Merge branch 'master' of github.com:mesos/spark

python/examples/als.py

@@ -48,8 +48,7 @@ def update(i, vec, mat, ratings):
 
 if __name__ == "__main__":
     if len(sys.argv) < 2:
-        print >> sys.stderr, \
-            "Usage: PythonALS <master> <M> <U> <F> <iters> <slices>"
+        print >> sys.stderr, "Usage: als <master> <M> <U> <F> <iters> <slices>"
         exit(-1)
     sc = SparkContext(sys.argv[1], "PythonALS", pyFiles=[realpath(__file__)])
     M = int(sys.argv[2]) if len(sys.argv) > 2 else 100
@@ -84,5 +83,5 @@ if __name__ == "__main__":
         usb = sc.broadcast(us)
 
         error = rmse(R, ms, us)
-        print "Iteration %d:" % i 
+        print "Iteration %d:" % i
         print "\nRMSE: %5.4f\n" % error

python/examples/kmeans.py

@@ -41,8 +41,7 @@ def closestPoint(p, centers):
 
 if __name__ == "__main__":
     if len(sys.argv) < 5:
-        print >> sys.stderr, \
-            "Usage: PythonKMeans <master> <file> <k> <convergeDist>"
+        print >> sys.stderr, "Usage: kmeans <master> <file> <k> <convergeDist>"
         exit(-1)
     sc = SparkContext(sys.argv[1], "PythonKMeans")
     lines = sc.textFile(sys.argv[2])

python/examples/logistic_regression.py

@@ -35,7 +35,7 @@ np.random.seed(42)
 
 
 DataPoint = namedtuple("DataPoint", ['x', 'y'])
-from lr import DataPoint  # So that DataPoint is properly serialized
+from logistic_regression import DataPoint  # So that DataPoint is properly serialized
 
 
 def generateData():
@@ -48,8 +48,7 @@ def generateData():
 
 if __name__ == "__main__":
     if len(sys.argv) == 1:
-        print >> sys.stderr, \
-            "Usage: PythonLR <master> [<slices>]"
+        print >> sys.stderr, "Usage: logistic_regression <master> [<slices>]"
         exit(-1)
     sc = SparkContext(sys.argv[1], "PythonLR", pyFiles=[realpath(__file__)])
     slices = int(sys.argv[2]) if len(sys.argv) > 2 else 2

python/examples/pi.py

@@ -24,8 +24,7 @@ from pyspark import SparkContext
 
 if __name__ == "__main__":
     if len(sys.argv) == 1:
-        print >> sys.stderr, \
-            "Usage: PythonPi <master> [<slices>]"
+        print >> sys.stderr, "Usage: pi <master> [<slices>]"
         exit(-1)
     sc = SparkContext(sys.argv[1], "PythonPi")
     slices = int(sys.argv[2]) if len(sys.argv) > 2 else 2

python/examples/transitive_closure.py

@@ -37,10 +37,9 @@ def generateGraph():
 
 if __name__ == "__main__":
     if len(sys.argv) == 1:
-        print >> sys.stderr, \
-            "Usage: PythonTC <master> [<slices>]"
+        print >> sys.stderr, "Usage: transitive_closure <master> [<slices>]"
         exit(-1)
-    sc = SparkContext(sys.argv[1], "PythonTC")
+    sc = SparkContext(sys.argv[1], "PythonTransitiveClosure")
     slices = int(sys.argv[2]) if len(sys.argv) > 2 else 2
     tc = sc.parallelize(generateGraph(), slices).cache()
 

python/examples/wordcount.py

@@ -23,8 +23,7 @@ from pyspark import SparkContext
 
 if __name__ == "__main__":
     if len(sys.argv) < 3:
-        print >> sys.stderr, \
-            "Usage: PythonWordCount <master> <file>"
+        print >> sys.stderr, "Usage: wordcount <master> <file>"
         exit(-1)
     sc = SparkContext(sys.argv[1], "PythonWordCount")
     lines = sc.textFile(sys.argv[2], 1)