notebook.community

Edit and run



In [3]:

    
from pyspark.sql import SparkSession

sparkSession = SparkSession.builder.getOrCreate()



In [ ]:

    
itemsDF = sparkSession.read.format("json") \
  .load("s3a://datapalooza/sparkafterdark/actors.json") \
  .withColumnRenamed("id", "itemId") \

itemsDF.show()



In [ ]:

    
ratingsDF = sparkSession.read \
    .format("org.apache.spark.sql.cassandra") \
    .options(keyspace="advancedspark", table="item_ratings") \
    .load()
    
ratingsDF.show()



In [ ]:

    
!export



In [ ]: