add docs and fix tests

Author: chelsea-lin

tests/system/small/test_series.py

@@ -3418,55 +3418,50 @@ def foo(x: int, y: int, df):
     assert_series_equal(bf_result, pd_result)
 
 
-def test_series_explode_int():
+@pytest.mark.parametrize(
+    ("data"),
+    [
+        pytest.param([[1, 2, 3], [], numpy.nan, [3, 4]], id="int"),
+        pytest.param(
+            [["A", "AA", "AAA"], ["BB", "B"], numpy.nan, [], ["C"]], id="string"
+        ),
+        pytest.param(
+            [
+                {"A": {"x": 1.0}, "B": "b"},
+                {"A": {"y": 2.0}, "B": "bb"},
+                {"A": {"z": 4.0}},
+                {},
+                numpy.nan,
+            ],
+            id="struct",
+        ),
+    ],
+)
+def test_series_explode(data):
     data = [[1, 2, 3], [], numpy.nan, [3, 4]]
     s = bigframes.pandas.Series(data)
     pd_s = pd.Series(data)
     pd.testing.assert_series_equal(
         s.explode().to_pandas(),
-        pd_s.explode().astype(pd.Int64Dtype()),
-        check_index_type=False,
-    )
-
-
-def test_series_explode_string():
-    array = [["A", "AA", "AAA"], ["BB", "B"], numpy.nan, [], ["C"]]
-    s = bigframes.pandas.Series(array)
-    pd_s = pd.Series(array, dtype=pd.ArrowDtype(pa.list_(pa.string())))
-    pd.testing.assert_series_equal(
-        s.explode().to_pandas(),
-        pd_s.explode().astype(pd.StringDtype(storage="pyarrow")),
-        check_index_type=False,
-    )
-
-
-def test_series_explode_struct():
-    array = [
-        {"A": {"x": 1.0}, "B": "b"},
-        {"A": {"y": 2.0}, "B": "bb"},
-        {"A": {"z": 4.0}},
-        {},
-        numpy.nan,
-    ]
-    s = bigframes.pandas.Series(array)
-    pd_s = s.to_pandas()
-    pd.testing.assert_series_equal(
-        s.explode().to_pandas(),
-        pd_s.explode(),
+        pd_s.explode().astype(),
         check_index_type=False,
+        check_dtype=False,
     )
 
 
 @pytest.mark.parametrize(
-    ("ignore_index"),
+    ("index", "ignore_index"),
     [
-        pytest.param(True, id="include_index"),
-        pytest.param(False, id="ignore_index"),
+        pytest.param(None, True, id="default_index"),
+        pytest.param(None, False, id="ignore_default_index"),
+        pytest.param([5, 1, 3, 2], True, id="unordered_index"),
+        pytest.param([5, 1, 3, 2], False, id="ignore_unordered_index"),
+        pytest.param(["z", "x", "a", "b"], True, id="str_index"),
+        pytest.param(["z", "x", "a", "b"], False, id="ignore_str_index"),
     ],
 )
-def test_series_explode_w_unordered_index(ignore_index):
+def test_series_explode_w_index(index, ignore_index):
     data = [[], [200.0, 23.12], [4.5, -9.0], [1.0]]
-    index = [5, 1, 3, 2]
     s = bigframes.pandas.Series(data, index=index)
     pd_s = pd.Series(data, index=index)
     pd.testing.assert_series_equal(

third_party/bigframes_vendored/pandas/core/frame.py

@@ -2804,6 +2804,57 @@ def combine_first(self, other) -> DataFrame:
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
+    def explode(
+        self, column: Union[str, Sequence[str]], *, ignore_index: Optional[bool] = False
+    ) -> DataFrame:
+        """
+        Transform each element of a list-like to a row, replicating index values.
+
+        **Examples:**
+
+            >>> import bigframes.pandas as bpd
+            >>> bpd.options.display.progress_bar = None
+
+            >>> df = bpd.DataFrame({'A': [[0, 1, 2], [], [], [3, 4]],
+            ...                     'B': 1,
+            ...                     'C': [['a', 'b', 'c'], np.nan, [], ['d', 'e']]})
+            >>> df.explode('A')
+                A  B              C
+            0     0  1  ['a' 'b' 'c']
+            0     1  1  ['a' 'b' 'c']
+            0     2  1  ['a' 'b' 'c']
+            1  <NA>  1             []
+            2  <NA>  1             []
+            3     3  1      ['d' 'e']
+            3     4  1      ['d' 'e']
+            <BLANKLINE>
+            [7 rows x 3 columns]
+            >>> df.explode(list('AC'))
+                A  B     C
+            0     0  1     a
+            0     1  1     b
+            0     2  1     c
+            1  <NA>  1  <NA>
+            2  <NA>  1  <NA>
+            3     3  1     d
+            3     4  1     e
+            <BLANKLINE>
+            [7 rows x 3 columns]
+
+        Args:
+            column (str, Sequence[str]):
+                Column(s) to explode. For multiple columns, specify a non-empty list
+                with each element be str or tuple, and all specified columns their
+                list-like data on same row of the frame must have matching length.
+            ignore_index (bool, default False):
+                If True, the resulting index will be labeled 0, 1, …, n - 1.
+
+        Returns:
+            bigframes.series.DataFrame: Exploded lists to rows of the subset columns;
+                index will be duplicated for these rows.
+        """
+        raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
+
     def corr(self, method, min_periods, numeric_only) -> DataFrame:
         """
         Compute pairwise correlation of columns, excluding NA/null values.

third_party/bigframes_vendored/pandas/core/series.py

@@ -3,7 +3,7 @@
 """
 from __future__ import annotations
 
-from typing import Hashable, IO, Literal, Mapping, Sequence, TYPE_CHECKING
+from typing import Hashable, IO, Literal, Mapping, Optional, Sequence, TYPE_CHECKING
 
 from bigframes_vendored.pandas.core.generic import NDFrame
 import numpy as np
@@ -751,6 +751,34 @@ def round(self, decimals: int = 0) -> Series:
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
+    def explode(self, *, ignore_index: Optional[bool] = False) -> Series:
+        """
+        Transform each element of a list-like to a row.
+
+        **Examples:**
+
+            >>> import bigframes.pandas as bpd
+            >>> bpd.options.display.progress_bar = None
+
+            >>> s = bpd.Series([[1, 2, 3], [], [3, 4]])
+            >>> s.explode()
+            0       1
+            0       2
+            0       3
+            1    <NA>
+            2       3
+            2       4
+            dtype: Int64
+
+        Args:
+            ignore_index (bool, default False):
+                If True, the resulting index will be labeled 0, 1, …, n - 1.
+
+        Returns:
+            bigframes.series.Series: Exploded lists to rows; index will be duplicated for these rows.
+        """
+        raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
+
     def corr(self, other, method="pearson", min_periods=None) -> float:
         """
         Compute the correlation with the other Series.  Non-number values are ignored in the