Properly fix and regenerate generated code

Author: srowen

mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala

@@ -206,6 +206,7 @@ abstract class ProbabilisticClassificationModel[
       var i = 0
       val probabilitySize = probability.size
       while (i < probabilitySize) {
+        // thresholds are all > 0
         val scaled = probability(i) / thresholds(i)
         if (scaled > max) {
           max = scaled

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

@@ -53,7 +53,7 @@ private[shared] object SharedParamsCodeGen {
         " Array must have length equal to the number of classes, with values > 0." +
         " The class with largest value p/t is predicted, where p is the original probability" +
         " of that class and t is the class's threshold",
-        isValid = "(t: Array[Double]) => t.forall(_ >= 0)", finalMethods = false),
+        isValid = "(t: Array[Double]) => t.forall(_ > 0)", finalMethods = false),
       ParamDesc[String]("inputCol", "input column name"),
       ParamDesc[Array[String]]("inputCols", "input column names"),
       ParamDesc[String]("outputCol", "output column name", Some("uid + \"__output\"")),

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

@@ -176,24 +176,10 @@ private[ml] trait HasThreshold extends Params {
 private[ml] trait HasThresholds extends Params {
 
   /**
-   * Defines "thresholds" for each class. These do not, actually, define the minimum
-   * probability per class for that class to be chosen. They act like like 'cutoff' values in
-   * R's [[https://cran.r-project.org/web/packages/randomForest/randomForest.pdf randomForest]]
-   * package, which ironically are also not cutoffs. That is, a class may be selected even if its
-   * probability does not exceed the threshold.
-   *
-   * Array must have length equal to the number of classes, with values > 0.
-   * The class with largest value p/t is predicted, where p is the original probability of that
-   * class and t is the class's threshold.
-   *
+   * Param for Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class's threshold.
    * @group param
    */
-  final val thresholds: DoubleArrayParam = new DoubleArrayParam(this, "thresholds",
-    "Thresholds in multi-class classification to adjust the probability of predicting each class. " +
-    "Array must have length equal to the number of classes, with values > 0. " +
-    "The class with largest value p/t is predicted, where p is the original probability of that " +
-    "class and t is the class's threshold",
-    (t: Array[Double]) => t.forall(_ > 0.0))
+  final val thresholds: DoubleArrayParam = new DoubleArrayParam(this, "thresholds", "Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class's threshold", (t: Array[Double]) => t.forall(_ > 0))
 
   /** @group getParam */
   def getThresholds: Array[Double] = $(thresholds)

python/pyspark/ml/param/shared.py

@@ -472,7 +472,7 @@ class HasThresholds(Params):
     Mixin for param thresholds: Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class's threshold.
     """
 
-    thresholds = Param(Params._dummy(), "thresholds","Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class's threshold.", typeConverter=TypeConverters.toListFloat)
+    thresholds = Param(Params._dummy(), "thresholds", "Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class's threshold.", typeConverter=TypeConverters.toListFloat)
 
     def __init__(self):
         super(HasThresholds, self).__init__()