def DistanceJoinQueryFlat(cls, spatialRDD: SpatialRDD, queryRDD: SpatialRDD, useIndex: bool, considerBoundaryIntersection: bool) -> RDD:
"""
:param spatialRDD: SpatialRDD
:param queryRDD: SpatialRDD
:param useIndex: bool
:param considerBoundaryIntersection: bool
>> spatial_rdd =
>> query_rdd =
>> spatial_join_result = JoinQuery.DistanceJoinQueryFlat(spatial_rdd, query_rdd, True, True)
>> spatial_join_result.collect()
[GeoData(), GeoData()]
:return:
"""
jvm = spatialRDD._jvm
sc = spatialRDD._sc
spatial_join = jvm.JoinQuery.DistanceJoinQueryFlat
srdd = spatial_join(
spatialRDD._srdd,
queryRDD._srdd,
useIndex,
considerBoundaryIntersection
)
serialized = JvmSedonaPythonConverter(jvm).\
translate_spatial_pair_rdd_to_python(srdd)
return RDD(serialized, sc, SedonaPickler())
def SpatialKnnQuery(self, spatialRDD: SpatialRDD,
originalQueryPoint: BaseGeometry, k: int,
useIndex: bool):
"""
:param spatialRDD: spatialRDD
:param originalQueryPoint: shapely.geometry.Point
:param k: int
:param useIndex: bool
:return: pyspark.RDD
"""
jvm = spatialRDD._jvm
jvm_geom = GeometryAdapter.create_jvm_geometry_from_base_geometry(
jvm, originalQueryPoint)
knn_neighbours = jvm.KNNQuery.SpatialKnnQuery(spatialRDD._srdd,
jvm_geom, k, useIndex)
srdd = JvmSedonaPythonConverter(jvm).translate_geometry_seq_to_python(
knn_neighbours)
geoms_data = []
for arr in srdd:
binary_parser = BinaryParser(arr)
geom = SpatialRDDParserData.deserialize(binary_parser)
geoms_data.append(geom)
return geoms_data
def SpatialRangeQuery(self, spatialRDD: SpatialRDD,
rangeQueryWindow: BaseGeometry,
considerBoundaryIntersection: bool,
usingIndex: bool):
"""
:param spatialRDD:
:param rangeQueryWindow:
:param considerBoundaryIntersection:
:param usingIndex:
:return:
"""
jvm = spatialRDD._jvm
sc = spatialRDD._sc
jvm_geom = GeometryAdapter.create_jvm_geometry_from_base_geometry(
jvm, rangeQueryWindow)
srdd = jvm.\
RangeQuery.SpatialRangeQuery(
spatialRDD._srdd,
jvm_geom,
considerBoundaryIntersection,
usingIndex
)
serialized = JvmSedonaPythonConverter(
jvm).translate_spatial_rdd_to_python(srdd)
return RDD(serialized, sc, SedonaPickler())
def rawSpatialRDD(self, spatial_rdd):
if isinstance(spatial_rdd, SpatialRDD):
self._srdd = spatial_rdd._srdd
self._sc = spatial_rdd._sc
self._jvm = spatial_rdd._jvm
self._spatial_partitioned = spatial_rdd._spatial_partitioned
elif isinstance(spatial_rdd, RDD):
jrdd = JvmSedonaPythonConverter(self._jvm).translate_python_rdd_to_java(spatial_rdd._jrdd)
self._srdd.setRawSpatialRDD(jrdd)
else:
self._srdd.setRawSpatialRDD(spatial_rdd)
def spatialJoin(cls, queryWindowRDD: SpatialRDD, objectRDD: SpatialRDD, joinParams: JoinParams) -> RDD:
"""
:param queryWindowRDD: SpatialRDD
:param objectRDD: SpatialRDD
:param joinParams: JoinParams
:return:
"""
jvm = queryWindowRDD._jvm
sc = queryWindowRDD._sc
jvm_join_params = joinParams.jvm_instance(jvm)
srdd = jvm.JoinQuery.spatialJoin(queryWindowRDD._srdd, objectRDD._srdd, jvm_join_params)
serialized = JvmSedonaPythonConverter(jvm).\
translate_spatial_pair_rdd_to_python(srdd)
return RDD(serialized, sc, SedonaPickler())
def DistanceJoinQuery(cls, spatialRDD: SpatialRDD, queryRDD: SpatialRDD, useIndex: bool, considerBoundaryIntersection: bool) -> RDD:
"""
:param spatialRDD: SpatialRDD
:param queryRDD: SpatialRDD
:param useIndex: bool
:param considerBoundaryIntersection: bool
:return:
"""
jvm = spatialRDD._jvm
sc = spatialRDD._sc
srdd = jvm.JoinQuery.DistanceJoinQuery(
spatialRDD._srdd,
queryRDD._srdd,
useIndex,
considerBoundaryIntersection
)
serialized = JvmSedonaPythonConverter(jvm).\
translate_spatial_pair_rdd_with_hashset_to_python(srdd)
return RDD(serialized, sc, SedonaPickler())
def SpatialJoinQueryFlat(cls, spatialRDD: SpatialRDD, queryRDD: SpatialRDD, useIndex: bool,
considerBoundaryIntersection: bool) -> RDD:
"""
Function takes SpatialRDD and other SpatialRDD and based on two parameters
- useIndex
- considerBoundaryIntersection
creates RDD with result of Spatial Join operation. It Returns RDD[GeoData, GeoData]
:param spatialRDD: SpatialRDD
:param queryRDD: SpatialRDD
:param useIndex: bool
:param considerBoundaryIntersection: bool
:return: RDD
>> spatial_join_result = JoinQuery.SpatialJoinQueryFlat(
>> spatialRDD, queryRDD, useIndex, considerBoundaryIntersection
>> )
>> spatial_join_result.collect()
[[GeoData(Polygon, ), GeoData()], [GeoData(), GeoData()], [GeoData(), GeoData()]]
"""
jvm = spatialRDD._jvm
sc = spatialRDD._sc
spatial_join = jvm.JoinQuery.SpatialJoinQueryFlat
srdd = spatial_join(
spatialRDD._srdd,
queryRDD._srdd,
useIndex,
considerBoundaryIntersection
)
serialized = JvmSedonaPythonConverter(jvm).\
translate_spatial_pair_rdd_to_python(srdd)
return RDD(serialized, sc, SedonaPickler())
def to_rdd(self):
jvm = self.sc._jvm
serialized = JvmSedonaPythonConverter(jvm). \
translate_spatial_pair_rdd_with_list_to_python(self.jsrdd)
return RDD(serialized, self.sc, SedonaPickler())