reading-data.scala

val conf = new SparkConf().setAppName("predictor")
val sc = new SparkContext(conf)
val sqlContext = new SQLContext(sc)

val rawData = sqlContext.read.format("com.databricks.spark.csv")
            .option("header", "true")
            .option("inferSchema", "true")
            .load(dataPath)
            .withColumn("DelayOutputVar", col("ArrDelay").cast("double"))
            .withColumn("DepDelayDouble", col("DepDelay").cast("double"))
            .withColumn("TaxiOutDouble", col("TaxiOut").cast("double"))
            .cache()