Removed fixed random seeds from Word2Vec and ALS. Changed shared param HasSeed to have default based on hashCode of class name, instead of random number.

Author: jkbradley

mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala

@@ -68,7 +68,6 @@ private[feature] trait Word2VecBase extends Params
 
   setDefault(stepSize -> 0.025)
   setDefault(maxIter -> 1)
-  setDefault(seed -> 42L)
 
   /**
    * Validate and transform the input schema.

mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala

@@ -53,7 +53,7 @@ private[shared] object SharedParamsCodeGen {
       ParamDesc[Int]("checkpointInterval", "checkpoint interval (>= 1)",
         isValid = "ParamValidators.gtEq(1)"),
       ParamDesc[Boolean]("fitIntercept", "whether to fit an intercept term", Some("true")),
-      ParamDesc[Long]("seed", "random seed", Some("Utils.random.nextLong()")),
+      ParamDesc[Long]("seed", "random seed", Some("this.getClass.getName.hashCode.toLong")),
       ParamDesc[Double]("elasticNetParam", "the ElasticNet mixing parameter, in range [0, 1]." +
         " For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty.",
         isValid = "ParamValidators.inRange(0, 1)"),

mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala

@@ -232,7 +232,7 @@ private[ml] trait HasFitIntercept extends Params {
 }
 
 /**
- * (private[ml]) Trait for shared param seed (default: Utils.random.nextLong()).
+ * (private[ml]) Trait for shared param seed (default: this.getClass.getName.hashCode.toLong).
  */
 private[ml] trait HasSeed extends Params {
 
@@ -242,7 +242,7 @@ private[ml] trait HasSeed extends Params {
    */
   final val seed: LongParam = new LongParam(this, "seed", "random seed")
 
-  setDefault(seed, Utils.random.nextLong())
+  setDefault(seed, this.getClass.getName.hashCode.toLong)
 
   /** @group getParam */
   final def getSeed: Long = $(seed)

mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala

@@ -148,7 +148,7 @@ private[recommendation] trait ALSParams extends Params with HasMaxIter with HasR
 
   setDefault(rank -> 10, maxIter -> 10, regParam -> 0.1, numUserBlocks -> 10, numItemBlocks -> 10,
     implicitPrefs -> false, alpha -> 1.0, userCol -> "user", itemCol -> "item",
-    ratingCol -> "rating", nonnegative -> false, checkpointInterval -> 10, seed -> 0L)
+    ratingCol -> "rating", nonnegative -> false, checkpointInterval -> 10)
 
   /**
    * Validates and transforms the input schema.