Very basic example workingHEADmaster

1 files changed, 9 insertions, 0 deletions

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..166a9fc
--- /dev/null
+++ b/main.py
@@ -0,0 +1,9 @@
+from pyspark.sql import SparkSession
+
+spark = SparkSession.builder.getOrCreate()
+dataList = [1, 2, 3, 4, 5]
+rdd = spark.sparkContext.parallelize(dataList)
+rdd2 = rdd.flatMap(lambda x: str(x))
+data = rdd2.collect()
+for x in data:
+    print(type(x), x)