set job desc with algorithm name (#97)

Author: Nicole00

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/BetweennessCentralityAlgo.scala

@@ -28,6 +28,7 @@ object BetweennessCentralityAlgo {
             dataset: Dataset[Row],
             betweennessConfig: BetweennessConfig,
             hasWeight: Boolean): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
 
     var encodeIdDf: DataFrame = null
 

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/BfsAlgo.scala

@@ -25,6 +25,8 @@ object BfsAlgo {
     * run the louvain algorithm for nebula graph
     */
   def apply(spark: SparkSession, dataset: Dataset[Row], bfsConfig: BfsConfig): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
+
     var encodeIdDf: DataFrame = null
     var finalRoot: Long       = 0
 

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/ClosenessAlgo.scala

@@ -35,6 +35,8 @@ object ClosenessAlgo {
     * run the Closeness algorithm for nebula graph
     */
   def apply(spark: SparkSession, dataset: Dataset[Row], hasWeight: Boolean): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
+
     val graph: Graph[None.type, Double] = NebulaUtil.loadInitGraph(dataset, hasWeight)
     val closenessRDD                    = execute(graph)
     val schema = StructType(

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/ClusteringCoefficientAlgo.scala

@@ -24,6 +24,7 @@ object ClusteringCoefficientAlgo {
   def apply(spark: SparkSession,
             dataset: Dataset[Row],
             coefficientConfig: CoefficientConfig): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
 
     var encodeIdDf: DataFrame = null
 

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/ConnectedComponentsAlgo.scala

@@ -10,7 +10,6 @@ import com.vesoft.nebula.algorithm.utils.{DecodeUtil, NebulaUtil}
 import org.apache.log4j.Logger
 import org.apache.spark.graphx.{Graph, VertexId, VertexRDD}
 import org.apache.spark.rdd.RDD
-import com.vesoft.nebula.algorithm.utils.NebulaUtil
 import org.apache.spark.graphx.lib.ConnectedComponents
 import org.apache.spark.sql.types.{DoubleType, LongType, StructField, StructType}
 import org.apache.spark.sql.{DataFrame, Dataset, Row, SparkSession}
@@ -27,6 +26,7 @@ object ConnectedComponentsAlgo {
             dataset: Dataset[Row],
             ccConfig: CcConfig,
             hasWeight: Boolean): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
 
     var encodeIdDf: DataFrame = null
 

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/DegreeStaticAlgo.scala

@@ -25,6 +25,8 @@ object DegreeStaticAlgo {
   def apply(spark: SparkSession,
             dataset: Dataset[Row],
             degreeConfig: DegreeStaticConfig = new DegreeStaticConfig): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
+
     var encodeIdDf: DataFrame = null
 
     val graph: Graph[None.type, Double] = if (degreeConfig.encodeId) {

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/DfsAlgo.scala

@@ -22,8 +22,11 @@ import scala.collection.mutable
 
 object DfsAlgo {
   var iterNums = 0
+  val ALGORITHM = "dfs"
 
   def apply(spark: SparkSession, dataset: Dataset[Row], dfsConfig: DfsConfig): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
+
     var encodeIdDf: DataFrame = null
     var finalRoot: Long       = 0
 

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/GraphTriangleCountAlgo.scala

@@ -13,8 +13,10 @@ import org.apache.spark.sql.types.{IntegerType, LongType, StructField, StructTyp
   *  compute all graph's triangle count
   */
 object GraphTriangleCountAlgo {
+  val ALGORITHM = "graphTriangleCount"
 
   def apply(spark: SparkSession, dataset: Dataset[Row]): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
 
     val triangleCount = TriangleCountAlgo(spark, dataset)
     val count = triangleCount

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/HanpAlgo.scala

@@ -28,6 +28,7 @@ object HanpAlgo {
             hanpConfig: HanpConfig,
             hasWeight: Boolean,
             preferences: RDD[(VertexId, Double)] = null): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
 
     var encodeIdDf: DataFrame = null
 

nebula-algorithm/src/main/scala/com/vesoft/nebula/algorithm/lib/JaccardAlgo.scala

@@ -6,15 +6,11 @@
 package com.vesoft.nebula.algorithm.lib
 
 import com.vesoft.nebula.algorithm.config.JaccardConfig
+import com.vesoft.nebula.algorithm.lib.HanpAlgo.ALGORITHM
 import com.vesoft.nebula.algorithm.utils.{DecodeUtil, NebulaUtil}
 import org.apache.log4j.Logger
 import org.apache.spark.graphx.Graph
-import org.apache.spark.ml.feature.{
-  CountVectorizer,
-  CountVectorizerModel,
-  MinHashLSH,
-  MinHashLSHModel
-}
+import org.apache.spark.ml.feature.{CountVectorizer, CountVectorizerModel, MinHashLSH, MinHashLSHModel}
 import org.apache.spark.ml.linalg.SparseVector
 import org.apache.spark.rdd.RDD
 import org.apache.spark.sql.{DataFrame, Dataset, Row, SparkSession}
@@ -30,6 +26,7 @@ object JaccardAlgo {
     * run the Jaccard algorithm for nebula graph
     */
   def apply(spark: SparkSession, dataset: Dataset[Row], jaccardConfig: JaccardConfig): DataFrame = {
+    spark.sparkContext.setJobGroup(ALGORITHM, s"Running $ALGORITHM")
 
     var encodeIdDf: DataFrame = null
     var data: DataFrame       = dataset