ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

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

Browse source
This commit is contained in:
Matei Zaharia 2013-07-29 02:52:02 -04:00
parent 497f55755f f11ad72d4e
commit d8158ced12
6 changed files with 9 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
python/examples/als.py
View file

@ -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

3
python/examples/kmeans.py Normal file → Executable file
View file

@ -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])

5
python/examples/logistic_regression.py
View file

@ -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

3
python/examples/pi.py Normal file → Executable file
View file

@ -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

5
python/examples/transitive_closure.py Normal file → Executable file
View file

@ -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()

3
python/examples/wordcount.py Normal file → Executable file
View file

@ -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)