CLN: Assorted cleanups (#27094)

Author: jbrockmendel

pandas/core/groupby/ops.py

@@ -475,7 +475,8 @@ def _cython_operation(self, kind, values, how, axis, min_count=-1,
         else:
             if axis > 0:
                 swapped = True
-                values = values.swapaxes(0, axis)
+                assert axis == 1, axis
+                values = values.T
             if arity > 1:
                 raise NotImplementedError("arity of more than 1 is not "
                                           "supported for the 'how' argument")

pandas/core/internals/__init__.py

@@ -1,3 +1,4 @@
+
 from .blocks import (  # noqa: F401
     Block, BoolBlock, CategoricalBlock, ComplexBlock, DatetimeBlock,
     DatetimeTZBlock, ExtensionBlock, FloatBlock, IntBlock, ObjectBlock,
@@ -9,7 +10,7 @@
 from .blocks import _safe_reshape  # noqa: F401; io.packers
 from .blocks import make_block  # noqa: F401; io.pytables, io.packers
 from .managers import (  # noqa: F401; reshape.concat, reshape.merge
+    _transform_index,
     concatenate_block_managers)
-from .managers import items_overlap_with_suffix  # noqa: F401; reshape.merge
 
 from .blocks import _block_shape  # noqa:F401; io.pytables

pandas/core/internals/blocks.py

@@ -722,16 +722,28 @@ def replace(self, to_replace, value, inplace=False, filter=None,
         try:
             values, to_replace = self._try_coerce_args(self.values,
                                                        to_replace)
-            mask = missing.mask_missing(values, to_replace)
-            if filter is not None:
-                filtered_out = ~self.mgr_locs.isin(filter)
-                mask[filtered_out.nonzero()[0]] = False
+        except (TypeError, ValueError):
+            # GH 22083, TypeError or ValueError occurred within error handling
+            # causes infinite loop. Cast and retry only if not objectblock.
+            if is_object_dtype(self):
+                raise
+
+            # try again with a compatible block
+            block = self.astype(object)
+            return block.replace(to_replace=original_to_replace,
+                                 value=value,
+                                 inplace=inplace,
+                                 filter=filter,
+                                 regex=regex,
+                                 convert=convert)
+
+        mask = missing.mask_missing(values, to_replace)
+        if filter is not None:
+            filtered_out = ~self.mgr_locs.isin(filter)
+            mask[filtered_out.nonzero()[0]] = False
 
+        try:
             blocks = self.putmask(mask, value, inplace=inplace)
-            if convert:
-                blocks = [b.convert(by_item=True, numeric=False,
-                                    copy=not inplace) for b in blocks]
-            return blocks
         except (TypeError, ValueError):
             # GH 22083, TypeError or ValueError occurred within error handling
             # causes infinite loop. Cast and retry only if not objectblock.
@@ -746,6 +758,10 @@ def replace(self, to_replace, value, inplace=False, filter=None,
                                  filter=filter,
                                  regex=regex,
                                  convert=convert)
+        if convert:
+            blocks = [b.convert(by_item=True, numeric=False,
+                                copy=not inplace) for b in blocks]
+        return blocks
 
     def _replace_single(self, *args, **kwargs):
         """ no-op on a non-ObjectBlock """

pandas/core/internals/managers.py

@@ -1859,48 +1859,6 @@ def _compare_or_regex_search(a, b, regex=False):
     return result
 
 
-# TODO: this is no longer used in this module, could be moved to concat
-def items_overlap_with_suffix(left, lsuffix, right, rsuffix):
-    """
-    If two indices overlap, add suffixes to overlapping entries.
-
-    If corresponding suffix is empty, the entry is simply converted to string.
-
-    """
-    to_rename = left.intersection(right)
-    if len(to_rename) == 0:
-        return left, right
-    else:
-        if not lsuffix and not rsuffix:
-            raise ValueError('columns overlap but no suffix specified: '
-                             '{rename}'.format(rename=to_rename))
-
-        def renamer(x, suffix):
-            """Rename the left and right indices.
-
-            If there is overlap, and suffix is not None, add
-            suffix, otherwise, leave it as-is.
-
-            Parameters
-            ----------
-            x : original column name
-            suffix : str or None
-
-            Returns
-            -------
-            x : renamed column name
-            """
-            if x in to_rename and suffix is not None:
-                return '{x}{suffix}'.format(x=x, suffix=suffix)
-            return x
-
-        lrenamer = partial(renamer, suffix=lsuffix)
-        rrenamer = partial(renamer, suffix=rsuffix)
-
-        return (_transform_index(left, lrenamer),
-                _transform_index(right, rrenamer))
-
-
 def _transform_index(index, func, level=None):
     """
     Apply function to all values found in index.

pandas/core/reshape/merge.py

@@ -3,6 +3,7 @@
 """
 
 import copy
+from functools import partial
 import string
 import warnings
 
@@ -27,8 +28,7 @@
 from pandas.core.arrays.categorical import _recode_for_categories
 import pandas.core.common as com
 from pandas.core.frame import _merge_doc
-from pandas.core.internals import (
-    concatenate_block_managers, items_overlap_with_suffix)
+from pandas.core.internals import _transform_index, concatenate_block_managers
 import pandas.core.sorting as sorting
 from pandas.core.sorting import is_int64_overflow_possible
 
@@ -555,8 +555,8 @@ def get_result(self):
         ldata, rdata = self.left._data, self.right._data
         lsuf, rsuf = self.suffixes
 
-        llabels, rlabels = items_overlap_with_suffix(ldata.items, lsuf,
-                                                     rdata.items, rsuf)
+        llabels, rlabels = _items_overlap_with_suffix(ldata.items, lsuf,
+                                                      rdata.items, rsuf)
 
         lindexers = {1: left_indexer} if left_indexer is not None else {}
         rindexers = {1: right_indexer} if right_indexer is not None else {}
@@ -1303,8 +1303,8 @@ def get_result(self):
         ldata, rdata = self.left._data, self.right._data
         lsuf, rsuf = self.suffixes
 
-        llabels, rlabels = items_overlap_with_suffix(ldata.items, lsuf,
-                                                     rdata.items, rsuf)
+        llabels, rlabels = _items_overlap_with_suffix(ldata.items, lsuf,
+                                                      rdata.items, rsuf)
 
         if self.fill_method == 'ffill':
             left_join_indexer = libjoin.ffill_indexer(left_indexer)
@@ -1809,3 +1809,45 @@ def validate_operand(obj):
     else:
         raise TypeError('Can only merge Series or DataFrame objects, '
                         'a {obj} was passed'.format(obj=type(obj)))
+
+
+def _items_overlap_with_suffix(left, lsuffix, right, rsuffix):
+    """
+    If two indices overlap, add suffixes to overlapping entries.
+
+    If corresponding suffix is empty, the entry is simply converted to string.
+
+    """
+    to_rename = left.intersection(right)
+    if len(to_rename) == 0:
+        return left, right
+
+    if not lsuffix and not rsuffix:
+        raise ValueError('columns overlap but no suffix specified: '
+                         '{rename}'.format(rename=to_rename))
+
+    def renamer(x, suffix):
+        """
+        Rename the left and right indices.
+
+        If there is overlap, and suffix is not None, add
+        suffix, otherwise, leave it as-is.
+
+        Parameters
+        ----------
+        x : original column name
+        suffix : str or None
+
+        Returns
+        -------
+        x : renamed column name
+        """
+        if x in to_rename and suffix is not None:
+            return '{x}{suffix}'.format(x=x, suffix=suffix)
+        return x
+
+    lrenamer = partial(renamer, suffix=lsuffix)
+    rrenamer = partial(renamer, suffix=rsuffix)
+
+    return (_transform_index(left, lrenamer),
+            _transform_index(right, rrenamer))

pandas/tests/io/test_html.py

@@ -262,6 +262,7 @@ def test_bad_url_protocol(self):
             self.read_html('git://github.com', match='.*Water.*')
 
     @network
+    @pytest.mark.slow
     def test_invalid_url(self):
         try:
             with pytest.raises(URLError):