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_raw_spatial_rdd_assignment(self):
spatial_rdd = PointRDD(self.sc, input_location, offset, splitter, True,
num_partitions, StorageLevel.MEMORY_ONLY)
spatial_rdd.analyze()
empty_point_rdd = PointRDD()
empty_point_rdd.rawSpatialRDD = spatial_rdd.rawSpatialRDD
empty_point_rdd.analyze()
assert empty_point_rdd.countWithoutDuplicates(
) == spatial_rdd.countWithoutDuplicates()
assert empty_point_rdd.boundaryEnvelope == spatial_rdd.boundaryEnvelope
assert empty_point_rdd.rawSpatialRDD.map(
lambda x: x.geom.area).collect()[0] == 0.0
assert empty_point_rdd.rawSpatialRDD.take(9)[4].getUserData(
) == "testattribute0\ttestattribute1\ttestattribute2"
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_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_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 main():
start_time = datetime.now()
# ----------------------------------------------------------
# copy gnaf tables from Postgres to a CSV file - a one off
# - export required fields only and no header
# ----------------------------------------------------------
pg_conn = pg_pool.getconn()
pg_cur = pg_conn.cursor()
sql = """COPY (
SELECT longitude, latitude, gnaf_pid, locality_pid, locality_name, postcode, state
FROM gnaf_202008.{}
) TO STDOUT WITH CSV"""
# address principals
with open(gnaf_csv_file_path, 'w') as csv_file:
pg_cur.copy_expert(sql.format("address_principals"), csv_file)
# append address aliases
with open(gnaf_csv_file_path, 'a') as csv_file:
pg_cur.copy_expert(sql.format("address_aliases"), csv_file)
pg_cur.close()
pg_pool.putconn(pg_conn)
logger.info("\t - GNAF points exported to CSV: {}".format(datetime.now() -
start_time))
start_time = datetime.now()
# ----------------------------------------------------------
# create Spark session and context
# ----------------------------------------------------------
# upload Apache Sedona JARs
upload_jars()
spark = (SparkSession.builder.master("local[*]").appName("query").config(
"spark.sql.session.timeZone",
"UTC").config("spark.sql.debug.maxToStringFields", 100).config(
"spark.serializer", KryoSerializer.getName).config(
"spark.kryo.registrator",
GeoSparkKryoRegistrator.getName).config(
"spark.cores.max", num_processors).config(
"spark.sql.adaptive.enabled",
"true").config("spark.driver.memory",
"8g").getOrCreate())
# Register Apache Sedona UDTs and UDFs
GeoSparkRegistrator.registerAll(spark)
# # set Sedona spatial indexing and partitioning config in Spark session
# # (no effect on the "small" spatial join query in this script. Will improve bigger queries)
# spark.conf.set("geospark.global.index", "true")
# spark.conf.set("geospark.global.indextype", "rtree")
# spark.conf.set("geospark.join.gridtype", "kdbtree")
sc = spark.sparkContext
logger.info("\t - PySpark {} session initiated: {}".format(
sc.version,
datetime.now() - start_time))
start_time = datetime.now()
# ----------------------------------------------------------
# create GNAF PointRDD from CSV file
# ----------------------------------------------------------
offset = 0 # The point long/lat fields start at column 0
carry_other_attributes = True # include non-geo columns
point_rdd = PointRDD(sc, os.path.join(output_path, gnaf_csv_file_path),
offset, FileDataSplitter.CSV, carry_other_attributes)
point_rdd.analyze()
# add partitioning and indexing
point_rdd.spatialPartitioning(GridType.KDBTREE)
point_rdd.buildIndex(IndexType.RTREE, True)
# set Spark storage type - set to MEMORY_AND_DISK if low on memory
point_rdd.indexedRDD.persist(StorageLevel.MEMORY_ONLY)
logger.info("\t - GNAF RDD created: {}".format(datetime.now() -
start_time))
# ----------------------------------------------------------
# get boundary tags using a spatial join
# ----------------------------------------------------------
for bdy in bdy_list:
bdy_tag(spark, point_rdd, bdy)
# point_rdd.unpersist() # no such method on a SpatialRDD
# ----------------------------------------------------------
# merge boundary tag dataframes with GNAF records
# - required because spatial joins are INNER JOIN only,
# need to add untagged GNAF points
# ----------------------------------------------------------
start_time = datetime.now()
# create gnaf dataframe and SQL view
gnaf_df = spark.read \
.option("header", False) \
.option("inferSchema", True) \
.csv(gnaf_csv_file_path) \
.drop("_C0") \
.drop("_C1") \
.withColumnRenamed("_C2", "gnaf_pid") \
.withColumnRenamed("_C3", "locality_pid") \
.withColumnRenamed("_C4", "locality_name") \
.withColumnRenamed("_C5", "postcode") \
.withColumnRenamed("_C6", "state")
# gnaf_df.printSchema()
# gnaf_df.show(10, False)
gnaf_df.createOrReplaceTempView("pnt")
# add bdy tags, one bdy type at a time
for bdy in bdy_list:
gnaf_df = join_bdy_tags(spark, bdy)
gnaf_df.createOrReplaceTempView("pnt")
# # add point geoms for output to Postgres - in the PostGIS specific EWKT format
# final_df = gnaf_df.withColumn("geom", f.expr("concat('SRID=4326;POINT (', longitude, ' ', latitude, ')')")) \
# .drop("longitude") \
# .drop("latitude")
# # final_df.printSchema()
# # final_df.show(10, False)
logger.info("\t - Boundary tags merged: {}".format(datetime.now() -
start_time))
# output result to Postgres
export_to_postgres(gnaf_df, "testing2.gnaf_with_bdy_tags",
os.path.join(output_path, "temp_gnaf_with_bdy_tags"),
True)
# cleanup
spark.stop()
# delete intermediate bdy tag files and GNAF csv file
for bdy in bdy_list:
shutil.rmtree(
os.path.join(output_path, "gnaf_with_{}".format(bdy["name"])))
os.remove(gnaf_csv_file_path)