embedded jars: replace spark-example.jar
we can use python implementation of spark pi job. Change-Id: I5428b814eba17153d045c34fe3852704be0cc104
This commit is contained in:
parent
35e5256521
commit
57a66164d8
Binary file not shown.
|
@ -0,0 +1,39 @@
|
|||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
# implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
from __future__ import print_function
|
||||
|
||||
import sys
|
||||
from random import random
|
||||
from operator import add
|
||||
|
||||
from pyspark import SparkContext
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
"""
|
||||
Usage: pi [partitions]
|
||||
"""
|
||||
sc = SparkContext(appName="PythonPi")
|
||||
partitions = int(sys.argv[1]) if len(sys.argv) > 1 else 2
|
||||
n = 100000 * partitions
|
||||
|
||||
def f(_):
|
||||
x = random() * 2 - 1
|
||||
y = random() * 2 - 1
|
||||
return 1 if x ** 2 + y ** 2 < 1 else 0
|
||||
|
||||
count = sc.parallelize(range(1, n + 1), partitions).map(f).reduce(add)
|
||||
print("Pi is roughly %f" % (4.0 * count / n))
|
||||
|
||||
sc.stop()
|
|
@ -65,9 +65,9 @@ edp_jobs_flow:
|
|||
- type: Spark
|
||||
main_lib:
|
||||
type: database
|
||||
source: edp-examples/edp-spark/spark-example.jar
|
||||
source: edp-examples/edp-spark/spark-pi.py
|
||||
configs:
|
||||
edp.java.main_class: org.apache.spark.examples.SparkPi
|
||||
edp.java.main_class: main
|
||||
args:
|
||||
- 4
|
||||
spark_wordcount:
|
||||
|
|
Loading…
Reference in New Issue