[Spark] 간단한 DataFrame 만드는 방법

코드

from pyspark.sql import SparkSession
from pyspark.sql import Row

if __name__ == "__main__":
        
    spark = SparkSession\
            .builder\
            .appName("0_save_file")\
            .getOrCreate()

    sc = spark.sparkContext

    data_1 = [("kim", 1), ("park", 2), ("choi", 3)]

    data_2 = [Row(name='kim',  age=5,  height=80),
              Row(name='park', age=5,  height=80),
              Row(name='choi', age=10, height=80)]

    df_1 = sc.parallelize(data_1).toDF()
    df_2 = sc.parallelize(data_2).toDF()

    print(df_1.show())
    print(df_2.show())

    spark.stop()

결과