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)
serlialized = jvm.GeoSerializerData.serializeToPython(srdd)
return RDD(serlialized, sc, GeoSparkPickler())
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 = JvmGeoSparkPythonConverter(jvm).translate_spatial_rdd_to_python(srdd)
return RDD(serialized, sc, GeoSparkPickler())
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)
serlialized = jvm.GeoSerializerData.serializeToPython(srdd)
return RDD(serlialized, sc, GeoSparkPickler())
def spatialPartitionedRDD(self):
"""
:return:
"""
serialized_spatial_rdd = self._jvm.GeoSerializerData.serializeToPython(
get_field(self._srdd, "spatialPartitionedRDD"))
if not hasattr(self, "_spatial_partitioned_rdd"):
setattr(self, "_spatial_partitioned_rdd",
RDD(serialized_spatial_rdd, self._sc, GeoSparkPickler()))
else:
self._spatial_partitioned_rdd._jrdd = serialized_spatial_rdd
return getattr(self, "_spatial_partitioned_rdd")
def getRawSpatialRDD(self):
"""
:return:
"""
serialized_spatial_rdd = GeoSparkPythonConverter(self._jvm).translate_spatial_rdd_to_python(self._srdd.getRawSpatialRDD())
if not hasattr(self, "_raw_spatial_rdd"):
RDD.saveAsObjectFile = lambda x, path: x._jrdd.saveAsObjectFile(path)
setattr(self, "_raw_spatial_rdd", RDD(serialized_spatial_rdd, self._sc, GeoSparkPickler()))
else:
self._raw_spatial_rdd._jrdd = serialized_spatial_rdd
return getattr(self, "_raw_spatial_rdd")
def spatialPartitionedRDD(self):
"""
:return:
"""
serialized_spatial_rdd = GeoSparkPythonConverter(
self._jvm).translate_spatial_rdd_to_python(
get_field(self._srdd, "spatialPartitionedRDD"))
if not hasattr(self, "_spatial_partitioned_rdd"):
setattr(self, "_spatial_partitioned_rdd",
RDD(serialized_spatial_rdd, self._sc, GeoSparkPickler()))
else:
self._spatial_partitioned_rdd._jrdd = serialized_spatial_rdd
return getattr(self, "_spatial_partitioned_rdd")
def getRawSpatialRDD(self):
"""
:return:
"""
serialized_spatial_rdd = self._jvm.GeoSerializerData.serializeToPython(
self._srdd.getRawSpatialRDD())
if not hasattr(self, "_raw_spatial_rdd"):
RDD.saveAsObjectFile = lambda x, path: x._jrdd.saveAsObjectFile(
path)
setattr(self, "_raw_spatial_rdd",
RDD(serialized_spatial_rdd, self._sc, GeoSparkPickler()))
else:
self._raw_spatial_rdd._jrdd = serialized_spatial_rdd
return getattr(self, "_raw_spatial_rdd")
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)
serlialized = jvm.GeoSerializerData.serializeToPythonHashSet(srdd)
return RDD(serlialized, sc, GeoSparkPickler())
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)
serlialized = jvm.GeoSerializerData.serializeToPython(srdd)
return RDD(serlialized, sc, GeoSparkPickler())
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 = JvmGeoSparkPythonConverter(jvm).\
translate_spatial_pair_rdd_to_python(srdd)
return RDD(serialized, sc, GeoSparkPickler())
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 = JvmGeoSparkPythonConverter(jvm).\
translate_spatial_pair_rdd_with_hashset_to_python(srdd)
return RDD(serialized, sc, GeoSparkPickler())