feat: add GroupBy.__iter__

Author: tswast

bigframes/core/groupby/__init__.py

@@ -15,7 +15,7 @@
 from __future__ import annotations
 
 import typing
-from typing import Sequence, Union
+from typing import Iterable, Sequence, Tuple, Union
 
 import bigframes_vendored.constants as constants
 import bigframes_vendored.pandas.core.groupby as vendored_pandas_groupby
@@ -142,6 +142,10 @@ def head(self, n: int = 5) -> df.DataFrame:
             )
         )
 
+    def __iter__(self) -> Iterable[Tuple[blocks.Label, pd.DataFrame]]:
+        # TODO: make a struct of all columns and then array_agg that.
+        return ()
+
     def size(self) -> typing.Union[df.DataFrame, series.Series]:
         agg_block, _ = self._block.aggregate_size(
             by_column_ids=self._by_col_ids,

third_party/bigframes_vendored/pandas/core/groupby/__init__.py

@@ -1032,11 +1032,11 @@ def size(self):
 
         **Examples:**
 
-        For SeriesGroupBy:
-
             >>> import bigframes.pandas as bpd
             >>> bpd.options.display.progress_bar = None
 
+        For SeriesGroupBy:
+
             >>> lst = ['a', 'a', 'b']
             >>> ser = bpd.Series([1, 2, 3], index=lst)
             >>> ser
@@ -1074,6 +1074,67 @@ def size(self):
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
+    def __iter__(self):
+        """
+        Groupby iterator.
+
+        This method provides an iterator over the groups created by the ``resample``
+        or ``groupby`` operation on the object. The method yields tuples where
+        the first element is the label (group key) corresponding to each group or
+        resampled bin, and the second element is the subset of the data that falls
+        within that group or bin.
+
+        **Examples:**
+
+            >>> import bigframes.pandas as bpd
+            >>> bpd.options.display.progress_bar = None
+
+        For SeriesGroupBy:
+
+            >>> lst = ["a", "a", "b"]
+            >>> ser = bpd.Series([1, 2, 3], index=lst)
+            >>> ser
+            a    1
+            a    2
+            b    3
+            dtype: Int64
+            >>> for x, y in ser.groupby(level=0):
+            ...     print(f"{x}\\n{y}\\n")
+            a
+            a    1
+            a    2
+            dtype: Int64
+            b
+            b    3
+            dtype: Int64
+
+        For DataFrameGroupBy:
+
+            >>> data = [[1, 2, 3], [1, 5, 6], [7, 8, 9]]
+            >>> df = bpd.DataFrame(data, columns=["a", "b", "c"])
+            >>> df
+               a  b  c
+            0  1  2  3
+            1  1  5  6
+            2  7  8  9
+            >>> for x, y in df.groupby(by=["a"]):
+            ...     print(f"{x}\\n{y}\\n")
+            (1,)
+               a  b  c
+            0  1  2  3
+            1  1  5  6
+            (7,)
+               a  b  c
+            2  7  8  9
+
+
+        Returns:
+            Iterator of tuples:
+                Generator yielding a sequence of (``name``, downloaded
+                ``pandas.DataFrame`` or ``pandas.Series``) for each group.
+        """
+        raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
+
 
 class SeriesGroupBy(GroupBy):
     def agg(self, func):