[MINOR] Fix typos in comments and testcase name of code

## What changes were proposed in this pull request?

This PR fixes typos in comments and testcase name of code.

## How was this patch tested?

manual.

Author: Dongjoon Hyun <dongjoon@apache.org>

Closes #11481 from dongjoon-hyun/minor_fix_typos_in_code.

core/src/main/scala/org/apache/spark/ui/ConsoleProgressBar.scala

@@ -28,7 +28,7 @@ import org.apache.spark._
  * of them will be combined together, showed in one line.
  */
 private[spark] class ConsoleProgressBar(sc: SparkContext) extends Logging {
-  // Carrige return
+  // Carriage return
   val CR = '\r'
   // Update period of progress bar, in milliseconds
   val UPDATE_PERIOD = 200L

core/src/test/scala/org/apache/sparktest/ImplicitSuite.scala

@@ -26,11 +26,11 @@ package org.apache.sparktest
  */
 class ImplicitSuite {
 
-  // We only want to test if `implict` works well with the compiler, so we don't need a real
+  // We only want to test if `implicit` works well with the compiler, so we don't need a real
   // SparkContext.
   def mockSparkContext[T]: org.apache.spark.SparkContext = null
 
-  // We only want to test if `implict` works well with the compiler, so we don't need a real RDD.
+  // We only want to test if `implicit` works well with the compiler, so we don't need a real RDD.
   def mockRDD[T]: org.apache.spark.rdd.RDD[T] = null
 
   def testRddToPairRDDFunctions(): Unit = {

dev/run-tests.py

@@ -563,7 +563,7 @@ def main():
 
     # backwards compatibility checks
     if build_tool == "sbt":
-        # Note: compatiblity tests only supported in sbt for now
+        # Note: compatibility tests only supported in sbt for now
         detect_binary_inop_with_mima()
 
     # run the test suites

examples/src/main/java/org/apache/spark/examples/ml/JavaDeveloperApiExample.java

@@ -228,7 +228,7 @@ public Vector predictRaw(Vector features) {
    * Create a copy of the model.
    * The copy is shallow, except for the embedded paramMap, which gets a deep copy.
    * <p>
-   * This is used for the defaul implementation of [[transform()]].
+   * This is used for the default implementation of [[transform()]].
    *
    * In Java, we have to make this method public since Java does not understand Scala's protected
    * modifier.

examples/src/main/python/mllib/naive_bayes_example.py

@@ -47,7 +47,7 @@ def parseLine(line):
     # $example on$
     data = sc.textFile('data/mllib/sample_naive_bayes_data.txt').map(parseLine)
 
-    # Split data aproximately into training (60%) and test (40%)
+    # Split data approximately into training (60%) and test (40%)
     training, test = data.randomSplit([0.6, 0.4], seed=0)
 
     # Train a naive Bayes model.

examples/src/main/python/mllib/ranking_metrics_example.py

@@ -47,7 +47,7 @@ def parseLine(line):
     # Instantiate regression metrics to compare predicted and actual ratings
     metrics = RegressionMetrics(scoreAndLabels)
 
-    # Root mean sqaured error
+    # Root mean squared error
     print("RMSE = %s" % metrics.rootMeanSquaredError)
 
     # R-squared

examples/src/main/python/mllib/word2vec.py

@@ -16,7 +16,7 @@
 #
 
 # This example uses text8 file from http://mattmahoney.net/dc/text8.zip
-# The file was downloadded, unziped and split into multiple lines using
+# The file was downloaded, unzipped and split into multiple lines using
 #
 # wget http://mattmahoney.net/dc/text8.zip
 # unzip text8.zip

examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala

@@ -30,7 +30,7 @@ import breeze.linalg.{DenseVector, Vector}
  * org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS based on your needs.
  */
 object LocalFileLR {
-  val D = 10   // Numer of dimensions
+  val D = 10   // Number of dimensions
   val rand = new Random(42)
 
   case class DataPoint(x: Vector[Double], y: Double)

examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala

@@ -35,7 +35,7 @@ import org.apache.spark._
  * org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS based on your needs.
  */
 object SparkHdfsLR {
-  val D = 10   // Numer of dimensions
+  val D = 10   // Number of dimensions
   val rand = new Random(42)
 
   case class DataPoint(x: Vector[Double], y: Double)

examples/src/main/scala/org/apache/spark/examples/SparkLR.scala

@@ -36,7 +36,7 @@ import org.apache.spark._
  */
 object SparkLR {
   val N = 10000  // Number of data points
-  val D = 10   // Numer of dimensions
+  val D = 10   // Number of dimensions
   val R = 0.7  // Scaling factor
   val ITERATIONS = 5
   val rand = new Random(42)

examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala

@@ -60,10 +60,10 @@ object RDDRelation {
     // Write out an RDD as a parquet file with overwrite mode.
     df.write.mode(SaveMode.Overwrite).parquet("pair.parquet")
 
-    // Read in parquet file.  Parquet files are self-describing so the schmema is preserved.
+    // Read in parquet file.  Parquet files are self-describing so the schema is preserved.
     val parquetFile = sqlContext.read.parquet("pair.parquet")
 
-    // Queries can be run using the DSL on parequet files just like the original RDD.
+    // Queries can be run using the DSL on parquet files just like the original RDD.
     parquetFile.where($"key" === 1).select($"value".as("a")).collect().foreach(println)
 
     // These files can also be registered as tables.

examples/src/main/scala/org/apache/spark/examples/streaming/TwitterPopularTags.scala

@@ -44,7 +44,7 @@ object TwitterPopularTags {
     val filters = args.takeRight(args.length - 4)
 
     // Set the system properties so that Twitter4j library used by twitter stream
-    // can use them to generat OAuth credentials
+    // can use them to generate OAuth credentials
     System.setProperty("twitter4j.oauth.consumerKey", consumerKey)
     System.setProperty("twitter4j.oauth.consumerSecret", consumerSecret)
     System.setProperty("twitter4j.oauth.accessToken", accessToken)

graphx/src/test/scala/org/apache/spark/graphx/EdgeSuite.scala

@@ -21,7 +21,7 @@ import org.apache.spark.SparkFunSuite
 
 class EdgeSuite extends SparkFunSuite {
   test ("compare") {
-    // decending order
+    // descending order
     val testEdges: Array[Edge[Int]] = Array(
       Edge(0x7FEDCBA987654321L, -0x7FEDCBA987654321L, 1),
       Edge(0x2345L, 0x1234L, 1),

mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala

@@ -541,7 +541,7 @@ object PrefixSpan extends Logging {
   }
 
   /**
-   * Represents a frequence sequence.
+   * Represents a frequent sequence.
    * @param sequence a sequence of itemsets stored as an Array of Arrays
    * @param freq frequency
    * @tparam Item item type

project/SparkBuild.scala

@@ -688,7 +688,7 @@ object Unidoc {
       "-noqualifier", "java.lang"
     ),
 
-    // Use GitHub repository for Scaladoc source linke
+    // Use GitHub repository for Scaladoc source links
     unidocSourceBase := s"https://github.com/apache/spark/tree/v${version.value}",
 
     scalacOptions in (ScalaUnidoc, unidoc) ++= Seq(

python/pyspark/mllib/fpm.py

@@ -127,7 +127,7 @@ class PrefixSpanModel(JavaModelWrapper):
 
     @since("1.6.0")
     def freqSequences(self):
-        """Gets frequence sequences"""
+        """Gets frequent sequences"""
         return self.call("getFreqSequences").map(lambda x: PrefixSpan.FreqSequence(x[0], x[1]))
 
 

repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkIMain.scala

@@ -72,7 +72,7 @@ import org.apache.spark.annotation.DeveloperApi
    *  all variables defined by that code.  To extract the result of an
    *  interpreted line to show the user, a second "result object" is created
    *  which imports the variables exported by the above object and then
-   *  exports members called "$eval" and "$print". To accomodate user expressions
+   *  exports members called "$eval" and "$print". To accommodate user expressions
    *  that read from variables or methods defined in previous statements, "import"
    *  statements are used.
    *
@@ -1515,7 +1515,7 @@ import org.apache.spark.annotation.DeveloperApi
     exprTyper.symbolOfLine(code)
 
   /**
-   * Constucts type information based on the provided expression's final
+   * Constructs type information based on the provided expression's final
    * result or the definition provided.
    *
    * @param expr The expression or definition

sql/core/src/main/scala/org/apache/spark/sql/jdbc/OracleDialect.scala

@@ -29,7 +29,7 @@ private case object OracleDialect extends JdbcDialect {
   override def getCatalystType(
       sqlType: Int, typeName: String, size: Int, md: MetadataBuilder): Option[DataType] = {
     // Handle NUMBER fields that have no precision/scale in special way
-    // because JDBC ResultSetMetaData converts this to 0 procision and -127 scale
+    // because JDBC ResultSetMetaData converts this to 0 precision and -127 scale
     // For more details, please see
     // https://github.com/apache/spark/pull/8780#issuecomment-145598968
     // and

sql/core/src/test/scala/org/apache/spark/sql/streaming/OffsetSuite.scala

@@ -23,7 +23,7 @@ import org.apache.spark.sql.execution.streaming.{CompositeOffset, LongOffset, Of
 trait OffsetSuite extends SparkFunSuite {
   /** Creates test to check all the comparisons of offsets given a `one` that is less than `two`. */
   def compare(one: Offset, two: Offset): Unit = {
-    test(s"comparision $one <=> $two") {
+    test(s"comparison $one <=> $two") {
       assert(one < two)
       assert(one <= two)
       assert(one <= one)