arahuja

/hpc/users/ahujaa01/spark/spark-1.6.2-bin-hadoop2.6/bin/spark-submit 
   --master yarn-client 
   --executor-memory 18g 
   --driver-memory 12g 
   --num-executors 100 
   --executor-cores 8 
   --class org.hammerlab.guacamole.Main 
   --conf spark.default.parallelism=10000 
   --conf spark.yarn.executor.memoryOverhead=3024 
   --conf spark.shuffle.service.enabled=true 

arahuja

let seq2hla_from_bam
    ~path
    ~sample =
  let open Biokepi.KEDSL in
  let open Biokepi.Pipeline.Construct in
  let reference_build = "b37" in
  let work_dir =
    Biokepi.Machine.work_dir Demeter.machine
    // "mskcc-bladder-rna" in
  let initial_bam =

arahuja

In [3]: transcripts = ensembl.transcripts_at_locus('chr12', 125621282)

In [4]: transcript = transcripts[0]

In [5]: transcript.spliced_offset(125621282)
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-5-59d91508f846> in <module>()
----> 1 transcript.spliced_offset(125621282)

arahuja

import org.apache.spark.{SparkContext, SparkConf}

object SimpleSparkApp extends App {
  
  override def main(args: Array[String]) = {

    val config: SparkConf = new SparkConf() 
    config.setMaster("local[4]")
    config.setAppName("MySimpleSparkApp")
    

arahuja

#! /bin/sh

SCRIPT_NAME=$(basename $0)

short_usage()
{
  echo "Cf :  $SCRIPT_NAME  [--help]"
}
long_usage()
{

arahuja

chr1:14416-14499,chr1:14510-14596,chr1:14693-14782,chr1:14853-14972,chr1:15033-15128,chr1:15632-15900,chr1:15922-16004,chr1:16562-16857,chr1:16914-17012,chr1:17272-17354,chr1:17424-17499,chr1:17567-17696,chr1:17752-17830,chr1:17883-17965,chr1:17997-18130,chr1:18154-18442,chr1:19051-19242,chr1:20523-20708,chr1:24441-24674,chr1:24698-24779,chr1:24802-24945,chr1:29178-29425,chr1:30249-30543,chr1:35079-35286,chr1:35289-35371,chr1:35677-35856,chr1:62953-63130,chr1:63136-63264,chr1:63352-63431,chr1:63535-63697,chr1:65447-65697,chr1:69036-69193,chr1:69230-69384,chr1:69421-69557,chr1:69576-69647,chr1:69667-69778,chr1:69787-69934,chr1:69941-70018,chr1:112640-112731,chr1:120796-120881,chr1:135148-135289,chr1:135712-135807,chr1:135815-136019,chr1:136084-136180,chr1:137370-137557,chr1:137625-137721,chr1:173694-173919,chr1:228206-228442,chr1:228467-228545,chr1:228615-228727,chr1:258957-259048,chr1:267027-267103,chr1:267117-267202,chr1:326427-326544,chr1:326561-326761,chr1:327136-327210,chr1:327236-327310,chr1:327322-32742

arahuja

      case taskNumberRegionPairs1 :: taskNumberRegionPairs2 :: Nil => {
        val rdd1Records = sc.accumulator(0L, s"rdd1.records")
        val rdd2Records = sc.accumulator(0L, s"rdd2.records")
        val lociAccum = sc.accumulator(0L, s"rdd.task.loci")
        // Cogroup-based implementation.
        val paritioned = taskNumberRegionPairs1.cogroup(taskNumberRegionPairs2, new PartitionByKey(numTasks.toInt))
        val sorted = new ShuffledRDD[TaskPosition, (Iterable[M], Iterable[M]), (Iterable[M], Iterable[M])](
          paritioned,
          new PartitionByKey(numTasks.toInt))
          .setKeyOrdering(implicitly[Ordering[TaskPosition]])

arahuja

package edu.berkeley.cs.amplab.adam.cli

import java.io.File;

import edu.berkeley.cs.amplab.adam.models.ADAMVariantContext
import edu.berkeley.cs.amplab.adam.rdd.AdamContext._
import edu.berkeley.cs.amplab.adam.rdd.variation.ADAMVariationContext._
import edu.berkeley.cs.amplab.adam.util.ParquetLogger
import java.util.logging.Level
import org.apache.hadoop.mapreduce.Job

arahuja

events = load 'data' USING PigStorage() as (timestamp:int, event_id:int, advertiser_id:int)
advertiser_data = load 'advertiser_data' USING PigStorage() as (id:int, name:chararray, campaign:chararray)

events_w_metadata = JOIN events by advertiser_id, advertiser_data by id;