[Spark] pyspark RDD count(), collect()

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(' '))
lines_filter = lines_flatmap.filter(lambda x: len(x) > 3)

print()
print(lines)
print(lines.count(), lines.collect())
print()
print(lines_map)
print(lines_map.count(), lines_map.collect())
print()
print(lines_flatmap)
print(lines_flatmap.count(), lines_flatmap.collect())
print()
print(lines_filter)
print(lines_filter.count(), lines_filter.collect())
print()

sc.stop()

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

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

PythonRDD[4] at RDD at PythonRDD.scala:53
11 ['i', 'love', 'you', 'you', 'are', 'my', 'friend', 'my', 'name', 'is', 'park']

PythonRDD[6] at RDD at PythonRDD.scala:53
4 ['love', 'friend', 'name', 'park']