change the form of arguments of GBT to OptionParser

Author: jtengyp

bin/functions/hibench_prop_env_mapping.py

@@ -115,7 +115,11 @@
     # For Gradient Boosting Tree
     NUM_EXAMPLES_GBT="hibench.gbt.examples",
     NUM_FEATURES_GBT="hibench.gbt.features",
+    NUM_CLASSES_GBT="hibench.gbt.numClasses",
+    MAX_DEPTH_GBT="hibench.gbt.maxDepth",
+    MAX_BINS_GBT="hibench.gbt.maxBins",
     NUM_ITERATIONS_GBT="hibench.gbt.numIterations",
+    LEARNING_RATE_GBT="hibench.gbt.learningRate",
     # For Random Forest
     NUM_EXAMPLES_RF="hibench.rf.examples",
     NUM_FEATURES_RF="hibench.rf.features",

bin/workloads/ml/gbt/spark/run.sh

@@ -26,7 +26,7 @@ rmr_hdfs $OUTPUT_HDFS || true
 
 SIZE=`dir_size $INPUT_HDFS`
 START_TIME=`timestamp`
-run_spark_job com.intel.hibench.sparkbench.ml.GradientBoostedTree ${INPUT_HDFS} ${NUM_ITERATIONS_GBT}
+run_spark_job com.intel.hibench.sparkbench.ml.GradientBoostedTree --numClasses $NUM_CLASSES_GBT --maxDepth $MAX_DEPTH_GBT --maxBins $MAX_BINS_GBT --numIterations $NUM_ITERATIONS_GBT --learningRate $LEARNING_RATE_GBT $INPUT_HDFS
 END_TIME=`timestamp`
 
 gen_report ${START_TIME} ${END_TIME} ${SIZE}

sparkbench/ml/src/main/scala/com/intel/sparkbench/ml/GradientBoostedTree.scala

@@ -60,10 +60,10 @@ object GradientBoostedTree {
       arg[String]("<dataPath>")
         .required()
         .text("data path for Gradient Boosted Tree")
-        .action((xc) => c.copy(dataPath = x))
+        .action((x,c) => c.copy(dataPath = x))
     }
     parser.parse(args, defaultParams) match {
-      case some(params) => run(params)
+      case Some(params) => run(params)
       case _ => sys.exit(1)
     }
   }

sparkbench/ml/src/main/scala/com/intel/sparkbench/ml/GradientBoostedTreeDataGenerator.scala

@@ -32,7 +32,7 @@ import org.apache.spark.rdd.RDD
  * Generate test data for Gradient Boosting Tree. This class chooses positive labels
  * with probability `probOne` and scales features for positive examples by `eps`.
  */
-object GradientBoostingTreeDataGenerator {
+object GradientBoostedTreeDataGenerator {
 
   /**
    * Generate an RDD containing test data for Gradient Boosting Tree.