Skip to content

Commit

Permalink
Browse files Browse the repository at this point in the history
[QC-METRICS-2] Cleaned up package names.
  • Loading branch information
fnothaft committed Mar 7, 2015
1 parent ab7c8b3 commit 9027cfa
Show file tree
Hide file tree
Showing 20 changed files with 79 additions and 46 deletions.
3 changes: 3 additions & 0 deletions .gitignore
Expand Up @@ -18,3 +18,6 @@ project/plugins/project/

*.iml
.idea/

*~
*#*
2 changes: 1 addition & 1 deletion pom.xml
Expand Up @@ -27,7 +27,7 @@
<hadoop.version>2.2.0</hadoop.version>
<scoverage.version>0.99.2</scoverage.version>

<adam.version>0.16.0</adam.version>
<adam.version>0.16.1-SNAPSHOT</adam.version>
<utils.version>0.1.2</utils.version>
</properties>

Expand Down
Expand Up @@ -15,19 +15,20 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.cli
package org.bdgenomics.qc.cli

import java.io.{ OutputStreamWriter, PrintWriter }

import org.apache.hadoop.fs.{ FileSystem, Path }
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.metrics.{ BucketComparisons, CombinedComparisons, DefaultComparisons }
import org.bdgenomics.adam.cli._
import org.bdgenomics.adam.projections.AlignmentRecordField._
import org.bdgenomics.adam.projections.FieldValue
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.rdd.read.comparisons.ComparisonTraversalEngine
import org.bdgenomics.qc.metrics.{ BucketComparisons, CombinedComparisons, DefaultComparisons }
import org.bdgenomics.qc.rdd.read.comparisons.ComparisonTraversalEngine
import org.bdgenomics.utils.metrics.aggregators.{ AggregatedCollection, CombinedAggregator, HistogramAggregator, Writable }
import org.bdgenomics.utils.metrics.{ Collection, Histogram }
import org.kohsuke.args4j.{ Argument, CmdLineParser, Option => Args4jOption }
Expand Down Expand Up @@ -251,4 +252,4 @@ class CompareADAM(protected val args: CompareADAMArgs) extends ADAMSparkCommand[
}
}
}
}
}
Expand Up @@ -15,19 +15,19 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.cli
package org.bdgenomics.qc.cli

import java.io.OutputStreamWriter
import java.util.regex.Pattern

import org.apache.hadoop.fs.{ FileSystem, Path }
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.metrics.filters.{ CombinedFilter, GeneratorFilter }
import org.bdgenomics.adam.metrics.{ BucketComparisons, DefaultComparisons }
import org.bdgenomics.adam.cli._
import org.bdgenomics.adam.models.ReadBucket
import org.bdgenomics.qc.metrics.filters.{ CombinedFilter, GeneratorFilter }
import org.bdgenomics.qc.metrics.{ BucketComparisons, DefaultComparisons }
import org.kohsuke.args4j.{ Argument, Option => Args4jOption }

import scala.collection.Seq
Expand Down
Expand Up @@ -15,17 +15,19 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.cli
package org.bdgenomics.qc.cli

import org.apache.hadoop.mapreduce.Job
import org.apache.spark.SparkContext._
import org.apache.spark.rdd.RDD
import org.apache.spark.{ Logging, SparkContext }
import org.bdgenomics.adam.cli._
import org.bdgenomics.adam.predicates.GenotypeRecordPASSPredicate
import org.bdgenomics.adam.projections.GenotypeField
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.rdd.variation.ConcordanceTable
import org.bdgenomics.formats.avro.Genotype
import org.bdgenomics.qc.rdd.QCContext._
import org.bdgenomics.qc.rdd.variation.ConcordanceTable
import org.kohsuke.args4j.{ Argument, Option => Args4jOption }

object GenotypeConcordance extends ADAMCommandCompanion {
Expand Down Expand Up @@ -62,8 +64,8 @@ class GenotypeConcordance(protected val args: GenotypeConcordanceArgs) extends A
None
val projection = None //Some(Projection(project))

val testGTs: RDD[Genotype] = sc.adamLoad(args.testGenotypesFile, predicate, projection)
val truthGTs: RDD[Genotype] = sc.adamLoad(args.truthGenotypesFile, predicate, projection)
val testGTs: RDD[Genotype] = sc.loadGenotypes(args.testGenotypesFile, predicate, projection)
val truthGTs: RDD[Genotype] = sc.loadGenotypes(args.truthGenotypesFile, predicate, projection)

val tables = testGTs.concordanceWith(truthGTs)

Expand Down
Expand Up @@ -15,11 +15,11 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.cli
package org.bdgenomics.qc.cli

import java.util.logging.Level._

import org.apache.spark.Logging
import org.bdgenomics.adam.cli._
import org.bdgenomics.adam.util.ParquetLogger

object QCMain extends Logging {
Expand Down
Expand Up @@ -15,7 +15,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.cli
package org.bdgenomics.qc.cli

import java.io.{ BufferedWriter, OutputStreamWriter }

Expand All @@ -24,9 +24,10 @@ import org.apache.hadoop.fs.{ FileSystem, Path }
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.rdd.RDD
import org.apache.spark.{ Logging, SparkContext }
import org.bdgenomics.adam.cli._
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.rdd.variation.{ GenotypesSummary, GenotypesSummaryFormatting }
import org.bdgenomics.formats.avro.Genotype
import org.bdgenomics.qc.rdd.variation.{ GenotypesSummary, GenotypesSummaryFormatting }
import org.kohsuke.args4j

object SummarizeGenotypes extends ADAMCommandCompanion {
Expand Down Expand Up @@ -54,7 +55,7 @@ class SummarizeGenotypes(val args: SummarizeGenotypesArgs) extends ADAMSparkComm
val companion = SummarizeGenotypes

def run(sc: SparkContext, job: Job) {
val adamGTs: RDD[Genotype] = sc.adamLoad(args.adamFile)
val adamGTs: RDD[Genotype] = sc.loadGenotypes(args.adamFile)
val stats = GenotypesSummary(adamGTs)
val result = args.format match {
case "human" => GenotypesSummaryFormatting.format_human_readable(stats)
Expand Down
Expand Up @@ -15,7 +15,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.metrics
package org.bdgenomics.qc.metrics

import org.bdgenomics.formats.avro.AlignmentRecord
import org.bdgenomics.adam.projections.FieldValue
Expand Down
Expand Up @@ -15,12 +15,12 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.metrics
package org.bdgenomics.qc.metrics

import java.util.regex.Pattern
import org.bdgenomics.adam.metrics.filters.ComparisonsFilter
import org.bdgenomics.adam.models.ReadBucket
import org.bdgenomics.adam.projections.FieldValue
import org.bdgenomics.qc.metrics.filters.ComparisonsFilter
import org.bdgenomics.utils.metrics.Collection

trait BucketComparisons[+T] {
Expand Down
Expand Up @@ -15,9 +15,9 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.metrics.filters
package org.bdgenomics.qc.metrics.filters

import org.bdgenomics.adam.metrics.{ CombinedComparisons, BucketComparisons }
import org.bdgenomics.qc.metrics.{ CombinedComparisons, BucketComparisons }
import org.bdgenomics.utils.metrics.{ Collection => BDGCollection }

/**
Expand Down
@@ -0,0 +1,26 @@
/**
* Licensed to Big Data Genomics (BDG) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The BDG licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.qc.rdd

import org.apache.spark.rdd.RDD
import org.bdgenomics.formats.avro.Genotype
import org.bdgenomics.qc.rdd.variation.GenotypeConcordanceRDDFunctions

object QCContext {
implicit def rddToGenotypeConcordanceRDD(rdd: RDD[Genotype]) = new GenotypeConcordanceRDDFunctions(rdd)
}
Expand Up @@ -15,18 +15,18 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.rdd.read.comparisons
package org.bdgenomics.qc.rdd.read.comparisons

import org.apache.hadoop.fs.Path
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.metrics.BucketComparisons
import org.bdgenomics.adam.metrics.filters.GeneratorFilter
import org.bdgenomics.adam.models.ReadBucket
import org.bdgenomics.adam.projections.{ FieldValue, Projection }
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.formats.avro.AlignmentRecord
import org.bdgenomics.qc.metrics.BucketComparisons
import org.bdgenomics.qc.metrics.filters.GeneratorFilter
import org.bdgenomics.utils.metrics.aggregators.{ Aggregated, Aggregator }

import scala.reflect.ClassTag
Expand Down
Expand Up @@ -15,7 +15,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.rdd.variation
package org.bdgenomics.qc.rdd.variation

import java.util.EnumSet

Expand Down Expand Up @@ -45,7 +45,7 @@ object ConcordanceTable {
* to "truth" genotypes.
*/
class ConcordanceTable {
import org.bdgenomics.adam.rdd.variation.ConcordanceTable._
import org.bdgenomics.qc.rdd.variation.ConcordanceTable._

private val table_ = Array.fill[Long](GenotypeType.values.length, GenotypeType.values.length)(0L)

Expand Down
Expand Up @@ -15,7 +15,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.rdd.variation
package org.bdgenomics.qc.rdd.variation

import org.apache.hadoop.io.LongWritable
import org.apache.spark.SparkContext._
Expand Down
Expand Up @@ -15,14 +15,13 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.rdd.variation
package org.bdgenomics.qc.rdd.variation

import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.rdd.variation.GenotypesSummary.StatisticsMap
import org.bdgenomics.adam.rdd.variation.GenotypesSummaryCounts.ReferenceAndAlternate
import org.bdgenomics.adam.rich.RichVariant._
import org.bdgenomics.formats.avro.{ Genotype, GenotypeAllele }

import org.bdgenomics.qc.rdd.variation.GenotypesSummary.StatisticsMap
import org.bdgenomics.qc.rdd.variation.GenotypesSummaryCounts.ReferenceAndAlternate
import scala.collection.JavaConverters._
import scala.collection.immutable.Map
import scala.collection.mutable
Expand Down
Expand Up @@ -15,7 +15,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.metrics
package org.bdgenomics.qc.metrics

import org.bdgenomics.adam.models.SingleReadBucket
import org.bdgenomics.adam.util.ADAMFunSuite
Expand Down
Expand Up @@ -15,7 +15,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.metrics.filters
package org.bdgenomics.qc.metrics.filters

import org.bdgenomics.utils.metrics.{ Collection => BDGCollection }
import org.scalatest._
Expand Down
Expand Up @@ -15,13 +15,13 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.rdd.read.comparisons
package org.bdgenomics.qc.rdd.read.comparisons

import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.metrics.MappedPosition
import org.bdgenomics.adam.projections.AlignmentRecordField
import org.bdgenomics.adam.util.ADAMFunSuite
import org.bdgenomics.formats.avro.{ AlignmentRecord, Contig }
import org.bdgenomics.qc.metrics.MappedPosition
import org.bdgenomics.utils.metrics.Histogram
import org.bdgenomics.utils.metrics.aggregators.HistogramAggregator

Expand Down
Expand Up @@ -15,13 +15,14 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.rdd.variation
package org.bdgenomics.qc.rdd.variation

import org.apache.spark.SparkContext._
import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.util.ADAMFunSuite
import org.bdgenomics.formats.avro._
import org.bdgenomics.qc.rdd.QCContext._

class GenotypeConcordanceRDDFunctionsSuite extends ADAMFunSuite {
def v0 = Variant.newBuilder
Expand All @@ -38,16 +39,16 @@ class GenotypeConcordanceRDDFunctionsSuite extends ADAMFunSuite {

val g0 = gb.build
val g1 = gb.build
val tables0 = sc.parallelize(Seq(g0)).concordanceWith(sc.parallelize(Seq(g1))).collectAsMap
val tables0: scala.collection.Map[String, ConcordanceTable] = sc.parallelize(Seq(g0)).concordanceWith(sc.parallelize(Seq(g1))).collectAsMap
assert(tables0.size === 1)
val table0 = tables0.getOrElse("NA12878", ConcordanceTable())
val table0: ConcordanceTable = tables0.getOrElse("NA12878", ConcordanceTable())
assert(table0.total === 1)
assert(table0.get(GenotypeType.HET, GenotypeType.HET) === 1)

val g2 = gb.setAlleles(List(GenotypeAllele.Ref, GenotypeAllele.Ref)).build
val table1 = sc.parallelize(Seq(g0))
val tables1: scala.collection.Map[String, ConcordanceTable] = sc.parallelize(Seq(g0))
.concordanceWith(sc.parallelize(Seq(g2))).collectAsMap()
.getOrElse("NA12878", ConcordanceTable())
val table1: ConcordanceTable = tables1.getOrElse("NA12878", ConcordanceTable())
assert(table1.total === 1)
assert(table1.get(GenotypeType.HET, GenotypeType.HOM_REF) === 1)
}
Expand All @@ -58,10 +59,10 @@ class GenotypeConcordanceRDDFunctionsSuite extends ADAMFunSuite {
val gts: RDD[Genotype] = sc.loadGenotypes(path)
assert(gts.filter(_.getSampleId == "NA12878").count === 5)

val tables = gts.concordanceWith(gts).collectAsMap
val tables: scala.collection.Map[String, ConcordanceTable] = gts.concordanceWith(gts).collectAsMap
assert(tables.size === 3L)

val table0 = tables.getOrElse("NA12878", ConcordanceTable())
val table0: ConcordanceTable = tables.getOrElse("NA12878", ConcordanceTable())
assert(table0.total === 5L)
assert(table0.concordance === 1.0)
}
Expand Down
Expand Up @@ -15,11 +15,11 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.rdd.variation
package org.bdgenomics.qc.rdd.variation

import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.rdd.variation.GenotypesSummaryCounts.ReferenceAndAlternate
import org.bdgenomics.adam.util.ADAMFunSuite
import org.bdgenomics.qc.rdd.variation.GenotypesSummaryCounts.ReferenceAndAlternate
import org.bdgenomics.formats.avro._

class GenotypesSummarySuite extends ADAMFunSuite {
Expand Down

0 comments on commit 9027cfa

Please sign in to comment.