def test_circle_rdd(self):
object_rdd = PointRDD(sparkContext=self.sc,
InputLocation=point_rdd_input_location,
Offset=point_rdd_offset,
splitter=point_rdd_splitter,
carryInputData=False)
circle_rdd = CircleRDD(object_rdd, 0.1)
collected_data = circle_rdd.getRawSpatialRDD().collect()
print([geo_data.geom.wkt for geo_data in collected_data])
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_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_circle_rdd(self):
spatial_rdd = PointRDD(
self.sc,
input_location,
offset,
splitter,
True,
num_partitions,
StorageLevel.MEMORY_ONLY
)
circle_rdd = CircleRDD(spatial_rdd, 0.5)
circle_rdd.analyze()
assert circle_rdd.approximateTotalCount == 3000
assert circle_rdd.rawSpatialRDD.take(1)[0].getUserData() == "testattribute0\ttestattribute1\ttestattribute2"
assert circle_rdd.rawSpatialRDD.take(1)[0].geom.radius == 0.5
def test_distance_join_result_to_dataframe(self):
point_csv_df = self.spark.\
read.\
format("csv").\
option("delimiter", ",").\
option("header", "false").load(
area_lm_point_input_location
)
point_csv_df.createOrReplaceTempView("pointtable")
point_df = self.spark.sql(
"select ST_Point(cast(pointtable._c0 as Decimal(24,20)),cast(pointtable._c1 as Decimal(24,20))) as arealandmark from pointtable"
)
point_rdd = Adapter.toSpatialRdd(point_df, "arealandmark")
point_rdd.analyze()
polygon_wkt_df = self.spark.read.\
format("csv").\
option("delimiter", "\t").\
option("header", "false").load(
mixed_wkt_geometry_input_location
)
polygon_wkt_df.createOrReplaceTempView("polygontable")
polygon_df = self.spark.\
sql("select ST_GeomFromWKT(polygontable._c0) as usacounty from polygontable")
polygon_rdd = Adapter.toSpatialRdd(polygon_df, "usacounty")
polygon_rdd.analyze()
circle_rdd = CircleRDD(polygon_rdd, 0.2)
point_rdd.spatialPartitioning(GridType.QUADTREE)
circle_rdd.spatialPartitioning(point_rdd.getPartitioner())
point_rdd.buildIndex(IndexType.QUADTREE, True)
join_result_pair_rdd = JoinQuery.\
DistanceJoinQueryFlat(point_rdd, circle_rdd, True, True)
join_result_df = Adapter.toDf(join_result_pair_rdd, self.spark)
join_result_df.printSchema()
join_result_df.show()
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.RTREE)
object_rdd.buildIndex(IndexType.RTREE, True)
window_rdd.spatialPartitioning(object_rdd.grids)
results = JoinQuery.DistanceJoinQuery(object_rdd, window_rdd, True,
False).collect()
assert results.__len__() == 5467
for data in results:
for polygon_data in data[1]:
assert Circle(data[0].geom, 0.1).covers(polygon_data.geom)
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_outside_polygon_distance_join_correctness(self):
center_geometry_rdd = PolygonRDD(
self.sc.parallelize(self.test_polygon_window_set),
StorageLevel.MEMORY_ONLY)
window_rdd = CircleRDD(center_geometry_rdd, 0.1)
object_rdd = PolygonRDD(
self.sc.parallelize(self.test_outside_polygon_set),
StorageLevel.MEMORY_ONLY)
self.prepare_rdd(object_rdd, window_rdd, GridType.QUADTREE)
result = JoinQuery.DistanceJoinQuery(object_rdd, window_rdd, True,
True).collect()
assert 0 == result.__len__()
result_no_index = JoinQuery.DistanceJoinQuery(object_rdd, window_rdd,
False, True).collect()
assert 0 == result_no_index.__len__()