MultipleDataframe.scala

import com.mongodb.spark._
import org.bson.Document
import com.mongodb.spark.config._

import org.apache.spark.sql.SQLContext
import com.mongodb.spark.sql._

// load the first dataframe "EVAs"
val evadf = sqlContext.read.mongo()
evadf.printSchema()
evadf.registerTempTable("evas")

// load the 2nd dataframe "astronautHours"
// reconfigure spark context to read from astronautHours
val astronautDF = sqlContext.read.option("collection", "astronautHours").mongo()
astronautDF.printSchema()
astronautDF.registerTempTable("astronautTotals")

sqlContext.sql("SELECT astronautTotals._id, astronautTotals.minutes, evas.Vehicle, evas.Duration FROM astronautTotals JOIN evas ON astronautTotals._id LIKE evas.Crew"  ).show()