Revert "[SPARK-17027][ML] Avoid integer overflow in PolynomialExpansion.getPolySize"

This reverts commit b54a586.

Author: srowen

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

@@ -19,8 +19,6 @@ package org.apache.spark.ml.feature
 
 import scala.collection.mutable
 
-import org.apache.commons.math3.util.CombinatoricsUtils
-
 import org.apache.spark.annotation.{Since, Experimental}
 import org.apache.spark.ml.UnaryTransformer
 import org.apache.spark.ml.param.{ParamMap, IntParam, ParamValidators}
@@ -82,12 +80,12 @@ class PolynomialExpansion(override val uid: String)
 @Since("1.6.0")
 object PolynomialExpansion extends DefaultParamsReadable[PolynomialExpansion] {
 
-  private def getPolySize(numFeatures: Int, degree: Int): Int = {
-    val n = CombinatoricsUtils.binomialCoefficient(numFeatures + degree, degree)
-    require(n <= Integer.MAX_VALUE)
-    n.toInt
+  private def choose(n: Int, k: Int): Int = {
+    Range(n, n - k, -1).product / Range(k, 1, -1).product
   }
 
+  private def getPolySize(numFeatures: Int, degree: Int): Int = choose(numFeatures + degree, degree)
+
   private def expandDense(
       values: Array[Double],
       lastIdx: Int,

mllib/src/test/scala/org/apache/spark/ml/feature/PolynomialExpansionSuite.scala

@@ -108,29 +108,5 @@ class PolynomialExpansionSuite
       .setDegree(3)
     testDefaultReadWrite(t)
   }
-
-  test("SPARK-17027. Integer overflow in PolynomialExpansion.getPolySize") {
-    val data: Array[(Vector, Int, Int)] = Array(
-      (Vectors.dense(1.0, 2.0, 3.0, 4.0, 5.0), 3002, 4367),
-      (Vectors.sparse(5, Seq((0, 1.0), (4, 5.0))), 3002, 4367),
-      (Vectors.dense(1.0, 2.0, 3.0, 4.0, 5.0, 6.0), 8007, 12375)
-    )
-
-    val df = spark.createDataFrame(data)
-      .toDF("features", "expectedPoly10size", "expectedPoly11size")
-
-    val t = new PolynomialExpansion()
-      .setInputCol("features")
-      .setOutputCol("polyFeatures")
-
-    for (i <- Seq(10, 11)) {
-      val transformed = t.setDegree(i)
-        .transform(df)
-        .select(s"expectedPoly${i}size", "polyFeatures")
-        .rdd.map { case Row(expected: Int, v: Vector) => expected == v.size }
-
-      assert(transformed.collect.forall(identity))
-    }
-  }
 }