Merge branch 'main' into shuowei-anywidget-index-testcase

Author: shuoweil

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/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"]

bigframes/core/reshape/pivot.py

@@ -0,0 +1,89 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from __future__ import annotations
+
+from typing import Optional, TYPE_CHECKING
+
+import bigframes_vendored.pandas.core.reshape.pivot as vendored_pandas_pivot
+import pandas as pd
+
+import bigframes
+from bigframes.core import convert, utils
+from bigframes.core.reshape import concat
+from bigframes.dataframe import DataFrame
+
+if TYPE_CHECKING:
+    import bigframes.session
+
+
+def crosstab(
+    index,
+    columns,
+    values=None,
+    rownames=None,
+    colnames=None,
+    aggfunc=None,
+    *,
+    session: Optional[bigframes.session.Session] = None,
+) -> DataFrame:
+    if _is_list_of_lists(index):
+        index = [
+            convert.to_bf_series(subindex, default_index=None, session=session)
+            for subindex in index
+        ]
+    else:
+        index = [convert.to_bf_series(index, default_index=None, session=session)]
+    if _is_list_of_lists(columns):
+        columns = [
+            convert.to_bf_series(subcol, default_index=None, session=session)
+            for subcol in columns
+        ]
+    else:
+        columns = [convert.to_bf_series(columns, default_index=None, session=session)]
+
+    df = concat.concat([*index, *columns], join="inner", axis=1)
+    # for uniqueness
+    tmp_index_names = [f"_crosstab_index_{i}" for i in range(len(index))]
+    tmp_col_names = [f"_crosstab_columns_{i}" for i in range(len(columns))]
+    df.columns = pd.Index([*tmp_index_names, *tmp_col_names])
+
+    values = (
+        convert.to_bf_series(values, default_index=df.index, session=session)
+        if values is not None
+        else 0
+    )
+
+    df["_crosstab_values"] = values
+    pivot_table = df.pivot_table(
+        values="_crosstab_values",
+        index=tmp_index_names,
+        columns=tmp_col_names,
+        aggfunc=aggfunc or "count",
+        sort=False,
+    )
+    pivot_table.index.names = rownames or [i.name for i in index]
+    pivot_table.columns.names = colnames or [c.name for c in columns]
+    if aggfunc is None:
+        # TODO: Push this into pivot_table itself
+        pivot_table = pivot_table.fillna(0)
+    return pivot_table
+
+
+def _is_list_of_lists(item) -> bool:
+    if not utils.is_list_like(item):
+        return False
+    return all(convert.can_convert_to_series(subitem) for subitem in item)
+
+
+crosstab.__doc__ = vendored_pandas_pivot.crosstab.__doc__

bigframes/dataframe.py

@@ -3479,7 +3479,34 @@ def pivot_table(
         ] = None,
         columns: typing.Union[blocks.Label, Sequence[blocks.Label]] = None,
         aggfunc: str = "mean",
+        fill_value=None,
+        margins: bool = False,
+        dropna: bool = True,
+        margins_name: Hashable = "All",
+        observed: bool = False,
+        sort: bool = True,
     ) -> DataFrame:
+        if fill_value is not None:
+            raise NotImplementedError(
+                "DataFrame.pivot_table fill_value arg not supported. {constants.FEEDBACK_LINK}"
+            )
+        if margins:
+            raise NotImplementedError(
+                "DataFrame.pivot_table margins arg not supported. {constants.FEEDBACK_LINK}"
+            )
+        if not dropna:
+            raise NotImplementedError(
+                "DataFrame.pivot_table dropna arg not supported. {constants.FEEDBACK_LINK}"
+            )
+        if margins_name != "All":
+            raise NotImplementedError(
+                "DataFrame.pivot_table margins_name arg not supported. {constants.FEEDBACK_LINK}"
+            )
+        if observed:
+            raise NotImplementedError(
+                "DataFrame.pivot_table observed arg not supported. {constants.FEEDBACK_LINK}"
+            )
+
         if isinstance(index, Iterable) and not (
             isinstance(index, blocks.Label) and index in self.columns
         ):
@@ -3521,7 +3548,9 @@ def pivot_table(
             columns=columns,
             index=index,
             values=values if len(values) > 1 else None,
-        ).sort_index()
+        )
+        if sort:
+            pivoted = pivoted.sort_index()
 
         # TODO: Remove the reordering step once the issue is resolved.
         # The pivot_table method results in multi-index columns that are always ordered.

bigframes/pandas/__init__.py

@@ -31,7 +31,7 @@
 import bigframes.core.blocks
 import bigframes.core.global_session as global_session
 import bigframes.core.indexes
-from bigframes.core.reshape.api import concat, cut, get_dummies, merge, qcut
+from bigframes.core.reshape.api import concat, crosstab, cut, get_dummies, merge, qcut
 import bigframes.core.tools
 import bigframes.dataframe
 import bigframes.enums
@@ -372,6 +372,7 @@ def reset_session():
 _functions = [
     clean_up_by_session_id,
     concat,
+    crosstab,
     cut,
     deploy_remote_function,
     deploy_udf,

bigframes/session/__init__.py

@@ -2312,6 +2312,21 @@ def cut(self, *args, **kwargs) -> bigframes.series.Series:
             **kwargs,
         )
 
+    def crosstab(self, *args, **kwargs) -> dataframe.DataFrame:
+        """Compute a simple cross tabulation of two (or more) factors.
+
+        Included for compatibility between bpd and Session.
+
+        See :func:`bigframes.pandas.crosstab` for full documentation.
+        """
+        import bigframes.core.reshape.pivot
+
+        return bigframes.core.reshape.pivot.crosstab(
+            *args,
+            session=self,
+            **kwargs,
+        )
+
     def DataFrame(self, *args, **kwargs):
         """Constructs a DataFrame.
 

bigframes/version.py

@@ -12,8 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "2.28.0"
+__version__ = "2.29.0"
 
 # {x-release-please-start-date}
-__release_date__ = "2025-11-03"
+__release_date__ = "2025-11-10"
 # {x-release-please-end}

tests/system/small/test_pandas.py

@@ -450,6 +450,72 @@ def test_merge_raises_error_when_left_right_on_set(scalars_dfs):
         )
 
 
+def test_crosstab_aligned_series(scalars_dfs):
+    scalars_df, scalars_pandas_df = scalars_dfs
+
+    pd_result = pd.crosstab(
+        scalars_pandas_df["int64_col"], scalars_pandas_df["int64_too"]
+    )
+    bf_result = bpd.crosstab(
+        scalars_df["int64_col"], scalars_df["int64_too"]
+    ).to_pandas()
+
+    assert_pandas_df_equal(bf_result, pd_result, check_dtype=False)
+
+
+def test_crosstab_nondefault_func(scalars_dfs):
+    scalars_df, scalars_pandas_df = scalars_dfs
+
+    pd_result = pd.crosstab(
+        scalars_pandas_df["int64_col"],
+        scalars_pandas_df["int64_too"],
+        values=scalars_pandas_df["float64_col"],
+        aggfunc="mean",
+    )
+    bf_result = bpd.crosstab(
+        scalars_df["int64_col"],
+        scalars_df["int64_too"],
+        values=scalars_df["float64_col"],
+        aggfunc="mean",
+    ).to_pandas()
+
+    assert_pandas_df_equal(bf_result, pd_result, check_dtype=False)
+
+
+def test_crosstab_multi_cols(scalars_dfs):
+    scalars_df, scalars_pandas_df = scalars_dfs
+
+    pd_result = pd.crosstab(
+        [scalars_pandas_df["int64_col"], scalars_pandas_df["bool_col"]],
+        [scalars_pandas_df["int64_too"], scalars_pandas_df["string_col"]],
+        rownames=["a", "b"],
+        colnames=["c", "d"],
+    )
+    bf_result = bpd.crosstab(
+        [scalars_df["int64_col"], scalars_df["bool_col"]],
+        [scalars_df["int64_too"], scalars_df["string_col"]],
+        rownames=["a", "b"],
+        colnames=["c", "d"],
+    ).to_pandas()
+
+    assert_pandas_df_equal(bf_result, pd_result, check_dtype=False)
+
+
+def test_crosstab_unaligned_series(scalars_dfs, session):
+    scalars_df, scalars_pandas_df = scalars_dfs
+    other_pd_series = pd.Series(
+        [10, 20, 10, 30, 10], index=[5, 4, 1, 2, 3], dtype="Int64", name="nums"
+    )
+    other_bf_series = session.Series(
+        [10, 20, 10, 30, 10], index=[5, 4, 1, 2, 3], name="nums"
+    )
+
+    pd_result = pd.crosstab(scalars_pandas_df["int64_col"], other_pd_series)
+    bf_result = bpd.crosstab(scalars_df["int64_col"], other_bf_series).to_pandas()
+
+    assert_pandas_df_equal(bf_result, pd_result, check_dtype=False)
+
+
 def _convert_pandas_category(pd_s: pd.Series):
     """
     Transforms a pandas Series with Categorical dtype into a bigframes-compatible

third_party/bigframes_vendored/pandas/core/reshape/pivot.py

@@ -0,0 +1,57 @@
+# Contains code from https://github.com/pandas-dev/pandas/blob/main/pandas/core/reshape/pivot.py
+from __future__ import annotations
+
+from bigframes import constants
+
+
+def crosstab(
+    index,
+    columns,
+    values=None,
+    rownames=None,
+    colnames=None,
+    aggfunc=None,
+):
+    """
+    Compute a simple cross tabulation of two (or more) factors.
+
+    By default, computes a frequency table of the factors unless an
+    array of values and an aggregation function are passed.
+
+    **Examples:**
+        >>> a = np.array(["foo", "foo", "foo", "foo", "bar", "bar",
+        ...               "bar", "bar", "foo", "foo", "foo"], dtype=object)
+        >>> b = np.array(["one", "one", "one", "two", "one", "one",
+        ...               "one", "two", "two", "two", "one"], dtype=object)
+        >>> c = np.array(["dull", "dull", "shiny", "dull", "dull", "shiny",
+        ...               "shiny", "dull", "shiny", "shiny", "shiny"],
+        ...              dtype=object)
+        >>> bpd.crosstab(a, [b, c], rownames=['a'], colnames=['b', 'c'])
+        b    one        two
+        c   dull shiny dull shiny
+        a
+        bar    1     2    1     0
+        foo    2     2    1     2
+        <BLANKLINE>
+        [2 rows x 4 columns]
+
+    Args:
+        index (array-like, Series, or list of arrays/Series):
+            Values to group by in the rows.
+        columns (array-like, Series, or list of arrays/Series):
+            Values to group by in the columns.
+        values (array-like, optional):
+            Array of values to aggregate according to the factors.
+            Requires `aggfunc` be specified.
+        rownames (sequence, default None):
+            If passed, must match number of row arrays passed.
+        colnames (sequence, default None):
+            If passed, must match number of column arrays passed.
+        aggfunc (function, optional):
+            If specified, requires `values` be specified as well.
+
+    Returns:
+        DataFrame:
+            Cross tabulation of the data.
+    """
+    raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)

third_party/bigframes_vendored/version.py

@@ -12,8 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "2.28.0"
+__version__ = "2.29.0"
 
 # {x-release-please-start-date}
-__release_date__ = "2025-11-03"
+__release_date__ = "2025-11-10"
 # {x-release-please-end}