This is working!
Thank you so much :)

Stefan Panayotov, PhD 
Home: 610-355-0919 
Cell: 610-517-5586 
email: [email protected] 
[email protected] 
[email protected]

 
From: [email protected]
Date: Tue, 21 Jul 2015 12:08:04 -0700
Subject: Re: Add column to DF
To: [email protected]
CC: [email protected]

Try instead:
import org.apache.spark.sql.functions._
val determineDayPartID = udf((evntStDate: String, evntStHour: String) => {
    val stFormat = new java.text.SimpleDateFormat("yyMMdd")
    var stDateStr:String = evntStDate.substring(2,8)
    val stDate:Date = stFormat.parse(stDateStr)
    val stHour = evntStHour.substring(1,3).toDouble + 0.1
    var bucket = Math.ceil(stHour/3.0).toInt
    val cal:Calendar = Calendar.getInstance
    cal.setTime(stDate)
    var dayOfWeek = cal.get(Calendar.DAY_OF_WEEK)
    if (dayOfWeek == 1) dayOfWeek = 8
    if (dayOfWeek > 6) bucket = bucket + 8
   bucket

  })

input.withColumn("DayPartID", determineDayPartID (col("StartDate"), 
col("EventStartHour")))                                       

Reply via email to