1. set initmode to Random (Intel-bigdata#655)

2. add initmode as an adjustable parameter to kmeans.conf and run.sh Signed-off-by: minmingz <[email protected]>
henrque · Dec 9, 2020 · 5b240b4 · 5b240b4
1 parent f55862a
commit 5b240b4
Show file tree

Hide file tree

Showing 4 changed files with 4 additions and 2 deletions.
diff --git a/bin/functions/hibench_prop_env_mapping.py b/bin/functions/hibench_prop_env_mapping.py
@@ -94,6 +94,7 @@
     MAX_ITERATION="hibench.kmeans.max_iteration",
     K="hibench.kmeans.k",
     K_STORAGE_LEVEL="hibench.kmeans.storage.level",
+    K_INIT_MODE="hibench.kmeans.initializationmode",
     # For gmm
     INPUT_SAMPLE_GMM="hibench.gmm.input.sample",
     INPUT_CLUSTER_GMM="hibench.gmm.input.cluster",

diff --git a/bin/workloads/ml/kmeans/spark/run.sh b/bin/workloads/ml/kmeans/spark/run.sh
@@ -28,7 +28,7 @@ rmr_hdfs $OUTPUT_HDFS || true
 SIZE=`dir_size $INPUT_HDFS`
 START_TIME=`timestamp`
 
-run_spark_job com.intel.hibench.sparkbench.ml.DenseKMeans -k $K --numIterations $MAX_ITERATION --storageLevel $K_STORAGE_LEVEL $INPUT_HDFS/samples
+run_spark_job com.intel.hibench.sparkbench.ml.DenseKMeans -k $K --numIterations $MAX_ITERATION --storageLevel $K_STORAGE_LEVEL --initMode $K_INIT_MODE $INPUT_HDFS/samples
 END_TIME=`timestamp`
 
 gen_report ${START_TIME} ${END_TIME} ${SIZE}

diff --git a/conf/workloads/ml/kmeans.conf b/conf/workloads/ml/kmeans.conf
@@ -49,3 +49,4 @@ hibench.workload.input			${hibench.hdfs.data.dir}/Kmeans/Input
 hibench.workload.output			${hibench.hdfs.data.dir}/Kmeans/Output
 
 hibench.kmeans.storage.level			MEMORY_ONLY
+hibench.kmeans.initializationmode Random
diff --git a/sparkbench/ml/src/main/scala/com/intel/sparkbench/ml/DenseKMeans.scala b/sparkbench/ml/src/main/scala/com/intel/sparkbench/ml/DenseKMeans.scala
@@ -39,7 +39,7 @@ object DenseKMeans {
       k: Int = -1,
       numIterations: Int = 10,
       storageLevel: String= "MEMORY_ONLY",
-      initializationMode: InitializationMode = Parallel)
+      initializationMode: InitializationMode = Random)
 
   def main(args: Array[String]) {
     val defaultParams = Params()
Original file line number	Diff line number	Diff line change
Expand Up		@@ -49,3 +49,4 @@ hibench.workload.input ${hibench.hdfs.data.dir}/Kmeans/Input
		hibench.workload.output ${hibench.hdfs.data.dir}/Kmeans/Output

		hibench.kmeans.storage.level MEMORY_ONLY
		hibench.kmeans.initializationmode Random