aboutsummaryrefslogtreecommitdiff
path: root/examples/src/main/python/als.py
diff options
context:
space:
mode:
authorZheng RuiFeng <ruifengz@foxmail.com>2016-05-20 16:40:33 -0700
committerAndrew Or <andrew@databricks.com>2016-05-20 16:40:33 -0700
commit127bf1bb07967e2e4f99ad7abaa7f6fab3b3f407 (patch)
treea127031cd361df2f1d895cb11489f8e183c76f73 /examples/src/main/python/als.py
parent06c9f520714e07259c6f8ce6f9ea5a230a278cb5 (diff)
downloadspark-127bf1bb07967e2e4f99ad7abaa7f6fab3b3f407.tar.gz
spark-127bf1bb07967e2e4f99ad7abaa7f6fab3b3f407.tar.bz2
spark-127bf1bb07967e2e4f99ad7abaa7f6fab3b3f407.zip
[SPARK-15031][EXAMPLE] Use SparkSession in examples
## What changes were proposed in this pull request? Use `SparkSession` according to [SPARK-15031](https://issues.apache.org/jira/browse/SPARK-15031) `MLLLIB` is not recommended to use now, so examples in `MLLIB` are ignored in this PR. `StreamingContext` can not be directly obtained from `SparkSession`, so example in `Streaming` are ignored too. cc andrewor14 ## How was this patch tested? manual tests with spark-submit Author: Zheng RuiFeng <ruifengz@foxmail.com> Closes #13164 from zhengruifeng/use_sparksession_ii.
Diffstat (limited to 'examples/src/main/python/als.py')
-rwxr-xr-xexamples/src/main/python/als.py12
1 files changed, 9 insertions, 3 deletions
diff --git a/examples/src/main/python/als.py b/examples/src/main/python/als.py
index f07020b503..81562e20a9 100755
--- a/examples/src/main/python/als.py
+++ b/examples/src/main/python/als.py
@@ -28,7 +28,7 @@ import sys
import numpy as np
from numpy.random import rand
from numpy import matrix
-from pyspark import SparkContext
+from pyspark.sql import SparkSession
LAMBDA = 0.01 # regularization
np.random.seed(42)
@@ -62,7 +62,13 @@ if __name__ == "__main__":
example. Please use pyspark.ml.recommendation.ALS for more
conventional use.""", file=sys.stderr)
- sc = SparkContext(appName="PythonALS")
+ spark = SparkSession\
+ .builder\
+ .appName("PythonALS")\
+ .getOrCreate()
+
+ sc = spark._sc
+
M = int(sys.argv[1]) if len(sys.argv) > 1 else 100
U = int(sys.argv[2]) if len(sys.argv) > 2 else 500
F = int(sys.argv[3]) if len(sys.argv) > 3 else 10
@@ -99,4 +105,4 @@ if __name__ == "__main__":
print("Iteration %d:" % i)
print("\nRMSE: %5.4f\n" % error)
- sc.stop()
+ spark.stop()