[Spark] pyspark RDD parallelize(), map(), flatMap()

code

from pyspark.sql import SparkSession

spark = SparkSession.builder \
                    .appName('0_test_rdd') \
                    .master('spark://spark-master-1:7077,spark-master-2:7077') \
                    .config('spark.driver.cores', '2') \
                    .config('spark.driver.memory','2g') \
                    .config('spark.executor.memory', '2g') \
                    .config('spark.executor.cores', '2') \
                    .config('spark.cores.max', '8') \
                    .getOrCreate()

sc = spark.sparkContext

line_1 = 'i love you'
line_2 = 'you are my friend'
line_3 = 'my name is park'

lines = sc.parallelize([line_1, line_2, line_3])
lines_map = lines.map(lambda x: x.split(' '))
lines_flatmap = lines.flatMap(lambda x: x.split(' '))

print()
print(lines)
print(lines.collect())
print()
print(lines_map)
print(lines_map.collect())
print()
print(lines_flatmap)
print(lines_flatmap.collect())
print()

sc.stop()

ParallelCollectionRDD[0] at readRDDFromFile at PythonRDD.scala:274
['i love you', 'you are my friend', 'my name is park']                          

PythonRDD[1] at RDD at PythonRDD.scala:53
[['i', 'love', 'you'], ['you', 'are', 'my', 'friend'], ['my', 'name', 'is', 'park']]

PythonRDD[2] at RDD at PythonRDD.scala:53
['i', 'love', 'you', 'you', 'are', 'my', 'friend', 'my', 'name', 'is', 'park']