Added rdd/persist/PersistExample.py

Pedro Bernardo · Pedro Bernardo · commit 80c20eda1687 · 2017-09-28T12:02:32.000+02:00
diff --git a/rdd/persist/PersistExample.py b/rdd/persist/PersistExample.py
@@ -0,0 +1,9 @@
+from pyspark import SparkContext, StorageLevel
+
+if __name__ == "__main__":
+    sc = SparkContext("local", "persist")
+    inputIntegers = [1, 2, 3, 4, 5]
+    integerRdd = sc.parallelize(inputIntegers)
+    integerRdd.persist(StorageLevel.MEMORY_ONLY)
+    integerRdd.reduce(lambda x, y: x*y)
+    integerRdd.count()
