eric-maynard

import org.apache.spark.util._

def vectorizedAddUnsafe128x3(a: Array[Byte], b: Array[Byte]): Array[Byte] = {
    var carry: Int = 0
    ((a.length -1) to 0 by -4).map(i => {
        val x: Long =
            java.lang.Integer.toUnsignedLong(((((((a(i - 3)) << 24) | a(i - 2)) << 16) | a(i - 1)) << 8) | a(i)) +
            java.lang.Integer.toUnsignedLong(((((((b(i - 3)) << 24) | b(i - 2)) << 16) | b(i - 1)) << 8) | b(i)) +
            carry
        carry = if (x > 0xFFFFFFFFL && (i - 3) % 16 != 0) 1 else 0

eric-maynard

#!/bin/bash
 ##################################################
#                   Constants                    #
##################################################


TABLE_NAME="underlying_tables"
DB_COL="db_name"
VIEW_COL="view_name"
TABLE_COL="table_name"

eric-maynard

#!/bin/bash

##################################################
#                   Constants                    #
##################################################

# curl constants:
HOST="bkestelman-1.gce.cloudera.com"
CM_USER="admin"
CM_PASS="admin"

eric-maynard

#!/bin/bash

##################################################
#                   Constants                    #
##################################################

delimiter='~'
soft_delimiter=","
column_limit=9

eric-maynard

package com.cloudera.example

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

import scala.collection.mutable._

import scala.collection.mutable.ListBuffer

eric-maynard

//command line args:
val buckets = 5
val myBucket = 1//method 2 only

//helper functions
case class TableWithHash(tableName: String, hash: Int)
def hashTable(string: tableName): TableWithHash = {
  TableWithHash(tableName, (tableName.hashCode % buckets).toInt)
}

eric-maynard

import org.apache.spark.ml._
import org.apache.spark.ml.tuning._
import org.apache.spark.ml.evaluation._
import org.apache.spark.mllib.regression._
import org.apache.spark.mllib.linalg.DenseVector
import org.apache.spark.sql._
import org.apache.spark.ml.classification._
import org.apache.spark.ml.feature._
import sqlContext.implicits._
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics