val df = CSV.load(args(0))
val sumSteps = df.sum("steps")

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

val df = sc.parallelize(Array(10,2,3,4)).toDF("steps")
df.select(col("steps")).rdd.map(_(0).asInstanceOf[Int]).reduce(_+_)

//res1 Int = 19

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

val df = CSV.load(args(0))
val sumSteps =  df.agg(sum("steps")).first.get(0)

val sumSteps: Long = df.agg(sum("steps").cast("long")).first.getLong(0)

val sums = df.agg(sum("col1").as("sum_col1"), sum("col2").as("sum_col2"), ...).first

df.groupBy().sum()

df.groupby('steps').sum().show()