[Spark] RDD의 데이터를 소문자, 대문자로 만드는 방법

코드

from pyspark.sql import SparkSession

spark = SparkSession\
        .builder\
        .appName("0_save_file")\
        .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.upper(), 
                        line_2.upper(), 
                        line_3.upper()])

lines_map = lines.map(lambda x: x.lower().split(' '))
lines_flatmap = lines.flatMap(lambda x: x.lower().split(' '))

print(f'lines.collect()         : {lines.collect()}')
print(f'lines_map.collect()     : {lines_map.collect()}')
print(f'lines_flatmap.collect() : {lines_flatmap.collect()}')

spark.stop()

결과