[SPARK-12615] Remove some deprecated APIs in RDD/SparkContext

I looked at each case individually and it looks like they can all be removed. The only one that I had to think twice was toArray (I even thought about un-deprecating it, until I realized it was a problem in Java to have toArray returning java.util.List).

Author: Reynold Xin <rxin@databricks.com>

Closes #10569 from rxin/SPARK-12615.

3 files changed, 8 insertions, 17 deletions

diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java
index 980a9108af..779fac01c4 100644
--- a/examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java
+++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java
@@ -68,22 +68,22 @@ public class JavaBinaryClassificationMetricsExample {
 
     // Precision by threshold
     JavaRDD<Tuple2<Object, Object>> precision = metrics.precisionByThreshold().toJavaRDD();
-    System.out.println("Precision by threshold: " + precision.toArray());
+    System.out.println("Precision by threshold: " + precision.collect());
 
     // Recall by threshold
     JavaRDD<Tuple2<Object, Object>> recall = metrics.recallByThreshold().toJavaRDD();
-    System.out.println("Recall by threshold: " + recall.toArray());
+    System.out.println("Recall by threshold: " + recall.collect());
 
     // F Score by threshold
     JavaRDD<Tuple2<Object, Object>> f1Score = metrics.fMeasureByThreshold().toJavaRDD();
-    System.out.println("F1 Score by threshold: " + f1Score.toArray());
+    System.out.println("F1 Score by threshold: " + f1Score.collect());
 
     JavaRDD<Tuple2<Object, Object>> f2Score = metrics.fMeasureByThreshold(2.0).toJavaRDD();
-    System.out.println("F2 Score by threshold: " + f2Score.toArray());
+    System.out.println("F2 Score by threshold: " + f2Score.collect());
 
     // Precision-recall curve
     JavaRDD<Tuple2<Object, Object>> prc = metrics.pr().toJavaRDD();
-    System.out.println("Precision-recall curve: " + prc.toArray());
+    System.out.println("Precision-recall curve: " + prc.collect());
 
     // Thresholds
     JavaRDD<Double> thresholds = precision.map(
@@ -96,7 +96,7 @@ public class JavaBinaryClassificationMetricsExample {
 
     // ROC Curve
     JavaRDD<Tuple2<Object, Object>> roc = metrics.roc().toJavaRDD();
-    System.out.println("ROC curve: " + roc.toArray());
+    System.out.println("ROC curve: " + roc.collect());
 
     // AUPRC
     System.out.println("Area under precision-recall curve = " + metrics.areaUnderPR());
diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala b/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala
index 6c90dbec3d..04dec57b71 100644
--- a/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala
@@ -26,8 +26,6 @@ import breeze.linalg.{DenseVector, Vector}
 import org.apache.hadoop.conf.Configuration
 
 import org.apache.spark._
-import org.apache.spark.scheduler.InputFormatInfo
-
 
 /**
  * Logistic regression based classification.
@@ -74,10 +72,7 @@ object SparkHdfsLR {
     val sparkConf = new SparkConf().setAppName("SparkHdfsLR")
     val inputPath = args(0)
     val conf = new Configuration()
-    val sc = new SparkContext(sparkConf,
-      InputFormatInfo.computePreferredLocations(
-        Seq(new InputFormatInfo(conf, classOf[org.apache.hadoop.mapred.TextInputFormat], inputPath))
-      ))
+    val sc = new SparkContext(sparkConf)
     val lines = sc.textFile(inputPath)
     val points = lines.map(parsePoint _).cache()
     val ITERATIONS = args(1).toInt
diff --git a/examples/src/main/scala/org/apache/spark/examples/SparkTachyonHdfsLR.scala b/examples/src/main/scala/org/apache/spark/examples/SparkTachyonHdfsLR.scala
index e492582710..ddc99d3f90 100644
--- a/examples/src/main/scala/org/apache/spark/examples/SparkTachyonHdfsLR.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/SparkTachyonHdfsLR.scala
@@ -26,7 +26,6 @@ import breeze.linalg.{DenseVector, Vector}
 import org.apache.hadoop.conf.Configuration
 
 import org.apache.spark._
-import org.apache.spark.scheduler.InputFormatInfo
 import org.apache.spark.storage.StorageLevel
 
 /**
@@ -70,10 +69,7 @@ object SparkTachyonHdfsLR {
     val inputPath = args(0)
     val sparkConf = new SparkConf().setAppName("SparkTachyonHdfsLR")
     val conf = new Configuration()
-    val sc = new SparkContext(sparkConf,
-      InputFormatInfo.computePreferredLocations(
-        Seq(new InputFormatInfo(conf, classOf[org.apache.hadoop.mapred.TextInputFormat], inputPath))
-      ))
+    val sc = new SparkContext(sparkConf)
     val lines = sc.textFile(inputPath)
     val points = lines.map(parsePoint _).persist(StorageLevel.OFF_HEAP)
     val ITERATIONS = args(1).toInt