Merge branch 'main' into main_chelsealin_notebooks

Author: chelsea-lin

CHANGELOG.md

@@ -4,6 +4,26 @@
 
 [1]: https://pypi.org/project/bigframes/#history
 
+## [1.13.0](https://github.com/googleapis/python-bigquery-dataframes/compare/v1.12.0...v1.13.0) (2024-08-05)
+
+
+### Features
+
+* `df.apply(axis=1)` to support remote function with mutiple params ([#851](https://github.com/googleapis/python-bigquery-dataframes/issues/851)) ([2158818](https://github.com/googleapis/python-bigquery-dataframes/commit/2158818e53e09e55c87ffd574e3ebc2e201285fb))
+* Allow windowing in 'partial' ordering mode ([#861](https://github.com/googleapis/python-bigquery-dataframes/issues/861)) ([ca26fe5](https://github.com/googleapis/python-bigquery-dataframes/commit/ca26fe5f9edec519788c276a09eaff33ecd87434))
+* Create a separate OrderingModePartialPreviewWarning for more fine-grained warning filters ([#879](https://github.com/googleapis/python-bigquery-dataframes/issues/879)) ([8753bdd](https://github.com/googleapis/python-bigquery-dataframes/commit/8753bdd1e44701e56eae914ebc0e91d9b1a6adf1))
+
+
+### Bug Fixes
+
+* Fix issue with invalid sql generated by ml distance functions ([#865](https://github.com/googleapis/python-bigquery-dataframes/issues/865)) ([9959fc8](https://github.com/googleapis/python-bigquery-dataframes/commit/9959fc8fcba93441fdd3d9c17e8fdbe6e6a7b504))
+
+
+### Documentation
+
+* Create sample notebook using `ordering_mode="partial"` ([#880](https://github.com/googleapis/python-bigquery-dataframes/issues/880)) ([c415eb9](https://github.com/googleapis/python-bigquery-dataframes/commit/c415eb91eb71dea53d245ba2bce416062e3f02f8))
+* Update streaming notebook ([#875](https://github.com/googleapis/python-bigquery-dataframes/issues/875)) ([e9b0557](https://github.com/googleapis/python-bigquery-dataframes/commit/e9b05571123cf13079772856317ca3cd3d564c5a))
+
 ## [1.12.0](https://github.com/googleapis/python-bigquery-dataframes/compare/v1.11.1...v1.12.0) (2024-07-31)
 
 

bigframes/series.py

@@ -641,7 +641,7 @@ def head(self, n: int = 5) -> Series:
  def tail(self, n: int = 5) -> Series:
  return typing.cast(Series, self.iloc[-n:])
 
- def peek(self, n: int = 5, *, force: bool = True) -> pandas.DataFrame:
+ def peek(self, n: int = 5, *, force: bool = True) -> pandas.Series:
  """
  Preview n arbitrary elements from the series without guarantees about row selection or ordering.
 

bigframes/session/__init__.py

@@ -1997,8 +1997,10 @@ def _cache_with_session_awareness(self, array_value: core.ArrayValue) -> None:
  )
  if len(cluster_cols) > 0:
  self._cache_with_cluster_cols(core.ArrayValue(target), cluster_cols)
- else:
+ elif self._strictly_ordered:
  self._cache_with_offsets(core.ArrayValue(target))
+ else:
+ self._cache_with_cluster_cols(core.ArrayValue(target), [])
 
  def _simplify_with_caching(self, array_value: core.ArrayValue):
  """Attempts to handle the complexity by caching duplicated subtrees and breaking the query into pieces."""

bigframes/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "1.12.0"
+__version__ = "1.13.0"

tests/system/small/test_unordered.py

@@ -19,7 +19,11 @@
 
 import bigframes.exceptions
 import bigframes.pandas as bpd
-from tests.system.utils import assert_pandas_df_equal, skip_legacy_pandas
+from tests.system.utils import (
+ assert_pandas_df_equal,
+ assert_series_equal,
+ skip_legacy_pandas,
+)
 
 
 def test_unordered_mode_sql_no_hash(unordered_session):
@@ -51,6 +55,15 @@ def test_unordered_mode_cache_aggregate(unordered_session):
  assert_pandas_df_equal(bf_result, pd_result, ignore_order=True)
 
 
+def test_unordered_mode_series_peek(unordered_session):
+ pd_series = pd.Series([1, 2, 3, 4, 5, 6], dtype=pd.Int64Dtype())
+ bf_series = bpd.Series(pd_series, session=unordered_session)
+ pd_result = pd_series.groupby(pd_series % 4).sum()
+ bf_peek = bf_series.groupby(bf_series % 4).sum().peek(2)
+
+ assert_series_equal(bf_peek, pd_result.reindex(bf_peek.index))
+
+
 def test_unordered_mode_single_aggregate(unordered_session):
  pd_df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]}, dtype=pd.Int64Dtype())
  bf_df = bpd.DataFrame(pd_df, session=unordered_session)