[training@localhost ~]$ hdfs dfs -cat people.json

{"name":"Alice","pcode":"94304"}

{"name":"Brayden","age":30,"pcode":"94304"}

{"name":"Carla","age":19,"pcoe":"10036"}

{"name":"Diana","age":46}

{"name":"Etienne","pcode":"94104"}

[training@localhost ~]$

hdfs dfs -cat pcodes.json

{"pcode":"10036","city":"New York","state":"NY"}

{"pcode:"87501","city":"Santa Fe","state":"NM"}

{"pcode":"94304","city":"Palo Alto","state":"CA"}

{"pcode":"94104","city":"San Francisco","state":"CA"}

sqlContext = HiveContext(sc)

peopleDF = sqlContext.read.json("people.json")

sqlContext = HiveContext(sc)

pcodesDF = sqlContext.read.json("pcodes.json")

mydf001=peopleDF.join(pcodesDF,"pcode")

mydf001.limit(5).show()

+-----+----+-------+----+---------------+-------------+-----+

|pcode| age| name|pcoe|_corrupt_record| city|state|

+-----+----+-------+----+---------------+-------------+-----+

|94304|null| Alice|null| null| Palo Alto| CA|

|94304| 30|Brayden|null| null| Palo Alto| CA|

|94104|null|Etienne|null| null|San Francisco| CA|

+-----+----+-------+----+---------------+-------------+-----+