CLN: simplify take_2d_multi (pandas-dev#29065)

Author: jbrockmendel

pandas/core/algorithms.py

@@ -1304,7 +1304,7 @@ def get_indexer(current_indexer, other_indexer):
         return frame.sort_values(columns, ascending=ascending, kind="mergesort")
 
 
-# ------- ## ---- #
+# ---- #
 # take #
 # ---- #
 
@@ -1712,59 +1712,44 @@ def take_nd(
 take_1d = take_nd
 
 
-def take_2d_multi(
-    arr, indexer, out=None, fill_value=np.nan, mask_info=None, allow_fill=True
-):
+def take_2d_multi(arr, indexer, fill_value=np.nan):
     """
     Specialized Cython take which sets NaN values in one pass
     """
-    if indexer is None or (indexer[0] is None and indexer[1] is None):
-        row_idx = np.arange(arr.shape[0], dtype=np.int64)
-        col_idx = np.arange(arr.shape[1], dtype=np.int64)
-        indexer = row_idx, col_idx
-        dtype, fill_value = arr.dtype, arr.dtype.type()
-    else:
-        row_idx, col_idx = indexer
-        if row_idx is None:
-            row_idx = np.arange(arr.shape[0], dtype=np.int64)
-        else:
-            row_idx = ensure_int64(row_idx)
-        if col_idx is None:
-            col_idx = np.arange(arr.shape[1], dtype=np.int64)
-        else:
-            col_idx = ensure_int64(col_idx)
-        indexer = row_idx, col_idx
-        if not allow_fill:
+    # This is only called from one place in DataFrame._reindex_multi,
+    #  so we know indexer is well-behaved.
+    assert indexer is not None
+    assert indexer[0] is not None
+    assert indexer[1] is not None
+
+    row_idx, col_idx = indexer
+
+    row_idx = ensure_int64(row_idx)
+    col_idx = ensure_int64(col_idx)
+    indexer = row_idx, col_idx
+    mask_info = None
+
+    # check for promotion based on types only (do this first because
+    # it's faster than computing a mask)
+    dtype, fill_value = maybe_promote(arr.dtype, fill_value)
+    if dtype != arr.dtype:
+        # check if promotion is actually required based on indexer
+        row_mask = row_idx == -1
+        col_mask = col_idx == -1
+        row_needs = row_mask.any()
+        col_needs = col_mask.any()
+        mask_info = (row_mask, col_mask), (row_needs, col_needs)
+
+        if not (row_needs or col_needs):
+            # if not, then depromote, set fill_value to dummy
+            # (it won't be used but we don't want the cython code
+            # to crash when trying to cast it to dtype)
             dtype, fill_value = arr.dtype, arr.dtype.type()
-            mask_info = None, False
-        else:
-            # check for promotion based on types only (do this first because
-            # it's faster than computing a mask)
-            dtype, fill_value = maybe_promote(arr.dtype, fill_value)
-            if dtype != arr.dtype and (out is None or out.dtype != dtype):
-                # check if promotion is actually required based on indexer
-                if mask_info is not None:
-                    (row_mask, col_mask), (row_needs, col_needs) = mask_info
-                else:
-                    row_mask = row_idx == -1
-                    col_mask = col_idx == -1
-                    row_needs = row_mask.any()
-                    col_needs = col_mask.any()
-                    mask_info = (row_mask, col_mask), (row_needs, col_needs)
-                if row_needs or col_needs:
-                    if out is not None and out.dtype != dtype:
-                        raise TypeError("Incompatible type for fill_value")
-                else:
-                    # if not, then depromote, set fill_value to dummy
-                    # (it won't be used but we don't want the cython code
-                    # to crash when trying to cast it to dtype)
-                    dtype, fill_value = arr.dtype, arr.dtype.type()
 
     # at this point, it's guaranteed that dtype can hold both the arr values
     # and the fill_value
-    if out is None:
-        out_shape = len(row_idx), len(col_idx)
-        out = np.empty(out_shape, dtype=dtype)
+    out_shape = len(row_idx), len(col_idx)
+    out = np.empty(out_shape, dtype=dtype)
 
     func = _take_2d_multi_dict.get((arr.dtype.name, out.dtype.name), None)
     if func is None and arr.dtype != out.dtype:

pandas/core/generic.py

@@ -4606,7 +4606,7 @@ def _needs_reindex_multi(self, axes, method, level):
         )
 
     def _reindex_multi(self, axes, copy, fill_value):
-        return NotImplemented
+        raise AbstractMethodError(self)
 
     def _reindex_with_indexers(
         self, reindexers, fill_value=None, copy=False, allow_dups=False