create_table.sql

CREATE table "datalake-raw"."test_data_parquet" WITH (
  format='PARQUET',
  parquet_compression='SNAPPY',
  partitioned_by=array['marketplace', 'product_category'],
  external_location = 's3://<my-bucket>/optimized-data/'
)
AS
SELECT 
  "customer_id"
, "review_id"
, "product_id"
, "product_parent"
, "product_title"
, "star_rating"
, "helpful_votes"
, "total_votes"
, "vine"
, "verified_purchase"
, "review_headline"
, "review_body"
, "review_date"
, "marketplace"
, "product_category"
FROM "datalake-raw"."test_data_archive"