Spark Interview question|pyspark explode| pyspark arrays_zip
#pyspark #code #explode #arrays_zip
from pyspark.sql import SparkSession
spark = SparkSession.builder.appName('pyspark-app').getOrCreate()
from pyspark.sql.functions import arrays_zip,explode
df = spark.createDataFrame([[1,['Math','ENG'],[90,80]],[2,['Math','PHY','ENG'],[100,75,80]]], ['id','sub','marks'])
df.withColumn("sub_marks", arrays_zip("sub","marks")) \
.select("id",explode("sub_marks").alias("check")) \
.select("id","check.sub","check.marks").show()