2 files changed, 29 insertions, 2 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
index 1f4cca1233..769f4406e2 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
@@ -103,6 +103,13 @@ final class QuantileDiscretizer(override val uid: String)
 
 @Since("1.6.0")
 object QuantileDiscretizer extends DefaultParamsReadable[QuantileDiscretizer] with Logging {
+
+  /**
+   * Minimum number of samples required for finding splits, regardless of number of bins.  If
+   * the dataset has fewer rows than this value, the entire dataset will be used.
+   */
+  private[spark] val minSamplesRequired: Int = 10000
+
   /**
    * Sampling from the given dataset to collect quantile statistics.
    */
@@ -110,8 +117,8 @@ object QuantileDiscretizer extends DefaultParamsReadable[QuantileDiscretizer] wi
     val totalSamples = dataset.count()
     require(totalSamples > 0,
       "QuantileDiscretizer requires non-empty input dataset but was given an empty input.")
-    val requiredSamples = math.max(numBins * numBins, 10000)
-    val fraction = math.min(requiredSamples / dataset.count(), 1.0)
+    val requiredSamples = math.max(numBins * numBins, minSamplesRequired)
+    val fraction = math.min(requiredSamples.toDouble / dataset.count(), 1.0)
     dataset.sample(withReplacement = false, fraction, new XORShiftRandom(seed).nextInt()).collect()
   }
 
diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
index 6a2c601bbe..25fabf64d5 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/feature/QuantileDiscretizerSuite.scala
@@ -71,6 +71,26 @@ class QuantileDiscretizerSuite
     }
   }
 
+  test("Test splits on dataset larger than minSamplesRequired") {
+    val sqlCtx = SQLContext.getOrCreate(sc)
+    import sqlCtx.implicits._
+
+    val datasetSize = QuantileDiscretizer.minSamplesRequired + 1
+    val numBuckets = 5
+    val df = sc.parallelize((1.0 to datasetSize by 1.0).map(Tuple1.apply)).toDF("input")
+    val discretizer = new QuantileDiscretizer()
+      .setInputCol("input")
+      .setOutputCol("result")
+      .setNumBuckets(numBuckets)
+      .setSeed(1)
+
+    val result = discretizer.fit(df).transform(df)
+    val observedNumBuckets = result.select("result").distinct.count
+
+    assert(observedNumBuckets === numBuckets,
+      "Observed number of buckets does not equal expected number of buckets.")
+  }
+
   test("read/write") {
     val t = new QuantileDiscretizer()
       .setInputCol("myInputCol")