clean up examples

markhamstra · Aug 18, 2014 · 189dcea · 189dcea
1 parent b8d7d24
commit 189dcea
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 17 deletions.
diff --git a/examples/src/main/python/streaming/network_wordcount.py b/examples/src/main/python/streaming/network_wordcount.py
@@ -14,12 +14,10 @@
     ssc = StreamingContext(conf=conf, duration=Seconds(1))
 
     lines = ssc.socketTextStream(sys.argv[1], int(sys.argv[2]))
-    fm_lines = lines.flatMap(lambda x: x.split(" "))
-    mapped_lines = fm_lines.map(lambda x: (x, 1))
-    reduced_lines = mapped_lines.reduceByKey(add)
+    words = lines.flatMap(lambda line: line.split(" "))
+    mapped_words = words.map(lambda word: (word, 1))
+    count = mapped_words.reduceByKey(add)
 
-    reduced_lines.pyprint()
-    count_lines = mapped_lines.count()
-    count_lines.pyprint()
+    count.pyprint()
     ssc.start()
     ssc.awaitTermination()
diff --git a/examples/src/main/python/streaming/wordcount.py b/examples/src/main/python/streaming/wordcount.py
@@ -11,21 +11,14 @@
         exit(-1)
     conf = SparkConf()
     conf.setAppName("PythonStreamingWordCount")
-    conf.set("spark.default.parallelism", 1)
 
-# still has a bug
-#    ssc = StreamingContext(appName="PythonStreamingWordCount", duration=Seconds(1))
     ssc = StreamingContext(conf=conf, duration=Seconds(1))
 
     lines = ssc.textFileStream(sys.argv[1])
-    fm_lines = lines.flatMap(lambda x: x.split(" "))
-    filtered_lines = fm_lines.filter(lambda line: "Spark" in line)
-    mapped_lines = fm_lines.map(lambda x: (x, 1))
-    reduced_lines = mapped_lines.reduceByKey(add)
+    words = lines.flatMap(lambda line: line.split(" "))
+    mapped_words = words.map(lambda x: (x, 1))
+    count = mapped_words.reduceByKey(add)
 
-    fm_lines.pyprint()
-    filtered_lines.pyprint()
-    mapped_lines.pyprint()
-    reduced_lines.pyprint()
+    count.pyprint()
     ssc.start()
     ssc.awaitTermination()