distinct.py

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

'''
SELECT DISTINCT seller_id,
       date
FROM sales_table
'''
sales_table_execution_plan = sales_table.select(
    col("seller_id"), col("date")
).distinct()

#   Print Schema
sales_table_execution_plan.show()