Added simple app example.

tamoanxx · Sep 15, 2015 · 3b41633 · 3b41633
1 parent fbdf357
commit 3b41633
Show file tree

Hide file tree

Showing 2 changed files with 21 additions and 3 deletions.
diff --git a/apache-spark-standalone/README.md b/apache-spark-standalone/README.md
@@ -6,15 +6,22 @@ Execute
 vagrant up
 ```
 
-to start the VM. Then try
+to start the VM, ```vagrant ssh``` into it and then try:
 
 ```
-vagrant ssh
-cd spark-1.5.0-bin-hadoop2.6
+cd ~/spark-1.5.0-bin-hadoop2.6
 ./bin/pyspark
 testFile = sc.textFile("README.md")
 testFile.count()
 ```
 
 Press ```CTRL+D``` to exit the pyspark shell
 
+or
+
+```
+cd ~/spark-1.5.0-bin-hadoop2.6
+./bin/spark-submit --master local /vagrant/simpleapp.py
+```
+
+
diff --git a/apache-spark-standalone/simpleapp.py b/apache-spark-standalone/simpleapp.py
@@ -0,0 +1,11 @@
+"""simpleapp.py"""
+from pyspark import SparkContext
+
+logFile = "/home/vagrant/spark-1.5.0-bin-hadoop2.6/README.md"  
+sc = SparkContext(appName="Simple App")
+logData = sc.textFile(logFile).cache()
+
+numAs = logData.filter(lambda s: 'a' in s).count()
+numBs = logData.filter(lambda s: 'b' in s).count()
+
+print("Lines with a: %i, lines with b: %i" % (numAs, numBs))