US County Shapefile loaded in Apache Sedona (GeoSpark)

spatial_covid.scala

//  ./spark-shell \
//  --packages org.apache.sedona:sedona-core-3.0_2.12:1.0.1-incubating,org.apache.sedona:sedona-sql-3.0_2.12:1.0.1-incubating,org.locationtech.jts:jts-core:1.18.2,org.datasyslab:geotools-wrapper:geotools-24.1 \
//  --conf spark.serializer=org.apache.spark.serializer.KryoSerializer \
//  --conf spark.kryo.registrator=org.apache.sedona.core.serde.SedonaKryoRegistrator

import org.apache.sedona.core.formatMapper.shapefileParser.ShapefileReader
import org.apache.sedona.core.spatialRDD.SpatialRDD
import org.apache.sedona.sql.utils.{Adapter, SedonaSQLRegistrator}
import org.locationtech.jts.geom.{Coordinate, Geometry, GeometryFactory}

SedonaSQLRegistrator.registerAll(spark)

System.setProperty("sedona.global.charset", "utf8")
val shapefileInputLocation="/home/ubuntu/geo/tl_2020_us_county"

var countyRDD = ShapefileReader.readToGeometryRDD(sc, shapefileInputLocation)
var rawSpatialDf = Adapter.toDf(countyRDD, spark)
rawSpatialDf.createOrReplaceTempView("rawSpatialDf")
var transformSQL = "SELECT geometry AS GEOM, STATEFP, COUNTYFP, COUNTYNS, GEOID, NAME, NAMELSAD, LSAD, CLASSFP, MTFCC, CSAFP, CBSAFP, METDIVFP, FUNCSTAT, CAST(ALAND AS Integer), CAST(AWATER AS Integer), ST_Point(CAST (INTPTLON AS decimal(24,20)),CAST (INTPTLAT AS decimal(24,20))) AS INTPTLATLONG FROM rawSpatialDf"
var countyDf = spark.sql(transformSQL.stripMargin)

countyDf.printSchema