使用Spark 2 Scala使用经纬度坐标计算距离

import org.apache.spark.sql.functions._

val lat1 = 40.7128 // 第一个点的纬度
val lon1 = -74.0060 // 第一个点的经度
val lat2 = 34.0522 // 第二个点的纬度
val lon2 = -118.2437 // 第二个点的经度

val distance = udf((lat1: Double, lon1: Double, lat2: Double, lon2: Double) => {
  val earthRadius = 6371 // 地球半径，单位为千米
  val dLat = math.toRadians(lat2 - lat1)
  val dLon = math.toRadians(lon2 - lon1)
  val a = math.sin(dLat / 2) * math.sin(dLat / 2) +
    math.cos(math.toRadians(lat1)) * math.cos(math.toRadians(lat2)) *
    math.sin(dLon / 2) * math.sin(dLon / 2)
  val c = 2 * math.atan2(math.sqrt(a), math.sqrt(1 - a))
  val distance = earthRadius * c
  distance
})

val result = spark.range(1).select(distance(lit(lat1), lit(lon1), lit(lat2), lit(lon2)).as("distance"))
result.show()