Last active
August 29, 2015 14:01
-
-
Save jlewi/59b0dec90b639d5d568e to your computer and use it in GitHub Desktop.
Reading a FastQ file in hadoop
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import contrail.AvroHelper | |
| import contrail.spark.SerializableGraphNodeData | |
| val contigFile = contrail.AvroHelper.readAvro(sc,"hdfs://hadoop-nn//tmp/contrail.stages.CompressAndCorrect/part-*.avro") | |
| val datums = contigFile.map(r => new SerializableGraphNodeData(r._1.datum)) | |
| val keyedById = datums.map(r => (r.node_id.toString, r)) | |
| keyedById.cache() | |
| keyedById.lookup(“4fw3YAOX8-lvVjIWgNPGYR3gc5CvsxI”) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import org.apache.spark.rdd.NewHadoopRDD | |
| import org.apache.hadoop.conf.Configuration | |
| import org.apache.avro.mapreduce.AvroKeyInputFormat | |
| import org.apache.hadoop.mapreduce.lib.input.FileInputFormat | |
| import org.apache.hadoop.mapreduce.Job | |
| import org.apache.hadoop.fs.Path | |
| import org.apache.avro.generic.GenericRecord | |
| import contrail.graph.GraphNodeData | |
| import org.apache.avro.mapred.AvroKey | |
| import org.apache.hadoop.io.NullWritable | |
| val job = new Job | |
| FileInputFormat.addInputPath(job, new Path("hdfs://hadoop-nn//tmp/contrail.stages.CompressAndCorrect/part-*.avro")) | |
| job.setInputFormatClass(classOf[AvroKeyInputFormat[GraphNodeData]]) | |
| val nodes = new NewHadoopRDD(sc, classOf[AvroKeyInputFormat[GraphNodeData]] , classOf[AvroKey[GraphNodeData]], classOf[NullWritable], job.getConfiguration) | |
| val nodesById = nodes.map(r => (r._1.datum.node_id, r._1)) | |
| nodesById.cache() | |
| nodesById.lookup("4fw3YAOX8-lvVjIWgNPGYR3gc5CvsxI") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import org.apache.spark.rdd.NewHadoopRDD | |
| import org.apache.hadoop.conf.Configuration | |
| import org.apache.hadoop.io.LongWritable | |
| import contrail.io.FastQWritable | |
| import contrail.io.mapreduce.FastQInputFormatNew | |
| import org.apache.hadoop.mapreduce.Job | |
| import org.apache.hadoop.fs.Path | |
| import org.apache.hadoop.mapreduce.lib.input.FileInputFormat | |
| val job = new Job | |
| FileInputFormat.addInputPath(job, new Path("hdfs://hadoop-nn/tmp/speciesA_300i_40x.2.fastq")) | |
| job.setInputFormatClass(classOf[FastQInputFormatNew]) | |
| val reads = new NewHadoopRDD(sc, classOf[FastQInputFormatNew], classOf[LongWritable], classOf[FastQWritable], job.getConfiguration) | |
| val keyed = reads.map(r => (r._2.getId, r._2)) | |
| keyed.cache() | |
| keyed.lookup("assemblathon_40x300i_b50/2") | |
| reads.count() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I would love to see the code for AvroHelper