select2.py

#   Read the source tables in Parquet format
sales_table = spark.read.parquet("./data/sales_parquet")

'''
SELECT order_id AS the_order_id,
       seller_id AS the_seller_id,
       num_pieces_sold AS the_number_of_pieces_sold
FROM sales_table
'''
#   Execution Plan and show action in one line
sales_table_execution_plan = sales_table.select(
    col("order_id").alias("the_order_id"),
    col("seller_id").alias("the_seller_id"),
    col("num_pieces_sold").alias("the_number_of_pieces_sold")
).show(5, True)