feat: Add IntervalIndex support to bigframes.pandas.cut (googleapis#254)

* feature: Add IntervalIndex support to bigframes.pandas.cut

* add bins <= 0 error in CutOp

* add type ignore

* add type ignore to session

---------

Co-authored-by: Shobhit Singh <[email protected]>

Author: Genesis929

bigframes/core/reshape/__init__.py

@@ -14,7 +14,9 @@
 from __future__ import annotations
 
 import typing
-from typing import Iterable, Literal, Optional, Union
+from typing import Iterable, Literal, Optional, Tuple, Union
+
+import pandas as pd
 
 import bigframes.constants as constants
 import bigframes.core as core
@@ -108,17 +110,29 @@ def concat(
 
 def cut(
     x: bigframes.series.Series,
-    bins: int,
+    bins: Union[
+        int,
+        pd.IntervalIndex,
+        Iterable[Tuple[Union[int, float], Union[int, float]]],
+    ],
     *,
     labels: Optional[bool] = None,
 ) -> bigframes.series.Series:
-    if bins <= 0:
+    if isinstance(bins, int) and bins <= 0:
         raise ValueError("`bins` should be a positive integer.")
 
+    if isinstance(bins, Iterable):
+        if not isinstance(bins, pd.IntervalIndex):
+            bins = pd.IntervalIndex.from_tuples(list(bins))
+
+        if bins.is_overlapping:
+            raise ValueError("Overlapping IntervalIndex is not accepted.")
+
     if labels is not False:
         raise NotImplementedError(
             f"Only labels=False is supported in BigQuery DataFrames so far. {constants.FEEDBACK_LINK}"
         )
+
     return x._apply_window_op(agg_ops.CutOp(bins), window_spec=core.WindowSpec())
 
 

bigframes/operations/aggregations.py

@@ -20,6 +20,7 @@
 import ibis.expr.datatypes as ibis_dtypes
 import ibis.expr.types as ibis_types
 from pandas import Int64Dtype
+import pandas as pd
 
 import bigframes.constants as constants
 import bigframes.dtypes as dtypes
@@ -228,21 +229,37 @@ def skips_nulls(self):
 
 
 class CutOp(WindowOp):
-    def __init__(self, bins: int):
-        self._bins_ibis = dtypes.literal_to_ibis_scalar(bins, force_dtype=Int64Dtype())
-        self._bins_int = bins
+    def __init__(self, bins: typing.Union[int, pd.IntervalIndex]):
+        if isinstance(bins, int):
+            if not bins > 0:
+                raise ValueError("`bins` should be a positive integer.")
+            self._bins_int = bins
+            self._bins = dtypes.literal_to_ibis_scalar(bins, force_dtype=Int64Dtype())
+        else:
+            self._bins_int = 0
+            self._bins = bins
 
     def _as_ibis(self, x: ibis_types.Column, window=None):
-        col_min = _apply_window_if_present(x.min(), window)
-        col_max = _apply_window_if_present(x.max(), window)
-        bin_width = (col_max - col_min) / self._bins_ibis
         out = ibis.case()
-        for this_bin in range(self._bins_int - 1):
-            out = out.when(
-                x <= (col_min + (this_bin + 1) * bin_width),
-                dtypes.literal_to_ibis_scalar(this_bin, force_dtype=Int64Dtype()),
-            )
-        out = out.when(x.notnull(), self._bins_ibis - 1)
+
+        if self._bins_int > 0:
+            col_min = _apply_window_if_present(x.min(), window)
+            col_max = _apply_window_if_present(x.max(), window)
+            bin_width = (col_max - col_min) / self._bins
+
+            for this_bin in range(self._bins_int - 1):
+                out = out.when(
+                    x <= (col_min + (this_bin + 1) * bin_width),
+                    dtypes.literal_to_ibis_scalar(this_bin, force_dtype=Int64Dtype()),
+                )
+            out = out.when(x.notnull(), self._bins - 1)
+        else:
+            for interval in self._bins:
+                condition = (x > interval.left) & (x <= interval.right)
+                interval_struct = ibis.struct(
+                    {"left_exclusive": interval.left, "right_inclusive": interval.right}
+                )
+                out = out.when(condition, interval_struct)
         return out.end()
 
     @property

bigframes/series.py

@@ -1324,7 +1324,7 @@ def to_csv(self, path_or_buf=None, **kwargs) -> typing.Optional[str]:
         return self.to_pandas().to_csv(path_or_buf, **kwargs)
 
     def to_dict(self, into: type[dict] = dict) -> typing.Mapping:
-        return typing.cast(dict, self.to_pandas().to_dict(into))
+        return typing.cast(dict, self.to_pandas().to_dict(into))  # type: ignore
 
     def to_excel(self, excel_writer, sheet_name="Sheet1", **kwargs) -> None:
         return self.to_pandas().to_excel(excel_writer, sheet_name, **kwargs)

bigframes/session/__init__.py

@@ -1017,13 +1017,13 @@ def read_csv(
                 header=header,
                 names=names,
                 index_col=index_col,
-                usecols=usecols,
+                usecols=usecols,  # type: ignore
                 dtype=dtype,
                 engine=engine,
                 encoding=encoding,
                 **kwargs,
             )
-            return self.read_pandas(pandas_df)
+            return self.read_pandas(pandas_df)  # type: ignore
 
     def read_pickle(
         self,

tests/system/small/test_pandas.py

@@ -365,6 +365,40 @@ def test_cut(scalars_dfs):
     pd.testing.assert_series_equal(bf_result, pd_result)
 
 
+@pytest.mark.parametrize(
+    ("bins",),
+    [
+        ([(-5, 2), (2, 3), (-3000, -10)],),
+        (pd.IntervalIndex.from_tuples([(1, 2), (2, 3), (4, 5)]),),
+    ],
+)
+def test_cut_with_interval(scalars_dfs, bins):
+    scalars_df, scalars_pandas_df = scalars_dfs
+    bf_result = bpd.cut(scalars_df["int64_too"], bins, labels=False).to_pandas()
+
+    if isinstance(bins, list):
+        bins = pd.IntervalIndex.from_tuples(bins)
+    pd_result = pd.cut(scalars_pandas_df["int64_too"], bins, labels=False)
+
+    # Convert to match data format
+    pd_result_converted = pd.Series(
+        [
+            {"left_exclusive": interval.left, "right_inclusive": interval.right}
+            if pd.notna(val)
+            else pd.NA
+            for val, interval in zip(
+                pd_result, pd_result.cat.categories[pd_result.cat.codes]
+            )
+        ],
+        name=pd_result.name,
+    )
+    pd_result.index = pd_result.index.astype("Int64")
+
+    pd.testing.assert_series_equal(
+        bf_result, pd_result_converted, check_index=False, check_dtype=False
+    )
+
+
 @pytest.mark.parametrize(
     ("q",),
     [

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

@@ -24,31 +24,61 @@ def cut(
 
     ``labels=False`` implies you just want the bins back.
 
-    Examples:
-
-    .. code-block::
-
-        import bigframes.pandas as pd
+    **Examples:**
+
+        >>> import bigframes.pandas as bpd
+        >>> bpd.options.display.progress_bar = None
+        >>> s = bpd.Series([0, 1, 5, 10])
+        >>> s
+        0     0
+        1     1
+        2     5
+        3    10
+        dtype: Int64
 
-        pd.options.display.progress_bar = None
-        s = pd.Series([0, 1, 1, 2])
-        pd.cut(s, bins=4, labels=False)
+    Cut with an integer (equal-width bins):
 
+        >>> bpd.cut(s, bins=4, labels=False)
         0    0
-        1    1
+        1    0
         2    1
         3    3
         dtype: Int64
 
+    Cut with pd.IntervalIndex, requires importing pandas for IntervalIndex:
+
+        >>> import pandas as pd
+
+        >>> interval_index = pd.IntervalIndex.from_tuples([(0, 1), (1, 5), (5, 20)])
+        >>> bpd.cut(s, bins=interval_index, labels=False)
+        0                                            <NA>
+        1     {'left_exclusive': 0, 'right_inclusive': 1}
+        2     {'left_exclusive': 1, 'right_inclusive': 5}
+        3    {'left_exclusive': 5, 'right_inclusive': 20}
+        dtype: struct<left_exclusive: int64, right_inclusive: int64>[pyarrow]
+
+    Cut with an iterable of tuples:
+
+        >>> bins_tuples = [(0, 1), (1, 4), (5, 20)]
+        >>> bpd.cut(s, bins=bins_tuples, labels=False)
+        0                                            <NA>
+        1     {'left_exclusive': 0, 'right_inclusive': 1}
+        2                                            <NA>
+        3    {'left_exclusive': 5, 'right_inclusive': 20}
+        dtype: struct<left_exclusive: int64, right_inclusive: int64>[pyarrow]
+
     Args:
         x (Series):
             The input Series to be binned. Must be 1-dimensional.
-        bins (int):
+        bins (int, pd.IntervalIndex, Iterable[Tuple[Union[int, float], Union[int, float]]]):
             The criteria to bin by.
 
-            int : Defines the number of equal-width bins in the range of `x`. The
+            int: Defines the number of equal-width bins in the range of `x`. The
             range of `x` is extended by .1% on each side to include the minimum
             and maximum values of `x`.
+
+            pd.IntervalIndex or Iterable of tuples: Defines the exact bins to be used.
+            It's important to ensure that these bins are non-overlapping.
         labels (None):
             Specifies the labels for the returned bins. Must be the same length as
             the resulting bins. If False, returns only integer indicators of the