def test_spatial_join_query_with_polygon_rdd_using_index(self):
query_rdd = PolygonRDD(self.sc, input_location_query_polygon, splitter,
True, num_partitions, StorageLevel.MEMORY_ONLY,
"epsg:4326", "epsg:3005")
spatial_rdd = PointRDD(self.sc, input_location, offset, splitter, True,
num_partitions, StorageLevel.MEMORY_ONLY,
"epsg:4326", "epsg:3005")
query_rdd.analyze()
spatial_rdd.analyze()
spatial_rdd.spatialPartitioning(grid_type)
spatial_rdd.buildIndex(IndexType.RTREE, True)
query_rdd.spatialPartitioning(spatial_rdd.getPartitioner())
result = JoinQuery.SpatialJoinQuery(spatial_rdd, query_rdd, False,
True).collect()
assert result[1][0].getUserData() is not None
for data in result:
if data[1].__len__() != 0:
for right_data in data[1]:
assert right_data.getUserData() is not None
def test_voronoi_spatial_partitioning(self):
spatial_rdd = PolygonRDD(sparkContext=self.sc,
InputLocation=input_location,
splitter=FileDataSplitter.CSV,
carryInputData=True,
partitions=10,
newLevel=StorageLevel.MEMORY_ONLY)
spatial_rdd.analyze()
spatial_rdd.spatialPartitioning(GridType.VORONOI)
for envelope in spatial_rdd.grids:
print(envelope)
def test_hilbert_curve_spatial_partitioning(self):
spatial_rdd = PolygonRDD(sparkContext=self.sc,
InputLocation=input_location,
splitter=splitter,
carryInputData=True,
partitions=10,
newLevel=StorageLevel.MEMORY_ONLY)
spatial_rdd.analyze()
spatial_rdd.spatialPartitioning(GridType.HILBERT)
for envelope in spatial_rdd.grids:
print(envelope)
def test_empty_constructor(self):
spatial_rdd = PolygonRDD(sparkContext=self.sc,
InputLocation=input_location,
splitter=splitter,
carryInputData=True,
partitions=num_partitions,
newLevel=StorageLevel.MEMORY_ONLY)
spatial_rdd.analyze()
spatial_rdd.spatialPartitioning(grid_type)
spatial_rdd.buildIndex(IndexType.RTREE, True)
spatial_rdd_copy = PolygonRDD()
spatial_rdd_copy.rawJvmSpatialRDD = spatial_rdd.rawJvmSpatialRDD
spatial_rdd_copy.analyze()
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_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()
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_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_polygon_distance_join_with_crs_transformation(self):
query_rdd = PolygonRDD(self.sc, input_location_query_polygon, splitter,
True, num_partitions, StorageLevel.MEMORY_ONLY,
"epsg:4326", "epsg:3857")
window_rdd = CircleRDD(query_rdd, 0.1)
object_rdd = PolygonRDD(self.sc, input_location_query_polygon,
splitter, True, num_partitions,
StorageLevel.MEMORY_ONLY, "epsg:4326",
"epsg:3857")
object_rdd.rawJvmSpatialRDD.jsrdd.repartition(4)
object_rdd.spatialPartitioning(GridType.KDBTREE)
object_rdd.buildIndex(IndexType.RTREE, True)
window_rdd.spatialPartitioning(object_rdd.getPartitioner())
results = JoinQuery.DistanceJoinQuery(object_rdd, window_rdd, True,
False).collect()
assert 5467 == results.__len__()
for data in results:
for polygon_data in data[1]:
assert Circle(data[0].geom, 0.1).covers(polygon_data.geom)