[SPARK-19134][EXAMPLE] Fix several sql, mllib and status api examples not working

examples/src/main/java/org/apache/spark/examples/sql/hive/JavaSparkHiveExample.java

@@ -17,6 +17,7 @@
 package org.apache.spark.examples.sql.hive;
 
 // $example on:spark_hive$
+import java.io.File;
 import java.io.Serializable;
 import java.util.ArrayList;
 import java.util.List;
@@ -56,7 +57,7 @@ public void setValue(String value) {
   public static void main(String[] args) {
     // $example on:spark_hive$
     // warehouseLocation points to the default location for managed databases and tables
-    String warehouseLocation = "spark-warehouse";
+    String warehouseLocation = new File("spark-warehouse").getAbsolutePath();
     SparkSession spark = SparkSession
       .builder()
       .appName("Java Spark Hive Example")

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

@@ -18,25 +18,20 @@
 Binary Classification Metrics Example.
 """
 from __future__ import print_function
-from pyspark.sql import SparkSession
+from pyspark import SparkContext
 # $example on$
 from pyspark.mllib.classification import LogisticRegressionWithLBFGS
 from pyspark.mllib.evaluation import BinaryClassificationMetrics
-from pyspark.mllib.regression import LabeledPoint
+from pyspark.mllib.util import MLUtils
 # $example off$
 
 if __name__ == "__main__":
-    spark = SparkSession\
-        .builder\
-        .appName("BinaryClassificationMetricsExample")\
-        .getOrCreate()
+    sc = SparkContext(appName="BinaryClassificationMetricsExample")
 
     # $example on$
     # Several of the methods available in scala are currently missing from pyspark
     # Load training data in LIBSVM format
-    data = spark\
-        .read.format("libsvm").load("data/mllib/sample_binary_classification_data.txt")\
-        .rdd.map(lambda row: LabeledPoint(row[0], row[1]))
+    data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_binary_classification_data.txt")
 
     # Split data into training (60%) and test (40%)
     training, test = data.randomSplit([0.6, 0.4], seed=11)
@@ -58,4 +53,4 @@
     print("Area under ROC = %s" % metrics.areaUnderROC)
     # $example off$
 
-    spark.stop()
+    sc.stop()

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

@@ -40,11 +40,6 @@
     # Evaluate clustering
     cost = model.computeCost(parsedData)
     print("Bisecting K-means Cost = " + str(cost))
-
-    # Save and load model
-    path = "target/org/apache/spark/PythonBisectingKMeansExample/BisectingKMeansModel"
-    model.save(sc, path)
-    sameModel = BisectingKMeansModel.load(sc, path)
     # $example off$
 
     sc.stop()

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

@@ -45,7 +45,7 @@
         print(each)
 
     print("transformedData2:")
-    for each in transformedData2.collect():
+    for each in transformedData2:
         print(each)
 
     sc.stop()

examples/src/main/python/sql/hive.py

@@ -18,7 +18,7 @@
 from __future__ import print_function
 
 # $example on:spark_hive$
-from os.path import expanduser, join
+from os.path import expanduser, join, abspath
 
 from pyspark.sql import SparkSession
 from pyspark.sql import Row
@@ -34,7 +34,7 @@
 if __name__ == "__main__":
     # $example on:spark_hive$
     # warehouse_location points to the default location for managed databases and tables
-    warehouse_location = 'spark-warehouse'
+    warehouse_location = abspath('spark-warehouse')
 
     spark = SparkSession \
         .builder \

examples/src/main/python/status_api_demo.py

@@ -19,7 +19,11 @@
 
 import time
 import threading
-import Queue
+import sys
+if sys.version >= '3':
+    import queue as Queue
+else:
+    import Queue
 
 from pyspark import SparkConf, SparkContext
 

examples/src/main/scala/org/apache/spark/examples/sql/hive/SparkHiveExample.scala

@@ -17,6 +17,8 @@
 package org.apache.spark.examples.sql.hive
 
 // $example on:spark_hive$
+import java.io.File
+
 import org.apache.spark.sql.Row
 import org.apache.spark.sql.SparkSession
 // $example off:spark_hive$
@@ -38,7 +40,7 @@ object SparkHiveExample {
 
     // $example on:spark_hive$
     // warehouseLocation points to the default location for managed databases and tables
-    val warehouseLocation = "spark-warehouse"
+    val warehouseLocation = new File("spark-warehouse").getAbsolutePath
 
     val spark = SparkSession
       .builder()