def test_creating_point_rdd(self):
point_rdd = PointRDD(self.spark._sc, point_path, 4,
FileDataSplitter.WKT, True)
point_rdd.analyze()
cnt = point_rdd.countWithoutDuplicates()
assert cnt == 12872, f"Point RDD should have 12872 but found {cnt}"
def test_empty_constructor_test(self):
object_rdd = PointRDD(sparkContext=self.sc,
InputLocation=point_rdd_input_location,
Offset=point_rdd_offset,
splitter=point_rdd_splitter,
carryInputData=False)
object_rdd_copy = PointRDD()
object_rdd_copy.rawJvmSpatialRDD = object_rdd.rawJvmSpatialRDD
object_rdd_copy.analyze()
def test_empty_constructor(self):
spatial_rdd = PointRDD(sparkContext=self.sc,
InputLocation=input_location,
Offset=offset,
splitter=splitter,
carryInputData=True,
partitions=num_partitions,
newLevel=StorageLevel.MEMORY_ONLY)
spatial_rdd.buildIndex(IndexType.RTREE, False)
spatial_rdd_copy = PointRDD()
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_equal_partitioning(self):
spatial_rdd = PointRDD(sparkContext=self.sc,
InputLocation=input_location,
Offset=offset,
splitter=splitter,
carryInputData=False,
partitions=10,
newLevel=StorageLevel.MEMORY_ONLY)
spatial_rdd.analyze()
spatial_rdd.spatialPartitioning(GridType.EQUALGRID)
for envelope in spatial_rdd.grids:
print("PointRDD spatial partitioning grids: " + str(envelope))
assert spatial_rdd.countWithoutDuplicates(
) == spatial_rdd.countWithoutDuplicatesSPRDD()
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_r_tree_spatial_partitioning(self):
spatial_rdd = PointRDD(sparkContext=self.sc,
InputLocation=input_location,
Offset=offset,
splitter=splitter,
carryInputData=True,
partitions=10,
newLevel=StorageLevel.MEMORY_ONLY)
spatial_rdd.analyze()
spatial_rdd.spatialPartitioning(GridType.RTREE)
for envelope in spatial_rdd.grids:
print(envelope)
assert spatial_rdd.countWithoutDuplicates(
) == spatial_rdd.countWithoutDuplicatesSPRDD()
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()