users1 = [
    {
        "email":"alovett0@nsw.gov.au",
        "first_name":"Aundrea",
        "last_name":"Lovett",
        "gender":"Male",
        "ip_address":"62.72.1.143"
    },
    {
        "email":"bjowling1@spiegel.de",
        "first_name":"Bettine",
        "last_name":"Jowling",
        "gender":"Female",
        "ip_address":"26.250.197.47"
    }
]

from pyspark.sql import Row
users1_df = spark.createDataFrame([Row(**user) for user in users1])

users2 = [{
        "email":"lbutland7@time.com",
        "first_name":"Lilas",
        "last_name":"Butland",
        "gender":"Female",
        "ip_address":"109.110.131.151"
    },
    {
        "email":"bjowling1@spiegel.de",
        "first_name":"Putnam",
        "last_name":"Alfonsetti",
        "gender":"Female",
        "ip_address":"167.97.48.246"
    }
]

users2_df = spark.createDataFrame([Row(**user) for user in users2])

users1_df. \
    join(users2_df, users1_df.email == users2_df.email, 'full_outer'). \
    show()

users1_df. \
    join(users2_df, 'email', 'full_outer'). \
    show()