clen up examples

Author: giwa

examples/src/main/python/streaming/network_wordcount.py

@@ -1,23 +1,21 @@
 import sys
 from operator import add
 
-from pyspark.conf import SparkConf
 from pyspark.streaming.context import StreamingContext
 from pyspark.streaming.duration import *
 
 if __name__ == "__main__":
     if len(sys.argv) != 3:
         print >> sys.stderr, "Usage: wordcount <hostname> <port>"
         exit(-1)
-    conf = SparkConf()
-    conf.setAppName("PythonStreamingNetworkWordCount")
-    ssc = StreamingContext(conf=conf, duration=Seconds(1))
+    ssc = StreamingContext(appName="PythonStreamingNetworkWordCount", 
+                           duration=Seconds(1))
 
     lines = ssc.socketTextStream(sys.argv[1], int(sys.argv[2]))
     words = lines.flatMap(lambda line: line.split(" "))
     mapped_words = words.map(lambda word: (word, 1))
     count = mapped_words.reduceByKey(add)
-
     count.pyprint()
+
     ssc.start()
     ssc.awaitTermination()

examples/src/main/python/streaming/wordcount.py

@@ -1,24 +1,20 @@
 import sys
-from operator import add
 
-from pyspark.conf import SparkConf
 from pyspark.streaming.context import StreamingContext
 from pyspark.streaming.duration import *
 
 if __name__ == "__main__":
     if len(sys.argv) != 2:
         print >> sys.stderr, "Usage: wordcount <directory>"
         exit(-1)
-    conf = SparkConf()
-    conf.setAppName("PythonStreamingWordCount")
 
-    ssc = StreamingContext(conf=conf, duration=Seconds(1))
+    ssc = StreamingContext(appName="PythonStreamingWordCount", duration=Seconds(1))
 
     lines = ssc.textFileStream(sys.argv[1])
     words = lines.flatMap(lambda line: line.split(" "))
     mapped_words = words.map(lambda x: (x, 1))
-    count = mapped_words.reduceByKey(add)
-    
+    count = mapped_words.reduceByKey(lambda a, b: a+b)
     count.pyprint()
+
     ssc.start()
     ssc.awaitTermination()