def test_indexed_rdd_assignment(self):
object_rdd = PointRDD(self.sc, point_rdd_input_location,
point_rdd_offset, point_rdd_splitter, True)
query_window_rdd = CircleRDD(object_rdd, 0.1)
object_rdd.analyze()
object_rdd.spatialPartitioning(GridType.QUADTREE)
object_rdd.buildIndex(IndexType.QUADTREE, True)
query_window_rdd.spatialPartitioning(object_rdd.getPartitioner())
object_rdd.buildIndex(IndexType.RTREE, False)
object_rdd.indexedRDD.persist(StorageLevel.MEMORY_ONLY)
query_window_rdd.jvmSpatialPartitionedRDD.persist(
StorageLevel.MEMORY_ONLY)
query_window_rdd.jvmSpatialPartitionedRDD.count()
object_rdd.indexedRDD.count()
import time
start = time.time()
for _ in range(each_query_loop_times):
result_size = JoinQuery.DistanceJoinQuery(object_rdd,
query_window_rdd, True,
True).count()
diff = time.time() - start
object_rdd = PointRDD(self.sc, point_rdd_input_location,
point_rdd_offset, point_rdd_splitter, True)
query_window_rdd = CircleRDD(object_rdd, 0.1)
object_rdd.analyze()
object_rdd.spatialPartitioning(GridType.QUADTREE)
object_rdd.buildIndex(IndexType.QUADTREE, True)
query_window_rdd.spatialPartitioning(object_rdd.getPartitioner())
object_rdd.buildIndex(IndexType.RTREE, False)
start1 = time.time()
for _ in range(each_query_loop_times):
result_size = JoinQuery.DistanceJoinQuery(object_rdd,
query_window_rdd, True,
True).count()
def test_spatial_join_query(self):
point_rdd = PointRDD(self.sc, point_path, 4, FileDataSplitter.WKT,
True)
polygon_rdd = PolygonRDD(self.sc, counties_path, 2, 3,
FileDataSplitter.WKT, True)
point_rdd.analyze()
point_rdd.spatialPartitioning(GridType.KDBTREE)
polygon_rdd.spatialPartitioning(point_rdd.getPartitioner())
result = JoinQuery.SpatialJoinQuery(point_rdd, polygon_rdd, True,
False)
print(result.count())
def test_distance_join_query(self):
object_rdd = PointRDD(sparkContext=self.sc,
InputLocation=point_rdd_input_location,
Offset=point_rdd_offset,
splitter=point_rdd_splitter,
carryInputData=False)
query_window_rdd = CircleRDD(object_rdd, 0.1)
object_rdd.analyze()
object_rdd.spatialPartitioning(GridType.QUADTREE)
query_window_rdd.spatialPartitioning(object_rdd.getPartitioner())
for i in range(each_query_loop_times):
result_size = JoinQuery.DistanceJoinQuery(object_rdd,
query_window_rdd, False,
True).count()
def test_spatial_join_query_and_build_index_on_points_on_the_fly(self):
query_window = PolygonRDD(self.sc, polygon_rdd_input_location,
polygon_rdd_start_offset,
polygon_rdd_end_offset, polygon_rdd_splitter,
True)
object_rdd = PointRDD(sparkContext=self.sc,
InputLocation=point_rdd_input_location,
Offset=point_rdd_offset,
splitter=point_rdd_splitter,
carryInputData=False)
object_rdd.analyze()
object_rdd.spatialPartitioning(join_query_partitionin_type)
query_window.spatialPartitioning(object_rdd.getPartitioner())
for i in range(each_query_loop_times):
result_size = JoinQuery.SpatialJoinQuery(object_rdd, query_window,
True, False).count()
def test_distance_join_query(self):
object_rdd = PointRDD(self.sc, point_rdd_input_location,
point_rdd_offset, point_rdd_splitter, True,
StorageLevel.MEMORY_ONLY)
query_window_rdd = CircleRDD(object_rdd, 0.1)
object_rdd.spatialPartitioning(GridType.QUADTREE)
query_window_rdd.spatialPartitioning(object_rdd.getPartitioner())
object_rdd.spatialPartitionedRDD.persist(StorageLevel.MEMORY_ONLY)
assert object_rdd.spatialPartitionedRDD.is_cached
query_window_rdd.spatialPartitionedRDD.persist(
StorageLevel.MEMORY_ONLY)
for _ in range(each_query_loop_times):
result_size = JoinQuery.DistanceJoinQuery(object_rdd,
query_window_rdd, False,
True).count()
def test_spatial_join_query_and_build_index_on_polygons_on_the_fly(self):
query_window_rdd = PolygonRDD(self.sc, polygon_rdd_input_location,
polygon_rdd_start_offset,
polygon_rdd_end_offset,
polygon_rdd_splitter, True)
object_rdd = PointRDD(sparkContext=self.sc,
InputLocation=point_rdd_input_location,
Offset=point_rdd_offset,
splitter=point_rdd_splitter,
carryInputData=False)
object_rdd.analyze()
object_rdd.spatialPartitioning(join_query_partitionin_type)
query_window_rdd.spatialPartitioning(object_rdd.getPartitioner())
for i in range(each_query_loop_times):
join_params = JoinParams(False, polygon_rdd_index_type,
JoinBuildSide.LEFT)
resultSize = JoinQuery.spatialJoin(query_window_rdd, object_rdd,
join_params).count()
def test_spatial_join_query(self):
query_window_rdd = PolygonRDD(self.sc, polygon_rdd_input_location,
polygon_rdd_start_offset,
polygon_rdd_end_offset,
polygon_rdd_splitter, True)
object_rdd = PointRDD(self.sc, point_rdd_input_location,
point_rdd_offset, point_rdd_splitter, True,
StorageLevel.MEMORY_ONLY)
object_rdd.spatialPartitioning(join_query_partitioning_type)
query_window_rdd.spatialPartitioning(object_rdd.getPartitioner())
object_rdd.jvmSpatialPartitionedRDD.persist(StorageLevel.MEMORY_ONLY)
query_window_rdd.jvmSpatialPartitionedRDD.persist(
StorageLevel.MEMORY_ONLY)
for _ in range(each_query_loop_times):
result_size = JoinQuery.SpatialJoinQuery(object_rdd,
query_window_rdd, False,
True).count()