Merge branch 'main' into add-py-314

Author: Linchin

.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

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/core/block_transforms.py

@@ -624,21 +624,7 @@ 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
@@ -662,16 +648,7 @@ 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
@@ -685,13 +662,38 @@ 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

bigframes/core/compile/sqlglot/aggregate_compiler.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 from __future__ import annotations
 
-import sqlglot.expressions as sge
+import bigframes_vendored.sqlglot.expressions as sge
 
 from bigframes.core import agg_expressions, window_spec
 from bigframes.core.compile.sqlglot.aggregations import (

bigframes/core/compile/sqlglot/aggregations/binary_compiler.py

@@ -16,7 +16,7 @@
 
 import typing
 
-import sqlglot.expressions as sge
+import bigframes_vendored.sqlglot.expressions as sge
 
 from bigframes.core import window_spec
 import bigframes.core.compile.sqlglot.aggregations.op_registration as reg

bigframes/core/compile/sqlglot/aggregations/nullary_compiler.py

@@ -16,7 +16,7 @@
 
 import typing
 
-import sqlglot.expressions as sge
+import bigframes_vendored.sqlglot.expressions as sge
 
 from bigframes.core import window_spec
 import bigframes.core.compile.sqlglot.aggregations.op_registration as reg

bigframes/core/compile/sqlglot/aggregations/op_registration.py

@@ -16,7 +16,7 @@
 
 import typing
 
-from sqlglot import expressions as sge
+from bigframes_vendored.sqlglot import expressions as sge
 
 from bigframes.operations import aggregations as agg_ops
 

bigframes/core/compile/sqlglot/aggregations/ordered_unary_compiler.py

@@ -14,7 +14,7 @@
 
 from __future__ import annotations
 
-import sqlglot.expressions as sge
+import bigframes_vendored.sqlglot.expressions as sge
 
 import bigframes.core.compile.sqlglot.aggregations.op_registration as reg
 import bigframes.core.compile.sqlglot.expressions.typed_expr as typed_expr