strings in the Series/Index with given separator.
 
@@ -109,7 +122,7 @@ def str_cat(arr, others=None, sep=None, na_rep=None):
         sep = ''
 
     if others is not None:
-        arrays = _get_array_list(arr, others)
+        arrays = _get_array_list(arr, others, align=align)
 
         n = _length_check(arrays)
         masks = np.array([isna(x) for x in arrays])
@@ -1737,9 +1750,10 @@ def cons_row(x):
                 return cons(result, name=name, index=index)
 
     @copy(str_cat)
-    def cat(self, others=None, sep=None, na_rep=None):
+    def cat(self, others=None, sep=None, na_rep=None, align=None):
         data = self._orig if self._is_categorical else self._data
-        result = str_cat(data, others=others, sep=sep, na_rep=na_rep)
+        result = str_cat(data, others=others, sep=sep,
+                         na_rep=na_rep, align=align)
         return self._wrap_result(result, use_codes=(not self._is_categorical))
 
     @copy(str_split)

pandas/tests/test_strings.py

@@ -2743,11 +2743,12 @@ def test_cat_on_filtered_index(self):
 
         str_year = df.year.astype('str')
         str_month = df.month.astype('str')
-        str_both = str_year.str.cat(str_month, sep=' ')
+        str_both = str_year.str.cat(str_month, sep=' ', align=True)
 
         assert str_both.loc[1] == '2011 2'
 
-        str_multiple = str_year.str.cat([str_month, str_month], sep=' ')
+        str_multiple = str_year.str.cat([str_month, str_month],
+                                        sep=' ', align=True)
 
         assert str_multiple.loc[1] == '2011 2 2'
 
@@ -2759,6 +2760,18 @@ def test_str_cat_raises_intuitive_error(self):
             s.str.cat('|')
         with tm.assert_raises_regex(ValueError, message):
             s.str.cat('    ')
+    
+    def test_str_cat_align(self):
+        # https://github.com/pandas-dev/pandas/issues/18657
+        s = Series(['a', 'b', 'c', 'd'])
+        t = Series(['a', 'b', 'c', 'd']).reindex([1,3,0,2])
+        expect_aligned = Series(['aa', 'bb', 'cc', 'dd'])
+        expect_unaligned = Series(['ab', 'bd', 'ca', 'dc'])
+        with tm.assert_produces_warning(expected_warning=UserWarning):
+            tm.assert_series_equal(s.str.cat(t), expect_unaligned)
+        tm.assert_series_equal(s.str.cat(t, align=False), expect_unaligned)
+        tm.assert_series_equal(s.str.cat(t, align=True), expect_aligned)
+        
 
     def test_index_str_accessor_visibility(self):
         from pandas.core.strings import StringMethods
@@ -2819,9 +2832,9 @@ def test_method_on_bytes(self):
         lhs = Series(np.array(list('abc'), 'S1').astype(object))
         rhs = Series(np.array(list('def'), 'S1').astype(object))
         if compat.PY3:
-            pytest.raises(TypeError, lhs.str.cat, rhs)
+            pytest.raises(TypeError, lhs.str.cat, rhs, align=True)
         else:
-            result = lhs.str.cat(rhs)
+            result = lhs.str.cat(rhs, align=True)
             expected = Series(np.array(
                 ['ad', 'be', 'cf'], 'S2').astype(object))
             tm.assert_series_equal(result, expected)