update

Author: WeichenXu123

mllib/src/main/scala/org/apache/spark/ml/optim/WeightedLeastSquares.scala

@@ -440,7 +440,7 @@ private[ml] object WeightedLeastSquares {
     /**
      * Weighted population standard deviation of labels.
      */
-    def bStd: Double = math.sqrt(bbSum / wSum - bBar * bBar)
+    def bStd: Double = math.sqrt(math.max(bbSum / wSum - bBar * bBar, 0.0))
 
     /**
      * Weighted mean of (label * features).

mllib/src/main/scala/org/apache/spark/ml/stat/Summarizer.scala

@@ -436,12 +436,8 @@ private[ml] object SummaryBuilderImpl extends Logging {
         var i = 0
         val len = currM2n.length
         while (i < len) {
-          realVariance(i) = (currM2n(i) + deltaMean(i) * deltaMean(i) * weightSum(i) *
-            (totalWeightSum - weightSum(i)) / totalWeightSum) / denominator
-          // Because of numerical error, it is possible to get negative real variance
-          if (realVariance(i) < 0.0) {
-            realVariance(i) = 0.0
-          }
+          realVariance(i) = math.max((currM2n(i) + deltaMean(i) * deltaMean(i) * weightSum(i) *
+            (totalWeightSum - weightSum(i)) / totalWeightSum) / denominator, 0.0)
           i += 1
         }
       }

mllib/src/main/scala/org/apache/spark/mllib/stat/MultivariateOnlineSummarizer.scala

@@ -213,12 +213,8 @@ class MultivariateOnlineSummarizer extends MultivariateStatisticalSummary with S
       var i = 0
       val len = currM2n.length
       while (i < len) {
-        realVariance(i) = (currM2n(i) + deltaMean(i) * deltaMean(i) * weightSum(i) *
-          (totalWeightSum - weightSum(i)) / totalWeightSum) / denominator
-        // Because of numerical error, it is possible to get negative real variance
-        if (realVariance(i) < 0.0) {
-          realVariance(i) = 0.0
-        }
+        realVariance(i) = math.max((currM2n(i) + deltaMean(i) * deltaMean(i) * weightSum(i) *
+          (totalWeightSum - weightSum(i)) / totalWeightSum) / denominator, 0.0)
         i += 1
       }
     }