Merge remote-tracking branch 'github/main' into selection_defer_plus

Author: TrevorBergeron

.github/workflows/docs.yml

@@ -2,6 +2,9 @@ on:
   pull_request:
     branches:
       - main
+  push:
+    branches:
+      - main
 name: docs
 jobs:
   docs:

.github/workflows/lint.yml

@@ -2,6 +2,9 @@ on:
   pull_request:
     branches:
       - main
+  push:
+    branches:
+      - main
 name: lint
 jobs:
   lint:

.github/workflows/mypy.yml

@@ -2,6 +2,9 @@ on:
   pull_request:
     branches:
       - main
+  push:
+    branches:
+      - main
 name: mypy
 jobs:
   mypy:

.github/workflows/unittest.yml

@@ -2,6 +2,9 @@ on:
   pull_request:
     branches:
       - main
+  push:
+    branches:
+      - main
 name: unittest
 jobs:
   unit:

CHANGELOG.md

@@ -4,6 +4,29 @@
 
 [1]: https://pypi.org/project/bigframes/#history
 
+## [2.29.0](https://github.com/googleapis/python-bigquery-dataframes/compare/v2.28.0...v2.29.0) (2025-11-10)
+
+
+### Features
+
+* Add bigframes.bigquery.st_regionstats to join raster data from Earth Engine ([#2228](https://github.com/googleapis/python-bigquery-dataframes/issues/2228)) ([10ec52f](https://github.com/googleapis/python-bigquery-dataframes/commit/10ec52f30a0a9c61b9eda9cf4f9bd6aa0cd95db5))
+* Add DataFrame.resample and Series.resample ([#2213](https://github.com/googleapis/python-bigquery-dataframes/issues/2213)) ([c9ca02c](https://github.com/googleapis/python-bigquery-dataframes/commit/c9ca02c5194c8b8e9b940eddd2224efd2ff0d5d9))
+* SQL Cell no longer escapes formatted string values ([#2245](https://github.com/googleapis/python-bigquery-dataframes/issues/2245)) ([d2d38f9](https://github.com/googleapis/python-bigquery-dataframes/commit/d2d38f94ed8333eae6f9cff3833177756eefe85a))
+* Support left_index and right_index for merge ([#2220](https://github.com/googleapis/python-bigquery-dataframes/issues/2220)) ([da9ba26](https://github.com/googleapis/python-bigquery-dataframes/commit/da9ba267812c01ffa6fa0b09943d7a4c63b8f187))
+
+
+### Bug Fixes
+
+* Correctly iterate over null struct values in ManagedArrowTable ([#2209](https://github.com/googleapis/python-bigquery-dataframes/issues/2209)) ([12e04d5](https://github.com/googleapis/python-bigquery-dataframes/commit/12e04d55f0d6aef1297b7ca773935aecf3313ee7))
+* Simplify UnsupportedTypeError message ([#2212](https://github.com/googleapis/python-bigquery-dataframes/issues/2212)) ([6c9a18d](https://github.com/googleapis/python-bigquery-dataframes/commit/6c9a18d7e67841c6fe6c1c6f34f80b950815141f))
+* Support results with STRUCT and ARRAY columns containing JSON subfields in `to_pandas_batches()` ([#2216](https://github.com/googleapis/python-bigquery-dataframes/issues/2216)) ([3d8b17f](https://github.com/googleapis/python-bigquery-dataframes/commit/3d8b17fa5eb9bbfc9e151031141a419f2dc3acb4))
+
+
+### Documentation
+
+* Switch API reference docs to pydata theme ([#2237](https://github.com/googleapis/python-bigquery-dataframes/issues/2237)) ([9b86dcf](https://github.com/googleapis/python-bigquery-dataframes/commit/9b86dcf87929648bf5ab565dfd46a23b639f01ac))
+* Update notebook for JSON subfields support in to_pandas_batches() ([#2138](https://github.com/googleapis/python-bigquery-dataframes/issues/2138)) ([5663d2a](https://github.com/googleapis/python-bigquery-dataframes/commit/5663d2a18064589596558af109e915f87d426eb0))
+
 ## [2.28.0](https://github.com/googleapis/python-bigquery-dataframes/compare/v2.27.0...v2.28.0) (2025-11-03)
 
 

bigframes/core/compile/sqlglot/expressions/geo_ops.py

@@ -21,6 +21,7 @@
 import bigframes.core.compile.sqlglot.scalar_compiler as scalar_compiler
 
 register_unary_op = scalar_compiler.scalar_op_compiler.register_unary_op
+register_binary_op = scalar_compiler.scalar_op_compiler.register_binary_op
 
 
 @register_unary_op(ops.geo_area_op)
@@ -108,3 +109,8 @@ def _(expr: TypedExpr) -> sge.Expression:
 @register_unary_op(ops.geo_y_op)
 def _(expr: TypedExpr) -> sge.Expression:
     return sge.func("SAFE.ST_Y", expr.expr)
+
+
+@register_binary_op(ops.geo_st_difference_op)
+def _(left: TypedExpr, right: TypedExpr) -> sge.Expression:
+    return sge.func("ST_DIFFERENCE", left.expr, right.expr)

bigframes/core/compile/sqlglot/expressions/numeric_ops.py

@@ -77,6 +77,13 @@ def _(expr: TypedExpr) -> sge.Expression:
     return sge.func("ASINH", expr.expr)
 
 
+@register_binary_op(ops.arctan2_op)
+def _(left: TypedExpr, right: TypedExpr) -> sge.Expression:
+    left_expr = _coerce_bool_to_int(left)
+    right_expr = _coerce_bool_to_int(right)
+    return sge.func("ATAN2", left_expr, right_expr)
+
+
 @register_unary_op(ops.arctan_op)
 def _(expr: TypedExpr) -> sge.Expression:
     return sge.func("ATAN", expr.expr)
@@ -118,6 +125,18 @@ def _(expr: TypedExpr) -> sge.Expression:
     )
 
 
+@register_binary_op(ops.cosine_distance_op)
+def _(left: TypedExpr, right: TypedExpr) -> sge.Expression:
+    return sge.Anonymous(
+        this="ML.DISTANCE",
+        expressions=[
+            left.expr,
+            right.expr,
+            sge.Literal.string("COSINE"),
+        ],
+    )
+
+
 @register_unary_op(ops.exp_op)
 def _(expr: TypedExpr) -> sge.Expression:
     return sge.Case(

bigframes/core/local_data.py

@@ -253,9 +253,16 @@ def _(
         value_generator = iter_array(
             array.flatten(), bigframes.dtypes.get_array_inner_type(dtype)
         )
-        for (start, end) in _pairwise(array.offsets):
-            arr_size = end.as_py() - start.as_py()
-            yield list(itertools.islice(value_generator, arr_size))
+        offset_generator = iter_array(array.offsets, bigframes.dtypes.INT_DTYPE)
+
+        start_offset = None
+        end_offset = None
+        for offset in offset_generator:
+            start_offset = end_offset
+            end_offset = offset
+            if start_offset is not None:
+                arr_size = end_offset - start_offset
+                yield list(itertools.islice(value_generator, arr_size))
 
     @iter_array.register
     def _(
@@ -267,8 +274,15 @@ def _(
             sub_generators[field_name] = iter_array(array.field(field_name), dtype)
 
         keys = list(sub_generators.keys())
-        for row_values in zip(*sub_generators.values()):
-            yield {key: value for key, value in zip(keys, row_values)}
+        is_null_generator = iter_array(array.is_null(), bigframes.dtypes.BOOL_DTYPE)
+
+        for values in zip(is_null_generator, *sub_generators.values()):
+            is_row_null = values[0]
+            row_values = values[1:]
+            if not is_row_null:
+                yield {key: value for key, value in zip(keys, row_values)}
+            else:
+                yield None
 
     for batch in table.to_batches():
         sub_generators: dict[str, Generator[Any, None, None]] = {}
@@ -491,16 +505,3 @@ def _schema_durations_to_ints(schema: pa.Schema) -> pa.Schema:
     return pa.schema(
         pa.field(field.name, _durations_to_ints(field.type)) for field in schema
     )
-
-
-def _pairwise(iterable):
-    do_yield = False
-    a = None
-    b = None
-    for item in iterable:
-        a = b
-        b = item
-        if do_yield:
-            yield (a, b)
-        else:
-            do_yield = True

bigframes/core/pyformat.py

@@ -104,6 +104,9 @@ def _field_to_template_value(
     if isinstance(value, bigframes.dataframe.DataFrame):
         return _table_to_sql(value._to_placeholder_table(dry_run=dry_run))
 
+    if isinstance(value, str):
+        return value
+
     return bigframes.core.sql.simple_literal(value)
 
 

bigframes/core/reshape/api.py

@@ -15,6 +15,7 @@
 from bigframes.core.reshape.concat import concat
 from bigframes.core.reshape.encoding import get_dummies
 from bigframes.core.reshape.merge import merge
+from bigframes.core.reshape.pivot import crosstab
 from bigframes.core.reshape.tile import cut, qcut
 
-__all__ = ["concat", "get_dummies", "merge", "cut", "qcut"]
+__all__ = ["concat", "get_dummies", "merge", "cut", "qcut", "crosstab"]