feat: add GeoSeries.difference() and bigframes.bigquery.st_difference() (#1471)

* feat: add GeoSeries.difference()

* add st_difference method and test cases for geo.difference and st_difference

* update method and tests

* update method and tests

* update test to cover different inputs

* update test assertion

* update testing with single geometry object and add notebook tag to ignore the exception

* fix docstrings

* modify geo_difference to make it available for use and update tests and notebook

* fix my py type error

Author: arwas11

bigframes/bigquery/__init__.py

@@ -27,7 +27,7 @@
     unix_millis,
     unix_seconds,
 )
-from bigframes.bigquery._operations.geo import st_area
+from bigframes.bigquery._operations.geo import st_area, st_difference
 from bigframes.bigquery._operations.json import (
     json_extract,
     json_extract_array,
@@ -48,6 +48,7 @@
     "array_to_string",
     # geo ops
     "st_area",
+    "st_difference",
     # json ops
     "json_set",
     "json_extract",

bigframes/bigquery/_operations/geo.py

@@ -15,6 +15,7 @@
 from __future__ import annotations
 
 from bigframes import operations as ops
+import bigframes.dtypes
 import bigframes.geopandas
 import bigframes.series
 
@@ -91,3 +92,122 @@ def st_area(series: bigframes.series.Series) -> bigframes.series.Series:
     series = series._apply_unary_op(ops.geo_area_op)
     series.name = None
     return series
+
+
+def st_difference(
+    series: bigframes.series.Series, other: bigframes.series.Series
+) -> bigframes.series.Series:
+    """
+    Returns a GEOGRAPHY that represents the point set difference of
+    `geography_1` and `geography_2`. Therefore, the result consists of the part
+    of `geography_1` that doesn't intersect with `geography_2`.
+
+    If `geometry_1` is completely contained in `geometry_2`, then ST_DIFFERENCE
+    returns an empty GEOGRAPHY.
+
+    ..note::
+        BigQuery's Geography functions, like `st_difference`, interpret the geometry
+        data type as a point set on the Earth's surface. A point set is a set
+        of points, lines, and polygons on the WGS84 reference spheroid, with
+        geodesic edges. See: https://cloud.google.com/bigquery/docs/geospatial-data
+
+    **Examples:**
+
+        >>> import bigframes as bpd
+        >>> import bigframes.bigquery as bbq
+        >>> import bigframes.geopandas
+        >>> from shapely.geometry import Polygon, LineString, Point
+        >>> bpd.options.display.progress_bar = None
+
+    We can check two GeoSeries against each other, row by row.
+
+        >>> s1 = bigframes.geopandas.GeoSeries(
+        ...    [
+        ...        Polygon([(0, 0), (2, 2), (0, 2)]),
+        ...        Polygon([(0, 0), (2, 2), (0, 2)]),
+        ...        LineString([(0, 0), (2, 2)]),
+        ...        LineString([(2, 0), (0, 2)]),
+        ...        Point(0, 1),
+        ...    ],
+        ... )
+        >>> s2 = bigframes.geopandas.GeoSeries(
+        ...    [
+        ...        Polygon([(0, 0), (1, 1), (0, 1)]),
+        ...        LineString([(1, 0), (1, 3)]),
+        ...        LineString([(2, 0), (0, 2)]),
+        ...        Point(1, 1),
+        ...        Point(0, 1),
+        ...    ],
+        ...    index=range(1, 6),
+        ... )
+
+        >>> s1
+        0    POLYGON ((0 0, 2 2, 0 2, 0 0))
+        1    POLYGON ((0 0, 2 2, 0 2, 0 0))
+        2             LINESTRING (0 0, 2 2)
+        3             LINESTRING (2 0, 0 2)
+        4                       POINT (0 1)
+        dtype: geometry
+
+        >>> s2
+        1    POLYGON ((0 0, 1 1, 0 1, 0 0))
+        2             LINESTRING (1 0, 1 3)
+        3             LINESTRING (2 0, 0 2)
+        4                       POINT (1 1)
+        5                       POINT (0 1)
+        dtype: geometry
+
+        >>> bbq.st_difference(s1, s2)
+        0                                               None
+        1    POLYGON ((0.99954 1, 2 2, 0 2, 0 1, 0.99954 1))
+        2                   LINESTRING (0 0, 1 1.00046, 2 2)
+        3                           GEOMETRYCOLLECTION EMPTY
+        4                                        POINT (0 1)
+        5                                               None
+        dtype: geometry
+
+    We can also check difference of single shapely geometries:
+
+        >>> sbq1 = bigframes.geopandas.GeoSeries(
+        ...     [
+        ...         Polygon([(0, 0), (10, 0), (10, 10), (0, 0)])
+        ...     ]
+        ... )
+        >>> sbq2 = bigframes.geopandas.GeoSeries(
+        ...     [
+        ...         Polygon([(4, 2), (6, 2), (8, 6), (4, 2)])
+        ...     ]
+        ... )
+
+        >>> sbq1
+        0    POLYGON ((0 0, 10 0, 10 10, 0 0))
+        dtype: geometry
+
+        >>> sbq2
+        0    POLYGON ((4 2, 6 2, 8 6, 4 2))
+        dtype: geometry
+
+        >>> bbq.st_difference(sbq1, sbq2)
+        0    POLYGON ((0 0, 10 0, 10 10, 0 0), (8 6, 6 2, 4...
+        dtype: geometry
+
+    Additionally, we can check difference of a GeoSeries against a single shapely geometry:
+
+        >>> bbq.st_difference(s1, sbq2)
+        0    POLYGON ((0 0, 2 2, 0 2, 0 0))
+        1                              None
+        2                              None
+        3                              None
+        4                              None
+        dtype: geometry
+
+    Args:
+        other (bigframes.series.Series or geometric object):
+            The GeoSeries (elementwise) or geometric object to find the difference to.
+
+    Returns:
+        bigframes.series.Series:
+            A GeoSeries of the points in each aligned geometry that are not
+            in other.
+    """
+    return series._apply_binary_op(other, ops.geo_st_difference_op)

bigframes/core/compile/scalar_op_compiler.py

@@ -1001,11 +1001,6 @@ def normalize_op_impl(x: ibis_types.Value):
 
 
 # Geo Ops
-@scalar_op_compiler.register_unary_op(ops.geo_st_boundary_op, pass_op=False)
-def geo_st_boundary_op_impl(x: ibis_types.Value):
-    return st_boundary(x)
-
-
 @scalar_op_compiler.register_unary_op(ops.geo_area_op)
 def geo_area_op_impl(x: ibis_types.Value):
     return typing.cast(ibis_types.GeoSpatialValue, x).area()
@@ -1016,6 +1011,18 @@ def geo_st_astext_op_impl(x: ibis_types.Value):
     return typing.cast(ibis_types.GeoSpatialValue, x).as_text()
 
 
+@scalar_op_compiler.register_unary_op(ops.geo_st_boundary_op, pass_op=False)
+def geo_st_boundary_op_impl(x: ibis_types.Value):
+    return st_boundary(x)
+
+
+@scalar_op_compiler.register_binary_op(ops.geo_st_difference_op, pass_op=False)
+def geo_st_difference_op_impl(x: ibis_types.Value, y: ibis_types.Value):
+    return typing.cast(ibis_types.GeoSpatialValue, x).difference(
+        typing.cast(ibis_types.GeoSpatialValue, y)
+    )
+
+
 @scalar_op_compiler.register_unary_op(ops.geo_st_geogfromtext_op)
 def geo_st_geogfromtext_op_impl(x: ibis_types.Value):
     # Ibis doesn't seem to provide a dedicated method to cast from string to geography,

bigframes/geopandas/geoseries.py

@@ -62,7 +62,7 @@ def area(self, crs=None) -> bigframes.series.Series:  # type: ignore
 
         Raises:
             NotImplementedError:
-                GeoSeries.area is not supported. Use bigframes.bigquery.st_area(series), insetead.
+                GeoSeries.area is not supported. Use bigframes.bigquery.st_area(series), instead.
         """
         raise NotImplementedError(
             f"GeoSeries.area is not supported. Use bigframes.bigquery.st_area(series), instead. {constants.FEEDBACK_LINK}"
@@ -93,3 +93,6 @@ def to_wkt(self: GeoSeries) -> bigframes.series.Series:
         series = self._apply_unary_op(ops.geo_st_astext_op)
         series.name = None
         return series
+
+    def difference(self: GeoSeries, other: GeoSeries) -> bigframes.series.Series:  # type: ignore
+        return self._apply_binary_op(other, ops.geo_st_difference_op)

bigframes/operations/__init__.py

@@ -90,6 +90,7 @@
     geo_area_op,
     geo_st_astext_op,
     geo_st_boundary_op,
+    geo_st_difference_op,
     geo_st_geogfromtext_op,
     geo_st_geogpoint_op,
     geo_x_op,
@@ -366,6 +367,7 @@
     # Geo ops
     "geo_area_op",
     "geo_st_boundary_op",
+    "geo_st_difference_op",
     "geo_st_astext_op",
     "geo_st_geogfromtext_op",
     "geo_st_geogpoint_op",

bigframes/operations/geo_ops.py

@@ -37,14 +37,17 @@
     ),
 )
 
+geo_st_difference_op = base_ops.create_binary_op(
+    name="geo_st_difference", type_signature=op_typing.BinaryGeo()
+)
+
 geo_st_geogfromtext_op = base_ops.create_unary_op(
     name="geo_st_geogfromtext",
     type_signature=op_typing.FixedOutputType(
         dtypes.is_string_like, dtypes.GEO_DTYPE, description="string-like"
     ),
 )
 
-
 geo_st_geogpoint_op = base_ops.create_binary_op(
     name="geo_st_geogpoint", type_signature=op_typing.BinaryNumericGeo()
 )

bigframes/operations/type.py

@@ -122,6 +122,20 @@ def output_type(
 
 
 @dataclasses.dataclass
+@dataclasses.dataclass
+class BinaryGeo(BinaryTypeSignature):
+    """Type signature for geo functions like difference that can map geo to geo."""
+
+    def output_type(
+        self, left_type: ExpressionType, right_type: ExpressionType
+    ) -> ExpressionType:
+        if (left_type is not None) and not bigframes.dtypes.is_geo_like(left_type):
+            raise TypeError(f"Type {left_type} is not geo")
+        if (right_type is not None) and not bigframes.dtypes.is_geo_like(right_type):
+            raise TypeError(f"Type {right_type} is not numeric")
+        return bigframes.dtypes.GEO_DTYPE
+
+
 class BinaryNumericGeo(BinaryTypeSignature):
     """Type signature for geo functions like from_xy that can map ints to ints."""