collect_set.py

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

'''
SELECT COLLECT_SET(num_pieces_sold) AS num_pieces_sold_set,
       COLLECT_LIST(num_pieces_list) AS num_pieces_sold_list,
       seller_id
FROM sales_table
GROUP BY seller_id
'''
sales_table_execution_plan = sales_table.groupBy(col("seller_id")).agg(
    collect_set(col("num_pieces_sold")).alias("num_pieces_sold_set"),
    collect_list(col("num_pieces_sold")).alias("num_pieces_sold_list"),

)

sales_table_execution_plan.show(10, True)