[MINOR] Fix Typos 'an -> a'

## What changes were proposed in this pull request?

`an -> a`

Use cmds like `find . -name '*.R' | xargs -i sh -c "grep -in ' an [^aeiou]' {} && echo {}"` to generate candidates, and review them one by one.

## How was this patch tested?
manual tests

Author: Zheng RuiFeng <ruifengz@foxmail.com>

Closes #13515 from zhengruifeng/an_a.

9 files changed, 10 insertions, 10 deletions

diff --git a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala
index b02aea92b7..25e56d70c2 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala
@@ -82,7 +82,7 @@ abstract class PipelineStage extends Params with Logging {
  * be called on the input dataset to fit a model. Then the model, which is a transformer, will be
  * used to transform the dataset as the input to the next stage. If a stage is a [[Transformer]],
  * its [[Transformer#transform]] method will be called to produce the dataset for the next stage.
- * The fitted model from a [[Pipeline]] is an [[PipelineModel]], which consists of fitted models and
+ * The fitted model from a [[Pipeline]] is a [[PipelineModel]], which consists of fitted models and
  * transformers, corresponding to the pipeline stages. If there are no stages, the pipeline acts as
  * an identity transformer.
  */
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
index cecf3c43df..1ea4d90e16 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
@@ -854,7 +854,7 @@ class BinaryLogisticRegressionSummary private[classification] (
 
   /**
    * Returns the receiver operating characteristic (ROC) curve,
-   * which is an Dataframe having two fields (FPR, TPR)
+   * which is a Dataframe having two fields (FPR, TPR)
    * with (0.0, 0.0) prepended and (1.0, 1.0) appended to it.
    *
    * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]].
@@ -874,7 +874,7 @@ class BinaryLogisticRegressionSummary private[classification] (
   lazy val areaUnderROC: Double = binaryMetrics.areaUnderROC()
 
   /**
-   * Returns the precision-recall curve, which is an Dataframe containing
+   * Returns the precision-recall curve, which is a Dataframe containing
    * two fields recall, precision with (0.0, 1.0) prepended to it.
    *
    * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]].
diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala
index be3792eb77..71c8c42ce5 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala
@@ -491,7 +491,7 @@ private[spark] object RandomForest extends Logging {
     timer.start("chooseSplits")
 
     // In each partition, iterate all instances and compute aggregate stats for each node,
-    // yield an (nodeIndex, nodeAggregateStats) pair for each node.
+    // yield a (nodeIndex, nodeAggregateStats) pair for each node.
     // After a `reduceByKey` operation,
     // stats of a node will be shuffled to a particular partition and be combined together,
     // then best splits for nodes are found there.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
index e4cc784cfe..e4cbf5acbc 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
@@ -86,7 +86,7 @@ class LogisticRegressionModel @Since("1.3.0") (
   /**
    * Sets the threshold that separates positive predictions from negative predictions
    * in Binary Logistic Regression. An example with prediction score greater than or equal to
-   * this threshold is identified as an positive, and negative otherwise. The default value is 0.5.
+   * this threshold is identified as a positive, and negative otherwise. The default value is 0.5.
    * It is only used for binary classification.
    */
   @Since("1.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala
index 783c1c835b..7c3ccbb40b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala
@@ -44,7 +44,7 @@ class SVMModel @Since("1.1.0") (
 
   /**
    * Sets the threshold that separates positive predictions from negative predictions. An example
-   * with prediction score greater than or equal to this threshold is identified as an positive,
+   * with prediction score greater than or equal to this threshold is identified as a positive,
    * and negative otherwise. The default value is 0.0.
    */
   @Since("1.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
index ca7385128d..9db725097a 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
@@ -53,7 +53,7 @@ trait VectorTransformer extends Serializable {
   }
 
   /**
-   * Applies transformation on an JavaRDD[Vector].
+   * Applies transformation on a JavaRDD[Vector].
    *
    * @param data JavaRDD[Vector] to be transformed.
    * @return transformed JavaRDD[Vector].
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
index 02fd60da7d..91f065831c 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
@@ -731,7 +731,7 @@ object DenseVector {
 }
 
 /**
- * A sparse vector represented by an index array and an value array.
+ * A sparse vector represented by an index array and a value array.
  *
  * @param size size of the vector.
  * @param indices index array, assume to be strictly increasing.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
index 97b03b340f..008b03d1cc 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
@@ -24,7 +24,7 @@ import org.apache.spark.mllib.linalg.{Matrix, SparseMatrix, Vectors}
 import org.apache.spark.rdd.RDD
 
 /**
- * Represents an entry in an distributed matrix.
+ * Represents an entry in a distributed matrix.
  * @param i row index
  * @param j column index
  * @param value value of the entry
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/rdd/MLPairRDDFunctions.scala b/mllib/src/main/scala/org/apache/spark/mllib/rdd/MLPairRDDFunctions.scala
index af4bc9f290..e28e1af5b0 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/rdd/MLPairRDDFunctions.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/rdd/MLPairRDDFunctions.scala
@@ -47,7 +47,7 @@ class MLPairRDDFunctions[K: ClassTag, V: ClassTag](self: RDD[(K, V)]) extends Se
       combOp = (queue1, queue2) => {
         queue1 ++= queue2
       }
-    ).mapValues(_.toArray.sorted(ord.reverse))  // This is an min-heap, so we reverse the order.
+    ).mapValues(_.toArray.sorted(ord.reverse))  // This is a min-heap, so we reverse the order.
   }
 }