In [ ]:

    

%AddDeps com.databricks spark-avro_2.11 4.0.0 --transitive


    

In [12]:

    

import com.databricks.spark.avro._


    

In [13]:

    

val df = spark.read.avro("s3a://temp-bucket/transactions")


    

    






df = [InvoiceNo: int, StockCode: string ... 10 more fields]







    
Out[13]:





[InvoiceNo: int, StockCode: string ... 10 more fields]

In [14]:

    

df.head()


    

    
Out[14]:





[5426731,22381,TOY TIDY PINK POLKADOT,2,1509279480000,2.1,14527,United Kingdom,8,12:18:00,0,542673180171029]

In [15]:

    

df.count()


    

    
Out[15]:





2414458

In [ ]: