[MINOR] Fix Typos 'a -> an'

## What changes were proposed in this pull request?

`a` -> `an`

I use regex to generate potential error lines:
`grep -in ' a [aeiou]' mllib/src/main/scala/org/apache/spark/ml/*/*scala`
and review them line by line.

## How was this patch tested?

local build
`lint-java` checking

Author: Zheng RuiFeng <ruifengz@foxmail.com>

Closes #13317 from zhengruifeng/a_an.

5 files changed, 7 insertions, 7 deletions

diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py
index 43d9072a24..705022934e 100644
--- a/python/pyspark/mllib/regression.py
+++ b/python/pyspark/mllib/regression.py
@@ -648,7 +648,7 @@ class IsotonicRegressionModel(Saveable, Loader):
 
     @since("1.4.0")
     def save(self, sc, path):
-        """Save a IsotonicRegressionModel."""
+        """Save an IsotonicRegressionModel."""
         java_boundaries = _py2java(sc, self.boundaries.tolist())
         java_predictions = _py2java(sc, self.predictions.tolist())
         java_model = sc._jvm.org.apache.spark.mllib.regression.IsotonicRegressionModel(
@@ -658,7 +658,7 @@ class IsotonicRegressionModel(Saveable, Loader):
     @classmethod
     @since("1.4.0")
     def load(cls, sc, path):
-        """Load a IsotonicRegressionModel."""
+        """Load an IsotonicRegressionModel."""
         java_model = sc._jvm.org.apache.spark.mllib.regression.IsotonicRegressionModel.load(
             sc._jsc.sc(), path)
         py_boundaries = _java2py(sc, java_model.boundaryVector()).toArray()
@@ -694,7 +694,7 @@ class IsotonicRegression(object):
     @since("1.4.0")
     def train(cls, data, isotonic=True):
         """
-        Train a isotonic regression model on the given data.
+        Train an isotonic regression model on the given data.
 
         :param data:
           RDD of (label, feature, weight) tuples.
diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py
index 64b8bc442d..15cefc8cf1 100644
--- a/python/pyspark/sql/functions.py
+++ b/python/pyspark/sql/functions.py
@@ -1177,7 +1177,7 @@ def sha2(col, numBits):
 
 @since(2.0)
 def hash(*cols):
-    """Calculates the hash code of given columns, and returns the result as a int column.
+    """Calculates the hash code of given columns, and returns the result as an int column.
 
     >>> spark.createDataFrame([('ABC',)], ['a']).select(hash('a').alias('hash')).collect()
     [Row(hash=-757602832)]
diff --git a/python/pyspark/sql/readwriter.py b/python/pyspark/sql/readwriter.py
index 73d2b81b6b..13d21d7143 100644
--- a/python/pyspark/sql/readwriter.py
+++ b/python/pyspark/sql/readwriter.py
@@ -847,7 +847,7 @@ class DataFrameWriter(object):
 
     @since(1.4)
     def jdbc(self, url, table, mode=None, properties=None):
-        """Saves the content of the :class:`DataFrame` to a external database table via JDBC.
+        """Saves the content of the :class:`DataFrame` to an external database table via JDBC.
 
         .. note:: Don't create too many partitions in parallel on a large cluster; \
         otherwise Spark might crash your external database systems.
diff --git a/python/pyspark/streaming/dstream.py b/python/pyspark/streaming/dstream.py
index 67a0819601..fb6c66f2df 100644
--- a/python/pyspark/streaming/dstream.py
+++ b/python/pyspark/streaming/dstream.py
@@ -623,7 +623,7 @@ class TransformedDStream(DStream):
         self._jdstream_val = None
 
         # Using type() to avoid folding the functions and compacting the DStreams which is not
-        # not strictly a object of TransformedDStream.
+        # not strictly an object of TransformedDStream.
         # Changed here is to avoid bug in KafkaTransformedDStream when calling offsetRanges().
         if (type(prev) is TransformedDStream and
                 not prev.is_cached and not prev.is_checkpointed):
diff --git a/python/pyspark/streaming/kafka.py b/python/pyspark/streaming/kafka.py
index 015ca77dbf..2c1a667fc8 100644
--- a/python/pyspark/streaming/kafka.py
+++ b/python/pyspark/streaming/kafka.py
@@ -228,7 +228,7 @@ class OffsetRange(object):
 
     def __init__(self, topic, partition, fromOffset, untilOffset):
         """
-        Create a OffsetRange to represent  range of offsets
+        Create an OffsetRange to represent range of offsets
         :param topic: Kafka topic name.
         :param partition: Kafka partition id.
         :param fromOffset: Inclusive starting offset.