Merge branch 'main' into better_uniform_sample

Author: TrevorBergeron

.github/ISSUE_TEMPLATE/bug_report.md

@@ -29,14 +29,12 @@ import bigframes
 import google.cloud.bigquery
 import pandas
 import pyarrow
-import sqlglot
 
 print(f"Python: {sys.version}")
 print(f"bigframes=={bigframes.__version__}")
 print(f"google-cloud-bigquery=={google.cloud.bigquery.__version__}")
 print(f"pandas=={pandas.__version__}")
 print(f"pyarrow=={pyarrow.__version__}")
-print(f"sqlglot=={sqlglot.__version__}")
 ```
 
 #### Steps to reproduce

.librarian/state.yaml

@@ -1,7 +1,7 @@
 image: us-central1-docker.pkg.dev/cloud-sdk-librarian-prod/images-prod/python-librarian-generator@sha256:c8612d3fffb3f6a32353b2d1abd16b61e87811866f7ec9d65b59b02eb452a620
 libraries:
   - id: bigframes
-    version: 2.31.0
+    version: 2.32.0
     last_generated_commit: ""
     apis: []
     source_roots:

CHANGELOG.md

@@ -4,6 +4,34 @@
 
 [1]: https://pypi.org/project/bigframes/#history
 
+## [2.32.0](https://github.com/googleapis/google-cloud-python/compare/bigframes-v2.31.0...bigframes-v2.32.0) (2026-01-05)
+
+
+### Documentation
+
+* generate sitemap.xml for better search indexing (#2351) ([7d2990f1c48c6d74e2af6bee3af87f90189a3d9b](https://github.com/googleapis/google-cloud-python/commit/7d2990f1c48c6d74e2af6bee3af87f90189a3d9b))
+* update supported pandas APIs documentation links (#2330) ([ea71936ce240b2becf21b552d4e41e8ef4418e2d](https://github.com/googleapis/google-cloud-python/commit/ea71936ce240b2becf21b552d4e41e8ef4418e2d))
+* Add time series analysis notebook (#2328) ([369f1c0aff29d197b577ec79e401b107985fe969](https://github.com/googleapis/google-cloud-python/commit/369f1c0aff29d197b577ec79e401b107985fe969))
+
+
+### Features
+
+* Enable multi-column sorting in anywidget mode (#2360) ([1feb956e4762e30276e5b380c0633e6ed7881357](https://github.com/googleapis/google-cloud-python/commit/1feb956e4762e30276e5b380c0633e6ed7881357))
+* display series in anywidget mode (#2346) ([7395d418550058c516ad878e13567256f4300a37](https://github.com/googleapis/google-cloud-python/commit/7395d418550058c516ad878e13567256f4300a37))
+* Refactor TableWidget and to_pandas_batches (#2250) ([b8f09015a7c8e6987dc124e6df925d4f6951b1da](https://github.com/googleapis/google-cloud-python/commit/b8f09015a7c8e6987dc124e6df925d4f6951b1da))
+* Auto-plan complex reduction expressions (#2298) ([4d5de14ccdd05b1ac8f50c3fe71c35ab9e5150c1](https://github.com/googleapis/google-cloud-python/commit/4d5de14ccdd05b1ac8f50c3fe71c35ab9e5150c1))
+* Display custom single index column in anywidget mode (#2311) ([f27196260743883ed8131d5fd33a335e311177e4](https://github.com/googleapis/google-cloud-python/commit/f27196260743883ed8131d5fd33a335e311177e4))
+* add fit_predict method to ml unsupervised models (#2320) ([59df7f70a12ef702224ad61e597bd775208dac45](https://github.com/googleapis/google-cloud-python/commit/59df7f70a12ef702224ad61e597bd775208dac45))
+
+
+### Bug Fixes
+
+* vendor sqlglot bigquery dialect and remove package dependency (#2354) ([b321d72d5eb005b6e9295541a002540f05f72209](https://github.com/googleapis/google-cloud-python/commit/b321d72d5eb005b6e9295541a002540f05f72209))
+* bigframes.ml fit with eval data in partial mode avoids join on null index (#2355) ([7171d21b8c8d5a2d61081f41fa1109b5c9c4bc5f](https://github.com/googleapis/google-cloud-python/commit/7171d21b8c8d5a2d61081f41fa1109b5c9c4bc5f))
+* Improve strictness of nan vs None usage (#2326) ([481d938fb0b840e17047bc4b57e61af15b976e54](https://github.com/googleapis/google-cloud-python/commit/481d938fb0b840e17047bc4b57e61af15b976e54))
+* Correct DataFrame widget rendering in Colab (#2319) ([7f1d3df3839ec58f52e48df088057fc0df967da9](https://github.com/googleapis/google-cloud-python/commit/7f1d3df3839ec58f52e48df088057fc0df967da9))
+* Fix pd.timedelta handling in polars comipler with polars 1.36 (#2325) ([252644826289d9db7a8548884de880b3a4fccafd](https://github.com/googleapis/google-cloud-python/commit/252644826289d9db7a8548884de880b3a4fccafd))
+
 ## [2.31.0](https://github.com/googleapis/google-cloud-python/compare/bigframes-v2.30.0...bigframes-v2.31.0) (2025-12-10)
 
 

LICENSE

@@ -318,3 +318,29 @@ SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+---
+
+Files: The bigframes_vendored.sqlglot module.
+
+MIT License
+
+Copyright (c) 2025 Toby Mao
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.rst

@@ -82,6 +82,7 @@ It also contains code derived from the following third-party packages:
 * `Python <https://www.python.org/>`_
 * `scikit-learn <https://scikit-learn.org/>`_
 * `XGBoost <https://xgboost.readthedocs.io/en/stable/>`_
+* `SQLGlot <https://sqlglot.com/sqlglot.html>`_
 
 For details, see the `third_party
 <https://github.com/googleapis/python-bigquery-dataframes/tree/main/third_party/bigframes_vendored>`_

bigframes/bigquery/__init__.py

@@ -60,7 +60,7 @@
 from bigframes.bigquery._operations.search import create_vector_index, vector_search
 from bigframes.bigquery._operations.sql import sql_scalar
 from bigframes.bigquery._operations.struct import struct
-from bigframes.core import log_adapter
+from bigframes.core.logging import log_adapter
 
 _functions = [
     # approximate aggregate ops

bigframes/bigquery/_operations/ai.py

@@ -26,7 +26,8 @@
 from bigframes import clients, dataframe, dtypes
 from bigframes import pandas as bpd
 from bigframes import series, session
-from bigframes.core import convert, log_adapter
+from bigframes.core import convert
+from bigframes.core.logging import log_adapter
 from bigframes.ml import core as ml_core
 from bigframes.operations import ai_ops, output_schemas
 

bigframes/bigquery/_operations/ml.py

@@ -20,7 +20,7 @@
 import google.cloud.bigquery
 import pandas as pd
 
-import bigframes.core.log_adapter as log_adapter
+import bigframes.core.logging.log_adapter as log_adapter
 import bigframes.core.sql.ml
 import bigframes.dataframe as dataframe
 import bigframes.ml.base

bigframes/core/block_transforms.py

@@ -625,21 +625,7 @@ def skew(
     # counts, moment3 for each column
     aggregations = []
     for col in original_columns:
-        delta3_expr = _mean_delta_to_power(3, col)
-        count_agg = agg_expressions.UnaryAggregation(
-            agg_ops.count_op,
-            ex.deref(col),
-        )
-        moment3_agg = agg_expressions.UnaryAggregation(
-            agg_ops.mean_op,
-            delta3_expr,
-        )
-        variance_agg = agg_expressions.UnaryAggregation(
-            agg_ops.PopVarOp(),
-            ex.deref(col),
-        )
-        skew_expr = _skew_from_moments_and_count(count_agg, moment3_agg, variance_agg)
-        aggregations.append(skew_expr)
+        aggregations.append(skew_expr(ex.deref(col)))
 
     block = block.aggregate(
         aggregations, grouping_column_ids, column_labels=column_labels
@@ -663,16 +649,7 @@ def kurt(
     # counts, moment4 for each column
     kurt_exprs = []
     for col in original_columns:
-        delta_4_expr = _mean_delta_to_power(4, col)
-        count_agg = agg_expressions.UnaryAggregation(agg_ops.count_op, ex.deref(col))
-        moment4_agg = agg_expressions.UnaryAggregation(agg_ops.mean_op, delta_4_expr)
-        variance_agg = agg_expressions.UnaryAggregation(
-            agg_ops.PopVarOp(), ex.deref(col)
-        )
-
-        # Corresponds to order of aggregations in preceding loop
-        kurt_expr = _kurt_from_moments_and_count(count_agg, moment4_agg, variance_agg)
-        kurt_exprs.append(kurt_expr)
+        kurt_exprs.append(kurt_expr(ex.deref(col)))
 
     block = block.aggregate(
         kurt_exprs, grouping_column_ids, column_labels=column_labels
@@ -686,13 +663,38 @@ def kurt(
     return block
 
 
+def skew_expr(expr: ex.Expression) -> ex.Expression:
+    delta3_expr = _mean_delta_to_power(3, expr)
+    count_agg = agg_expressions.UnaryAggregation(
+        agg_ops.count_op,
+        expr,
+    )
+    moment3_agg = agg_expressions.UnaryAggregation(
+        agg_ops.mean_op,
+        delta3_expr,
+    )
+    variance_agg = agg_expressions.UnaryAggregation(
+        agg_ops.PopVarOp(),
+        expr,
+    )
+    return _skew_from_moments_and_count(count_agg, moment3_agg, variance_agg)
+
+
+def kurt_expr(expr: ex.Expression) -> ex.Expression:
+    delta_4_expr = _mean_delta_to_power(4, expr)
+    count_agg = agg_expressions.UnaryAggregation(agg_ops.count_op, expr)
+    moment4_agg = agg_expressions.UnaryAggregation(agg_ops.mean_op, delta_4_expr)
+    variance_agg = agg_expressions.UnaryAggregation(agg_ops.PopVarOp(), expr)
+    return _kurt_from_moments_and_count(count_agg, moment4_agg, variance_agg)
+
+
 def _mean_delta_to_power(
     n_power: int,
-    val_id: str,
+    col_expr: ex.Expression,
 ) -> ex.Expression:
     """Calculate (x-mean(x))^n. Useful for calculating moment statistics such as skew and kurtosis."""
-    mean_expr = agg_expressions.UnaryAggregation(agg_ops.mean_op, ex.deref(val_id))
-    delta = ops.sub_op.as_expr(val_id, mean_expr)
+    mean_expr = agg_expressions.UnaryAggregation(agg_ops.mean_op, col_expr)
+    delta = ops.sub_op.as_expr(col_expr, mean_expr)
     return ops.pow_op.as_expr(delta, ex.const(n_power))
 
 

bigframes/core/bq_data.py

@@ -64,6 +64,21 @@ def from_table(table: bq.Table, columns: Sequence[str] = ()) -> GbqTable:
             else tuple(table.clustering_fields),
         )
 
+    @staticmethod
+    def from_ref_and_schema(
+        table_ref: bq.TableReference,
+        schema: Sequence[bq.SchemaField],
+        cluster_cols: Optional[Sequence[str]] = None,
+    ) -> GbqTable:
+        return GbqTable(
+            project_id=table_ref.project,
+            dataset_id=table_ref.dataset_id,
+            table_id=table_ref.table_id,
+            physical_schema=tuple(schema),
+            is_physically_stored=True,
+            cluster_cols=tuple(cluster_cols) if cluster_cols else None,
+        )
+
     def get_table_ref(self) -> bq.TableReference:
         return bq.TableReference(
             bq.DatasetReference(self.project_id, self.dataset_id), self.table_id