CLN: indexing (pandas-dev#37142)

Author: jbrockmendel

pandas/core/frame.py

@@ -3091,7 +3091,7 @@ def _setitem_array(self, key, value):
                 for k1, k2 in zip(key, value.columns):
                     self[k1] = value[k2]
             else:
-                self.loc._ensure_listlike_indexer(key, axis=1)
+                self.loc._ensure_listlike_indexer(key, axis=1, value=value)
                 indexer = self.loc._get_listlike_indexer(
                     key, axis=1, raise_missing=False
                 )[1]

pandas/core/indexing.py

@@ -633,7 +633,7 @@ def _get_setitem_indexer(self, key):
                 raise
             raise IndexingError(key) from e
 
-    def _ensure_listlike_indexer(self, key, axis=None):
+    def _ensure_listlike_indexer(self, key, axis=None, value=None):
         """
         Ensure that a list-like of column labels are all present by adding them if
         they do not already exist.
@@ -663,9 +663,14 @@ def _ensure_listlike_indexer(self, key, axis=None):
             and not com.is_bool_indexer(key)
             and all(is_hashable(k) for k in key)
         ):
-            for k in key:
+            for i, k in enumerate(key):
                 if k not in self.obj:
-                    self.obj[k] = np.nan
+                    if value is None:
+                        self.obj[k] = np.nan
+                    elif is_list_like(value):
+                        self.obj[k] = value[i]
+                    else:
+                        self.obj[k] = value
 
     def __setitem__(self, key, value):
         if isinstance(key, tuple):
@@ -1540,9 +1545,10 @@ def _setitem_with_indexer(self, indexer, value):
         # if there is only one block/type, still have to take split path
         # unless the block is one-dimensional or it can hold the value
         if not take_split_path and self.obj._mgr.blocks:
-            (blk,) = self.obj._mgr.blocks
-            if 1 < blk.ndim:  # in case of dict, keys are indices
+            if self.ndim > 1:
+                # in case of dict, keys are indices
                 val = list(value.values()) if isinstance(value, dict) else value
+                blk = self.obj._mgr.blocks[0]
                 take_split_path = not blk._can_hold_element(val)
 
         # if we have any multi-indexes that have non-trivial slices
@@ -1576,10 +1582,7 @@ def _setitem_with_indexer(self, indexer, value):
                         # must have all defined axes if we have a scalar
                         # or a list-like on the non-info axes if we have a
                         # list-like
-                        len_non_info_axes = (
-                            len(_ax) for _i, _ax in enumerate(self.obj.axes) if _i != i
-                        )
-                        if any(not l for l in len_non_info_axes):
+                        if not len(self.obj):
                             if not is_list_like_indexer(value):
                                 raise ValueError(
                                     "cannot set a frame with no "
@@ -1764,7 +1767,7 @@ def _setitem_with_indexer(self, indexer, value):
                     self._setitem_single_column(loc, value, pi)
 
         else:
-            self._setitem_single_block_inplace(indexer, value)
+            self._setitem_single_block(indexer, value)
 
     def _setitem_single_column(self, loc: int, value, plane_indexer):
         # positional setting on column loc
@@ -1791,10 +1794,9 @@ def _setitem_single_column(self, loc: int, value, plane_indexer):
         # reset the sliced object if unique
         self.obj._iset_item(loc, ser)
 
-    def _setitem_single_block_inplace(self, indexer, value):
+    def _setitem_single_block(self, indexer, value):
         """
-        _setitem_with_indexer for the case when we have a single Block
-        and the value can be set into it without casting.
+        _setitem_with_indexer for the case when we have a single Block.
         """
         from pandas import Series
 

pandas/core/internals/blocks.py

@@ -340,7 +340,7 @@ def dtype(self):
     def iget(self, i):
         return self.values[i]
 
-    def set(self, locs, values):
+    def set_inplace(self, locs, values):
         """
         Modify block values in-place with new item value.
 
@@ -1676,7 +1676,9 @@ def iget(self, col):
                 raise IndexError(f"{self} only contains one item")
             return self.values
 
-    def set(self, locs, values):
+    def set_inplace(self, locs, values):
+        # NB: This is a misnomer, is supposed to be inplace but is not,
+        #  see GH#33457
         assert locs.tolist() == [0]
         self.values = values
 
@@ -2231,7 +2233,7 @@ def _can_hold_element(self, element: Any) -> bool:
 
         return is_valid_nat_for_dtype(element, self.dtype)
 
-    def set(self, locs, values):
+    def set_inplace(self, locs, values):
         """
         See Block.set.__doc__
         """

pandas/core/internals/managers.py

@@ -1083,7 +1083,7 @@ def value_getitem(placement):
             blk = self.blocks[blkno]
             blk_locs = blklocs[val_locs.indexer]
             if blk.should_store(value):
-                blk.set(blk_locs, value_getitem(val_locs))
+                blk.set_inplace(blk_locs, value_getitem(val_locs))
             else:
                 unfit_mgr_locs.append(blk.mgr_locs.as_array[blk_locs])
                 unfit_val_locs.append(val_locs)