sequila sample script

sequila_sample.scala

////// RUN
// map volumes according to your data directory

docker run -it --rm  \
-e USERID=$UID -e GROUPID=$(id -g) \
-v /Users/aga/workplace/data/slice/:/data \
biodatageeks/bdg-sequila:0.5.5-spark-2.4.2-SNAPSHOT \
	spark-shell --driver-memory=4g \
	--jars /tmp/bdg-toolset/bdg-sequila-assembly-0.5.5-spark-2.4.2-SNAPSHOT.jar \
	--conf spark.sql.warehouse.dir=/home/bdgeek/spark-warehouse



//////// SCRIPT

sc.setLogLevel("WARN")

import org.apache.spark.sql.SequilaSession
import org.biodatageeks.utils.{SequilaRegister, UDFRegister,BDGInternalParams}


val ss = SequilaSession(spark)
SequilaRegister.register(ss)

ss.sqlContext.setConf("spark.biodatageeks.bam.useGKLInflate","true")
ss.sqlContext.setConf("spark.biodatageeks.bam.useSparkBAM","false")

ss.sql("CREATE DATABASE IF NOT EXISTS dna")
ss.sql("USE dna")


val bamPath = "/data/NA12878.slice.bam"
val tableNameBAM = "reads"
  
   ss.sql(
    s"""
       |CREATE TABLE ${tableNameBAM}
       |USING org.biodatageeks.datasources.BAM.BAMDataSource
       |OPTIONS(path "${bamPath}")
       |
  """.stripMargin)

ss.sql(s"SELECT * FROM bdg_coverage('${tableNameBAM}','NA12878.slice', 'blocks')").show(5)


val testPath = "/data/test2.bam"
val testTable = "reads_test"

  
   ss.sql(
    s"""
       |CREATE TABLE ${testTable}
       |USING org.biodatageeks.datasources.BAM.BAMDataSource
       |OPTIONS(path "${testPath}")
       |
  """.stripMargin)

ss.sql(s"SELECT * FROM bdg_coverage('${testTable}','test2', 'blocks')").show(5)