Fix index from 1 for genes

Bump version to 5.1.5 Remove Artifactory resolver for jobserver
data-intuitive · Aug 23, 2023 · 9c274a1 · 9c274a1
1 parent 755d1c9
commit 9c274a1
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -15,6 +15,7 @@ There's still a lot of work to be done on this (version numbers don't reflect ev
 | 5.1.2     | 4.1.1      | 0.11.1          | 2.4.7 |
 | 5.1.3     | 4.1.1      | 0.11.1          | 2.4.7 |
 | 5.1.4     | 4.1.2      | 0.11.1          | 2.4.7 |
+| 5.1.5     | 4.1.2      | 0.11.1          | 2.4.7 |
 
 # API Documentation
 

diff --git a/build.sbt b/build.sbt
@@ -2,7 +2,7 @@ name := "LuciusAPI"
 
 import aether.AetherKeys._
 
-ThisBuild / version := "5.1.4"
+ThisBuild / version := "5.1.5"
 
 scalaVersion := "2.11.12"
 

diff --git a/src/main/scala/com/dataintuitive/luciusapi/IO.scala b/src/main/scala/com/dataintuitive/luciusapi/IO.scala
@@ -8,7 +8,8 @@ import io.GenesIO._
 import io.{ Version, DatedVersionedObject, State }
 
 import org.apache.spark.sql.SparkSession
-import org.apache.spark.sql.functions.{lit, typedLit, concat, array, monotonicallyIncreasingId, col}
+import org.apache.spark.sql.functions.{lit, typedLit, concat, array, col, row_number}
+import org.apache.spark.sql.expressions.Window
 
 import org.apache.hadoop.fs.{FileSystem, Path}
 
@@ -20,7 +21,7 @@ object IO {
     val genesRaw = sparkSession.read.parquet(geneAnnotationsFile)
     val genesMapped = genesRaw
       .drop("gene_description", "probe_set_id")
-      .withColumn("index", monotonicallyIncreasingId.cast("integer"))
+      .withColumn("index",row_number().over(Window.orderBy(lit(1))))
       .withColumnRenamed("gene_id", "id")
       .withColumn("entrezid", typedLit(Option.empty[Set[String]]))
       .withColumn("ensemblid", typedLit(Option.empty[Set[String]]))