CLN: Make iterators lazier (#58200)

Author: mroeschke

pandas/core/apply.py

@@ -1710,9 +1710,9 @@ def normalize_keyword_aggregation(
     # TODO: aggspec type: typing.Dict[str, List[AggScalar]]
     aggspec = defaultdict(list)
     order = []
-    columns, pairs = list(zip(*kwargs.items()))
+    columns = tuple(kwargs.keys())
 
-    for column, aggfunc in pairs:
+    for column, aggfunc in kwargs.values():
         aggspec[column].append(aggfunc)
         order.append((column, com.get_callable_name(aggfunc) or aggfunc))
 

pandas/core/frame.py

@@ -6168,12 +6168,13 @@ class    max    type
             names = self.index._get_default_index_names(names, default)
 
             if isinstance(self.index, MultiIndex):
-                to_insert = zip(self.index.levels, self.index.codes)
+                to_insert = zip(reversed(self.index.levels), reversed(self.index.codes))
             else:
                 to_insert = ((self.index, None),)
 
             multi_col = isinstance(self.columns, MultiIndex)
-            for i, (lev, lab) in reversed(list(enumerate(to_insert))):
+            for j, (lev, lab) in enumerate(to_insert, start=1):
+                i = self.index.nlevels - j
                 if level is not None and i not in level:
                     continue
                 name = names[i]

pandas/core/groupby/ops.py

@@ -706,7 +706,7 @@ def groups(self) -> dict[Hashable, Index]:
             return self.groupings[0].groups
         result_index, ids = self.result_index_and_ids
         values = result_index._values
-        categories = Categorical(ids, categories=np.arange(len(result_index)))
+        categories = Categorical(ids, categories=range(len(result_index)))
         result = {
             # mypy is not aware that group has to be an integer
             values[group]: self.axis.take(axis_ilocs)  # type: ignore[call-overload]

pandas/core/indexing.py

@@ -899,7 +899,7 @@ def __setitem__(self, key, value) -> None:
 
         check_dict_or_set_indexers(key)
         if isinstance(key, tuple):
-            key = tuple(list(x) if is_iterator(x) else x for x in key)
+            key = (list(x) if is_iterator(x) else x for x in key)
             key = tuple(com.apply_if_callable(x, self.obj) for x in key)
         else:
             maybe_callable = com.apply_if_callable(key, self.obj)
@@ -1177,7 +1177,7 @@ def _check_deprecated_callable_usage(self, key: Any, maybe_callable: T) -> T:
     def __getitem__(self, key):
         check_dict_or_set_indexers(key)
         if type(key) is tuple:
-            key = tuple(list(x) if is_iterator(x) else x for x in key)
+            key = (list(x) if is_iterator(x) else x for x in key)
             key = tuple(com.apply_if_callable(x, self.obj) for x in key)
             if self._is_scalar_access(key):
                 return self.obj._get_value(*key, takeable=self._takeable)

pandas/core/sorting.py

@@ -172,8 +172,6 @@ def maybe_lift(lab, size: int) -> tuple[np.ndarray, int]:
         for i, (lab, size) in enumerate(zip(labels, shape)):
             labels[i], lshape[i] = maybe_lift(lab, size)
 
-    labels = list(labels)
-
     # Iteratively process all the labels in chunks sized so less
     # than lib.i8max unique int ids will be required for each chunk
     while True: