databricks-tpcds 0.1.0__py3-none-any.whl

databricks_tpcds/__init__.py

@@ -0,0 +1,9 @@
+import os
+import sys
+
+# Ensure that the package can find resources
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+# Expose modules so they can be imported directly
+from resources import table_names
+from .databricks_tpcds import DatabricksTPCDS

databricks_tpcds/databricks_tpcds.py

@@ -0,0 +1,153 @@
+import time
+from resources import table_names
+import importlib.resources as pkg_resources
+
+
+class DatabricksTPCDS:
+    """
+    A class to interact with Databricks for TPC-DS benchmarking.
+
+    Attributes
+    ----------
+    spark : pyspark.sql.session.SparkSession
+        The SparkSession used to interact with Databricks.
+    catalog_name : str
+        The name of the catalog in Databricks.
+    time_taken_by_query : dict
+        A dictionary to store the time taken by each query.
+
+    Methods
+    -------
+    use_catalog() -> None:
+        Uses the catalog in Databricks.
+    create_catalog() -> None:
+        Creates a new catalog in Databricks.
+    create_table(bucket_name: str, prefix: str, table_name: str) -> None:
+        Creates a new table in the Databricks catalog.
+    create_tables(bucket_name: str, prefix: str, table_names: list[str]) -> None:
+        Creates multiple tables in the Databricks catalog.
+    create_all_tables(bucket_name: str, prefix: str) -> None:
+        Creates all tables in the Databricks catalog.
+    run_query(query_num: int) -> float:
+        Runs a TPC-DS query and returns the total execution time.
+    run_queries(query_nums: list[int]) -> dict[int, float]:
+        Runs multiple TPC-DS queries and returns a dictionary of total execution times.
+    run_all_queries() -> dict[int, float]:
+        Runs all TPC-DS queries and returns a dictionary of total execution times.
+    """
+
+    order_by_cols: dict[str, str] = {
+        "call_center": "cc_call_center_id",
+        "catalog_page": "cp_catalog_page_id",
+        "catalog_returns": "cr_returned_date_sk",
+        "catalog_sales": "cs_sold_date_sk",
+        "customer": "c_customer_id",
+        "customer_address": "ca_address_id",
+        "customer_demographics": "cd_demo_sk",
+        "date_dim": "d_date_id",
+        "household_demographics": "hd_demo_sk",
+        "income_band": "ib_income_band_sk",
+        "inventory": "inv_item_sk",
+        "item": "i_item_id",
+        "promotion": "p_promo_id",
+        "reason": "r_reason_id",
+        "ship_mode": "sm_ship_mode_id",
+        "store": "s_store_id",
+        "store_returns": "sr_returned_date_sk",
+        "store_sales": "ss_sold_date_sk",
+        "time_dim": "t_time_id",
+        "warehouse": "w_warehouse_id",
+        "web_page": "wp_web_page_id",
+        "web_returns": "wr_returned_date_sk",
+        "web_sales": "ws_sold_date_sk",
+        "web_site": "web_site_id"
+    }
+
+    def __init__(self, spark, schema_name, catalog_name=None):
+        self.spark = spark
+        self.catalog_name = catalog_name
+        self.schema_name = schema_name
+        # self.enable_cache = enable_cache
+        self.time_taken_by_query = {}
+        print(f"Disk cache enabled: {self.spark.conf.get('spark.databricks.io.cache.enabled')}")
+
+    # def enable_disk_cache(self) -> None:
+    #     if self.enable_cache == True:
+    #         self.spark.conf.set("spark.databricks.io.cache.enabled", "true")
+    #     elif self.enable_cache == False:
+    #         self.spark.conf.set("spark.databricks.io.cache.enabled", "false")
+
+    def use_catalog(self) -> None:
+        if self.catalog_name:
+            self.spark.sql(f"USE CATALOG {self.catalog_name}")
+    
+    def use_schema(self) -> None:
+        self.spark.sql(f"USE SCHEMA {self.schema_name}")
+
+    def create_catalog(self) -> None:
+        if self.catalog_name:
+            self.spark.sql(f"CREATE CATALOG IF NOT EXISTS {self.catalog_name}")
+
+    def create_schema(self) -> None:
+        self.use_catalog()
+        self.spark.sql(f"CREATE SCHEMA IF NOT EXISTS {self.schema_name}")
+
+    def create_table(self, bucket_name: str, prefix: str, table_name: str, table_format: str = "delta") -> None:
+        table_path = f"s3://{bucket_name}/{prefix}/{table_name}"
+        self.use_catalog()
+        self.use_schema()
+        self.spark.sql(f"CREATE TABLE IF NOT EXISTS {table_name} USING {table_format} LOCATION '{table_path}'")
+        print(f"Table {table_name} created successfully using {table_format} format.")
+
+    def create_tables(self, bucket_name: str, prefix: str, table_names: list[str], table_format: str = "delta") -> None:
+        for table in table_names:
+            self.create_table(bucket_name, prefix, table, table_format)
+
+    def create_all_tables(self, bucket_name: str, prefix: str, table_format: str = "delta") -> None:
+        self.create_tables(bucket_name, prefix, table_names.TABLE_NAMES, table_format)
+
+    def warm_up(self) -> None:
+        self.use_catalog()
+        self.use_schema()
+        for table in table_names.TABLE_NAMES:
+            order_by_col = self.order_by_cols[table]
+            self.spark.sql(f"SELECT * FROM {table} ORDER BY {order_by_col} LIMIT 100").collect()
+
+    def run_query(self, query_num: str) -> float:
+        self.use_catalog()
+        self.use_schema()
+        query_filename = f"q{query_num}.sql"
+
+        try:
+            with pkg_resources.open_text("resources.queries", query_filename) as query:
+                query_desc = f"q{query_num}"
+                print(query_desc)
+                query_string = query.read()
+                start_time = time.time()
+                self.spark.sparkContext.setJobGroup(query_desc, query_desc, interruptOnCancel=True)
+                self.spark.sql(query_string).collect()
+                end_time = time.time()
+                time_taken = (end_time - start_time) * 1000
+                self.time_taken_by_query[query_num] = time_taken
+                return round(time_taken)
+        except FileNotFoundError:
+            print(f"Query file {query_filename} not found in package.")
+            return -1
+
+    def run_queries(self, query_nums: list[int]) -> dict[int, float]:
+        time_taken_by_queries = {}
+        for query_num in query_nums:
+            time_taken_by_queries[query_num] = self.run_query(str(query_num))
+        return time_taken_by_queries
+
+    def run_all_queries(self, should_warmup=False) -> dict[int, float]:
+        if should_warmup:
+            self.warm_up()
+        time_taken_by_queries = {}
+        for query_num in range(1, 100):
+            if query_num in [14, 23, 24, 39]:
+                for subqueries in ["a", "b"]:
+                    time_taken_by_queries[f"{query_num}{subqueries}"] = self.run_query(f"{query_num}{subqueries}")
+            else:
+                time_taken_by_queries[query_num] = self.run_query(str(query_num))
+        return time_taken_by_queries

databricks_tpcds-0.1.0.dist-info/METADATA

@@ -0,0 +1,101 @@
+Metadata-Version: 2.4
+Name: databricks-tpcds
+Version: 0.1.0
+Summary: Run the TPC-DS benchmark on Databricks (Delta Lake).
+Home-page: https://github.com/onehouseinc/onebench
+Author: Onehouse
+License: Apache-2.0
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-python
+Dynamic: summary
+
+## Running TPCDS on Databricks
+This document describes how to run TPCDS on Databricks. The TPCDS benchmark is a decision support benchmark that models several generally applicable aspects of a decision support system, including queries and data maintenance. The benchmark provides a representative evaluation of performance as a general purpose decision support system. The benchmark is the result of a partnership between the Transaction Processing Performance Council (TPC) and the decision support group (DS) of the Association for Computing Machinery (ACM).
+
+### Pre-requisites
+1. Databricks workspace
+2. Databricks metastore configured to workspace
+3. Databricks cluster (jobs/all purpose etc)
+
+## Install from PyPI
+Install the package directly in a Databricks notebook:
+```shell
+%pip install databricks-tpcds
+```
+
+The package provides the `DatabricksTPCDS` library. You drive it from an entrypoint script like
+the Delta Lake example below.
+
+## Delta Lake entrypoint example
+Fill in the placeholder `catalog_name`, `bucket_name`, `prefix`, and `schema_name` with your own
+values, then run it on your Databricks cluster.
+
+```python
+from pyspark.sql import SparkSession
+from databricks_tpcds.databricks_tpcds import DatabricksTPCDS
+
+
+def main():
+    catalog_name = 'my_catalog'
+    bucket_name = 'my-bucket'
+    prefix = 'path/to/tpcds-datasets/1TB'
+    schema_name = 'my_schema'
+
+    # Initialize Spark session
+    spark = SparkSession.builder.appName("TPCDS Query Runner").getOrCreate()
+
+    # Enable/disable cache
+    spark.conf.set("spark.databricks.io.cache.enabled", "false")
+
+    databricks_tpcds = DatabricksTPCDS(spark, schema_name=schema_name, catalog_name=catalog_name)
+
+    # Create catalog
+    databricks_tpcds.create_catalog()
+
+    # Create schema
+    databricks_tpcds.create_schema()
+
+    # Create a single table, provide the table name
+    # databricks_tpcds.create_table(bucket_name, prefix, "call_center")
+
+    # Create multiple tables, provide the list of table names
+    # databricks_tpcds.create_tables(bucket_name, prefix, ["call_center", "catalog_page"])
+
+    # Create all tables, provide the bucket name and prefix, it'll create all the tables
+    databricks_tpcds.create_all_tables(bucket_name, prefix)
+
+    # Run all queries
+    for i in range(3):
+        time_taken_by_queries = databricks_tpcds.run_all_queries(should_warmup=False)
+        print("QUERY_NUMBER,TIME_TAKEN")
+        for query_no, time_taken in time_taken_by_queries.items():
+            print(f"{query_no},{time_taken}")
+
+
+if __name__ == "__main__":
+    main()
+```
+
+## Developing locally
+1. Modify the code if necessary in `src/databricks_tpcds/databricks_tpcds.py`
+2. Take a look or modify the queries in `src/resources/queries/`
+3. Build the package:
+```shell
+cd tpcds/databricks
+python3.10 -m build
+```
+4. Upload the built `.whl` to your Databricks workspace and install it in a notebook:
+```shell
+%pip install path/to/databricks_tpcds-0.1.0-py3-none-any.whl --force-reinstall
+```
+5. Run the benchmark using the Delta Lake entrypoint example above.

databricks_tpcds-0.1.0.dist-info/RECORD

@@ -0,0 +1,116 @@
+databricks_tpcds/__init__.py,sha256=D3UhqQMa2Zo1O18AJBfv0kZL_7Updi9zINGH7-ODTy0,258
+databricks_tpcds/databricks_tpcds.py,sha256=L1C8UmYrMTYkXKk70Dw-di-K_kgp_S5aEmFnUfeeAP8,6415
+resources/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+resources/table_names.py,sha256=x8g3Hu7CqrWK1mbcNEUCwpFHLcLlEjpwgK9380R7cjs,466
+resources/queries/q0.sql,sha256=1kSAiQgPOTSwisGkxqNmF4LLwbXIi6G7g-zLytgny38,47
+resources/queries/q1.sql,sha256=PTYMAqFW1-Q7eE8QWq5XqMk9EPseKXYJK5KPxesDprY,626
+resources/queries/q10.sql,sha256=OZ9ouFNSaTAX_XTxkb6yZkGpZRJKvvqhHllgI-UYT0k,1754
+resources/queries/q11.sql,sha256=JwR4vAl2cJDUgT81GQr67uOzGsc8M5CFiBm_plYSAdg,2830
+resources/queries/q12.sql,sha256=StYz8D6HE89N29N6jPLz0YGXIRknQSxlQaEWTY9_uFA,750
+resources/queries/q13.sql,sha256=CBDKyBa14NzTywVqw55sA4WwN37qoqBxyB8M1_5coOc,1457
+resources/queries/q14.sql,sha256=66j0TUGmDnPbsUHy5wX5SX-dBqgGjwpYKxKdckPdvCc,7382
+resources/queries/q14a.sql,sha256=6fi3XM8GQVRQUbC8zUUg6OrTsOfxc5N-JwA_bqU3C1A,3511
+resources/queries/q14b.sql,sha256=MZRv8vkkM6Tdx6x1LKL1VnJWXg0eqfgPu-0ljSDmH6k,3869
+resources/queries/q15.sql,sha256=ZnkABvPLLS_fNfvTv8K1e4LU6JNXPk2-osLZTyDtLHU,545
+resources/queries/q16.sql,sha256=ydKhoakonPpRR-8asN_gJVpmYbWOrk42D-b927fY2Ts,973
+resources/queries/q17.sql,sha256=pHu6PBqMPb06PyRI_hdR9-NNq0Dq5WAzrtYDw5Covv0,1637
+resources/queries/q18.sql,sha256=kBCntZr4tf0bKvEGqdmHHC0vctzz8v19B3VcvlsnRYA,1240
+resources/queries/q19.sql,sha256=c9Sz_2l-d9ZABPLX-PAjJruWa94N5W1SB5wyOSBl8Ag,666
+resources/queries/q2.sql,sha256=Es3tZnyYmGwPA1HCq6KV1GAsu4lOumamhpwDtpXF6Lc,2117
+resources/queries/q20.sql,sha256=9Bm2Z1ElEznDqiU3_UAK9E7BuvteKVzk0csa9UqoyoQ,768
+resources/queries/q21.sql,sha256=TgXZrPTdt9H3K0Y25-VUzbjGj5CreEIhFkdWs5g9HWo,1040
+resources/queries/q22.sql,sha256=Y2OA_KcO1yfEgZt2i2WHjyuKRZTY4tVG4Gr30TwldJ8,550
+resources/queries/q23.sql,sha256=PxR4sSEBgiNZAoQDjMwjFG9XUzxYYZSNEk8WjyRS1og,3789
+resources/queries/q23a.sql,sha256=CEsE_NpeFh4Xrs_mJrWKBrAIAdNMFh3kYmQl19Bzb8E,1694
+resources/queries/q23b.sql,sha256=-tBHJ4MjF2xjbXox2IRBgCe5joErmlDnU7eM1yy9joA,2054
+resources/queries/q24.sql,sha256=Bghu-03GNLBnhsFdfdk0Uf9e_kD4lzfJMe24cO82DXg,2324
+resources/queries/q24a.sql,sha256=KWV2Sg2Bf7gbe_5-_ZJTtVwRQBXd688z-qZaD1JzTtM,1155
+resources/queries/q24b.sql,sha256=-s04D7KhD-wfZEMQATKlJOctLKL2mCqfBiXHg1WcUZk,1155
+resources/queries/q25.sql,sha256=omZEK7nySq7kRMeUCYxCnLVbgl2eq3qYg53yg1Ex2MQ,1005
+resources/queries/q26.sql,sha256=3o6gqMkMAHgcmekM3VcHTpWR0TNbrko01Rv5kyIGppk,629
+resources/queries/q27.sql,sha256=F08oFBAuyY5vnuC7btOV5kHVXpYovmtDWxpjriJL_qs,690
+resources/queries/q28.sql,sha256=vAQCnMnHg95sZOYU_jAWo-G6KVlnXvfSbHw2ptcRmsE,2178
+resources/queries/q29.sql,sha256=T0NIgYAsHVPbySyjnxUjcAgP_ZQaMwyb6Li3VpzdrMM,1251
+resources/queries/q3.sql,sha256=oLf7g392MnqkhO_JScL9J2l41eg3vYV74fmS1tlc0J4,464
+resources/queries/q30.sql,sha256=Buvtr4UUz_GAcYkYKLB5lk7UqF2B4c8hUJQKE0AzHnk,1205
+resources/queries/q31.sql,sha256=NMYKUubYRSZT52pGtaDV8UUNaX_Jx8ijk9h-71kVM7g,1695
+resources/queries/q32.sql,sha256=pbi-B4Rkfp53Bp4z3LgDQFvqdujjaAQHvFba_R-r3Jo,688
+resources/queries/q33.sql,sha256=1BaP8vu92vJb9TaemzK-UNxroo3zssaQHn3Cp65Dl20,1867
+resources/queries/q34.sql,sha256=BAfGjRZEGCl3UpxVYT86dqEzCKHTN5wTPWiPZ2x4lzI,1385
+resources/queries/q35.sql,sha256=aGsrUgIOoU6PtN_OS2ATZPNTZ_tXtaZEMNo-QYu4oAk,1737
+resources/queries/q36.sql,sha256=w3jE1d_DD_c84WC6rTDSRcJy-BZuiDyawBn5xF7ZqRs,799
+resources/queries/q37.sql,sha256=FAoOHxwZhjGlumpQF5x4oX9y8g99RPJ4zRckosY0eo8,510
+resources/queries/q38.sql,sha256=dPDU6jQJ_I6fpiqC0ns_bfDTunTcmB1fDvBD5Vti1Wo,907
+resources/queries/q39.sql,sha256=0PdwZt60nE1wl7ZXHsRM9m80HYHg4G9PouKPscGJaEg,2463
+resources/queries/q39a.sql,sha256=HtqWU4iYoPYHVKQpOiAahAd26prdELGJrXGzu6LtToE,1208
+resources/queries/q39b.sql,sha256=6M_l1lUbAc6XNhVsWEneT6y4KvrlHYrN5U1a_Y-erBs,1242
+resources/queries/q4.sql,sha256=rWgvmSYKNqPHKljU-JBGvRMvO9mrAmq8UupA4RSbaik,4219
+resources/queries/q40.sql,sha256=ALOaGtcjoJJYscwU9kGEmKizlQ802IYQQIR1pT10jfU,885
+resources/queries/q41.sql,sha256=1quQOx8ZshgEfahNDIdZTLPS0vNO6XH9lZU6hPNwZoU,1907
+resources/queries/q42.sql,sha256=p1wEaPLqJO6iKEjKqFwHyBUNv1HMX3Y0nblUzCeyODE,482
+resources/queries/q43.sql,sha256=UJlnIZ8MykPJib4jIzIqxkDhnMLcotj2X29w_8bugxg,999
+resources/queries/q44.sql,sha256=rbMjwL-6R3cdVTPbh-yczlyrXEdKPtnYR97NG2aT73Q,1623
+resources/queries/q45.sql,sha256=tFAqAmqAzxK-UDZWboI5vOTkw7t-F-a7ZkzehBw_4z8,688
+resources/queries/q46.sql,sha256=Mn9NhmHQj398ITp07iJ91U3CAq41Rbf4ywe0BeJVrMM,1273
+resources/queries/q47.sql,sha256=H1vUjdw8BbXPC-dTssa_awWsWnUmsqdVjKovLBg1fY8,1787
+resources/queries/q48.sql,sha256=TaB5mkKlGAUXzdFvxsV-K0A03UZ-qlzzgEiO3iqVZ7U,1212
+resources/queries/q49.sql,sha256=TXNUlYPUhFW_dUvkXnyZLyTFRhTRjrxYglZaPpfMsfA,3749
+resources/queries/q5.sql,sha256=PS2FUJQ48Rh0BX2xJ9m_imgv2ghhHtMp4CjMM28UKOg,3914
+resources/queries/q50.sql,sha256=DfaGuneMmgzekbjEJtdeoTde-vy3urwlNV21ad6OJRU,1571
+resources/queries/q51.sql,sha256=7DBWp5FmM79h_dcXNzl4eVQ3fqjNfXJeCyZRWk23ic0,1650
+resources/queries/q52.sql,sha256=6Jl4XhoruiW1CDTiWH5RsWC-XNJH4boDAlgjDX9FyVY,454
+resources/queries/q53.sql,sha256=avH82lc22lIqxzAVPI-JK3-7iaHs9QH76oNLNGCDGGY,1068
+resources/queries/q54.sql,sha256=Rz9AYaKvZE-g3o14ncgFPqHcdwJ-4DJcBUKvDmCJmYw,1699
+resources/queries/q55.sql,sha256=ScPPDeyBlddwFoIEu18Rm1BLu0zKZHhWcuW4gtucrUk,326
+resources/queries/q56.sql,sha256=aJ0Db5J7FM0J-U-jOjNRf-duZPIJh9KC0gEBiN8SdnY,1851
+resources/queries/q57.sql,sha256=0vtHOvQlk88ecte68krJ4-R1fzy9F7ZxJXoCXRcPF6I,1546
+resources/queries/q58.sql,sha256=NehEN-eEUNXITW-Ka6THtWFoAcSDRkpGX36MdjG7GQ4,2333
+resources/queries/q59.sql,sha256=SRIYDS0ks7O1rRV8kt51PZ57J6EvJfrzuToyZPbdL-4,2020
+resources/queries/q6.sql,sha256=b97p0TEaC0fvbElwjS1mi1xiZ-OODLfH5c4G5jfKqsI,674
+resources/queries/q60.sql,sha256=9l_Vdw2sjEweOj51k_YkWyyuvREraZuvvubgc7la95g,1836
+resources/queries/q61.sql,sha256=KzLPq4vTFaXsGxRCa3zRzU-O14oiOK5urZ3nGpe-NbM,1254
+resources/queries/q62.sql,sha256=ew5Re2cTHhjsT7qekV77dBFBqOaXy8wnESelFrS7Qcw,1163
+resources/queries/q63.sql,sha256=Ji_bZ43Ol3g3JFI0v6i0cGT3ARE_qu7fYFfrw7tGYug,1272
+resources/queries/q64.sql,sha256=ayb_luuiJLLWP2O_o0O0vQaOdKILqm6fAoSA6qK40gU,3548
+resources/queries/q65.sql,sha256=B7FBYsTU9SG_ow0mtFsT0bhvq70JxcVINMExOe4lWy0,854
+resources/queries/q66.sql,sha256=o8z9wkhIL3NVJPNrmdoT9x1vZPn60Fp3TQjdSP5dL5o,7376
+resources/queries/q67.sql,sha256=9mxTsb4Ggqj8P3CY8vp8KjOAhqk6vzRv-r7w7DFEy3Q,1173
+resources/queries/q68.sql,sha256=Rc8WuuOE8_wR-ZDgGfQUCkvlP9EJAfAaXht5EJO2moo,1427
+resources/queries/q69.sql,sha256=fv3YiVDnNpUgZVvqThH3SXuGPqj2Fhqf41CQ5o-98tk,1400
+resources/queries/q7.sql,sha256=nx9_RD27ZRwVL9ft4XlmqHi8_fzHKkBk-oeazzMIbgM,621
+resources/queries/q70.sql,sha256=FvfNqjqzjzi01T42OcHwjNy79IoJ4uLgxqqkJ-TQfrs,1144
+resources/queries/q71.sql,sha256=qANpSw4VQ8hnUsAnUhybRxJogQqihr1pEe25-RoefTA,1550
+resources/queries/q72.sql,sha256=DhcRW2Ebkh6M0kK58WdBFuXb2WrovwqejOPSMC1Z9jc,1166
+resources/queries/q73.sql,sha256=dFLIGHVc8atujUtq6ytTks6wcoexqcSbfq6j65iL3FQ,1189
+resources/queries/q74.sql,sha256=dc_vfeCoiyZAiVNaG5eZAYyHve8bxzCEM9Ct6yOWgoM,2037
+resources/queries/q75.sql,sha256=JfB2Yb48ztnJ2Zzu7Olt0txOsGyO_LxZepwV-LpNw_w,3091
+resources/queries/q76.sql,sha256=qRyV06LwHCAYvsbuKlfsG7uSDgMcEib-xLnLbeyyYYM,1143
+resources/queries/q77.sql,sha256=m2gIbfiJQfQ_SI_KLboXHG9FCoqkex6LjRbox61-TIg,3103
+resources/queries/q78.sql,sha256=U6-F4qWCjAEVbWITwscA5e8AYHp2oTHI8l1Hz-waDJQ,2103
+resources/queries/q79.sql,sha256=LLlvDkG9pffqYG_FI9gIPC8Cp0A6pQhA0i4397ArsiM,915
+resources/queries/q8.sql,sha256=fGlXIjsNORZ2Poh3-WOlyTs4Yev0SWgdCwO6vRtvx6M,6117
+resources/queries/q80.sql,sha256=BoERhyoZQkF324dFTtXWQ1FbGpgECgQkasCN49ml9l8,2904
+resources/queries/q81.sql,sha256=W6XT1bwR7iWV9H1tiE_K4I0hUJ8aiVy0kVW50hkDaaE,1281
+resources/queries/q82.sql,sha256=mzPia-WUsBckcIawfTmbT4NGZcKxQhWAsfvUdtPjq-I,506
+resources/queries/q83.sql,sha256=sjsx6E68g5YjZY0bkNyl2JOkMUTavse_-GejT0h1k9Q,1772
+resources/queries/q84.sql,sha256=pqcU2aZ3Skc4wNCGZvF5ND54z4c7Tc7qaVodpkuIttg,617
+resources/queries/q85.sql,sha256=5y10U9-sB_ytpACwnCZeEwLz3IfwnMAQ6I-SRPu1JA8,2039
+resources/queries/q86.sql,sha256=pByvmQ3HIKSGnsYmfQS9rhcAk6yIxy4Z_njvm72kQFU,649
+resources/queries/q87.sql,sha256=a8-79rL4_UDUiauGQCN6ZRE8L_fMwNo_dM9OWz3X33U,920
+resources/queries/q88.sql,sha256=L99dHSuf2XuR_KYDMthldMVNVM7NZgAm1Y4gY7wy_OI,5150
+resources/queries/q89.sql,sha256=HM_0TSFZW6Vzae_7jnA_70vXgjNGrjST-9PuEynuAJI,991
+resources/queries/q9.sql,sha256=zhCamHClUEJeaXhFJOL9WCYtz2OpkDjA0r0fTyCVHJY,2147
+resources/queries/q90.sql,sha256=PXUiDx_Ho2J74NNFd1ty4PmnUZi_6KKohPi1fd-L414,979
+resources/queries/q91.sql,sha256=N2hIFKX8obNiPvlG2e7G5hJAXZ5gVvFD2jvTIm5Yemk,1089
+resources/queries/q92.sql,sha256=6buORPAAzk8N251ABwk-IxrZr4fziZ0fez1WOrIVt0E,719
+resources/queries/q93.sql,sha256=StkuqrAWnZ85JjPaD6IhGOfC7TPN1-rzk9KPNT5fhcg,798
+resources/queries/q94.sql,sha256=PtxIr05pAeixCEFelSJoVL4eHOE8hOZSaIQgCK7S4yI,839
+resources/queries/q95.sql,sha256=RNQPYyZIwNz2gdQ9JQtuDHkz_6ekJ6zGAe0xhPcnSww,1034
+resources/queries/q96.sql,sha256=E4SiwqMu0caEc7NSw_lS0Tdsn6PFwF9JkMjvV9GzdKg,407
+resources/queries/q97.sql,sha256=6LhpRiUg_nyLXSwajoTO-gIqypcILpvtgam00qPniYM,958
+resources/queries/q98.sql,sha256=xAR1tfC6LloysNrfg9vFWmr7TZGzicMZv09Wxk1DY1w,737
+resources/queries/q99.sql,sha256=PQqOgSeqjOjAqn8g9jLpSG73Jj014xoHDdJchW8d7uo,1174
+databricks_tpcds-0.1.0.dist-info/METADATA,sha256=vjLDTYCkRC1aL08QhBNisfDwnevBufIiQBVgwn3DJ0M,3649
+databricks_tpcds-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+databricks_tpcds-0.1.0.dist-info/top_level.txt,sha256=eCGMT_zAX9GV67BgZU59Ha2zM560Y1TWU9D-O7uREfw,27
+databricks_tpcds-0.1.0.dist-info/RECORD,,

databricks_tpcds-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

databricks_tpcds-0.1.0.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+databricks_tpcds
+resources

resources/queries/q0.sql

@@ -0,0 +1,2 @@
+--TPC-DS Q0
+select * from call_center limit 10;

resources/queries/q1.sql

@@ -0,0 +1,24 @@
+--TPC-DS Q1
+with customer_total_return as
+(select sr_customer_sk as ctr_customer_sk
+,sr_store_sk as ctr_store_sk
+,sum(SR_RETURN_AMT_INC_TAX) as ctr_total_return
+from store_returns
+,date_dim
+where sr_returned_date_sk = d_date_sk
+and d_year =1999
+group by sr_customer_sk
+,sr_store_sk)
+ select  c_customer_id
+from customer_total_return ctr1
+,store
+,customer
+where ctr1.ctr_total_return > (select avg(ctr_total_return)*1.2
+from customer_total_return ctr2
+where ctr1.ctr_store_sk = ctr2.ctr_store_sk)
+and s_store_sk = ctr1.ctr_store_sk
+and s_state = 'TN'
+and ctr1.ctr_customer_sk = c_customer_sk
+order by c_customer_id
+limit 100;
+

resources/queries/q10.sql

@@ -0,0 +1,58 @@
+--TPC-DS Q10
+select  
+  cd_gender,
+  cd_marital_status,
+  cd_education_status,
+  count(*) cnt1,
+  cd_purchase_estimate,
+  count(*) cnt2,
+  cd_credit_rating,
+  count(*) cnt3,
+  cd_dep_count,
+  count(*) cnt4,
+  cd_dep_employed_count,
+  count(*) cnt5,
+  cd_dep_college_count,
+  count(*) cnt6
+ from
+  customer c,customer_address ca,customer_demographics
+ where
+  c.c_current_addr_sk = ca.ca_address_sk and
+  ca_county in ('Clinton County','Platte County','Franklin County','Louisa County','Harmon County') and
+  cd_demo_sk = c.c_current_cdemo_sk and 
+  exists (select *
+          from store_sales,date_dim
+          where c.c_customer_sk = ss_customer_sk and
+                ss_sold_date_sk = d_date_sk and
+                d_year = 2002 and
+                d_moy between 3 and 3+3) and
+   (exists (select *
+            from web_sales,date_dim
+            where c.c_customer_sk = ws_bill_customer_sk and
+                  ws_sold_date_sk = d_date_sk and
+                  d_year = 2002 and
+                  d_moy between 3 ANd 3+3) or 
+    exists (select * 
+            from catalog_sales,date_dim
+            where c.c_customer_sk = cs_ship_customer_sk and
+                  cs_sold_date_sk = d_date_sk and
+                  d_year = 2002 and
+                  d_moy between 3 and 3+3))
+ group by cd_gender,
+          cd_marital_status,
+          cd_education_status,
+          cd_purchase_estimate,
+          cd_credit_rating,
+          cd_dep_count,
+          cd_dep_employed_count,
+          cd_dep_college_count
+ order by cd_gender,
+          cd_marital_status,
+          cd_education_status,
+          cd_purchase_estimate,
+          cd_credit_rating,
+          cd_dep_count,
+          cd_dep_employed_count,
+          cd_dep_college_count
+limit 100;
+

resources/queries/q11.sql

@@ -0,0 +1,80 @@
+--TPC-DS Q11
+with year_total as (
+ select c_customer_id customer_id
+       ,c_first_name customer_first_name
+       ,c_last_name customer_last_name
+       ,c_preferred_cust_flag customer_preferred_cust_flag
+       ,c_birth_country customer_birth_country
+       ,c_login customer_login
+       ,c_email_address customer_email_address
+       ,d_year dyear
+       ,sum(ss_ext_list_price-ss_ext_discount_amt) year_total
+       ,'s' sale_type
+ from customer
+     ,store_sales
+     ,date_dim
+ where c_customer_sk = ss_customer_sk
+   and ss_sold_date_sk = d_date_sk
+ group by c_customer_id
+         ,c_first_name
+         ,c_last_name
+         ,c_preferred_cust_flag 
+         ,c_birth_country
+         ,c_login
+         ,c_email_address
+         ,d_year 
+ union all
+ select c_customer_id customer_id
+       ,c_first_name customer_first_name
+       ,c_last_name customer_last_name
+       ,c_preferred_cust_flag customer_preferred_cust_flag
+       ,c_birth_country customer_birth_country
+       ,c_login customer_login
+       ,c_email_address customer_email_address
+       ,d_year dyear
+       ,sum(ws_ext_list_price-ws_ext_discount_amt) year_total
+       ,'w' sale_type
+ from customer
+     ,web_sales
+     ,date_dim
+ where c_customer_sk = ws_bill_customer_sk
+   and ws_sold_date_sk = d_date_sk
+ group by c_customer_id
+         ,c_first_name
+         ,c_last_name
+         ,c_preferred_cust_flag 
+         ,c_birth_country
+         ,c_login
+         ,c_email_address
+         ,d_year
+         )
+  select  
+                  t_s_secyear.customer_id
+                 ,t_s_secyear.customer_first_name
+                 ,t_s_secyear.customer_last_name
+                 ,t_s_secyear.customer_email_address
+ from year_total t_s_firstyear
+     ,year_total t_s_secyear
+     ,year_total t_w_firstyear
+     ,year_total t_w_secyear
+ where t_s_secyear.customer_id = t_s_firstyear.customer_id
+         and t_s_firstyear.customer_id = t_w_secyear.customer_id
+         and t_s_firstyear.customer_id = t_w_firstyear.customer_id
+         and t_s_firstyear.sale_type = 's'
+         and t_w_firstyear.sale_type = 'w'
+         and t_s_secyear.sale_type = 's'
+         and t_w_secyear.sale_type = 'w'
+         and t_s_firstyear.dyear = 1999
+         and t_s_secyear.dyear = 1999+1
+         and t_w_firstyear.dyear = 1999
+         and t_w_secyear.dyear = 1999+1
+         and t_s_firstyear.year_total > 0
+         and t_w_firstyear.year_total > 0
+         and case when t_w_firstyear.year_total > 0 then t_w_secyear.year_total / t_w_firstyear.year_total else 0.0 end
+             > case when t_s_firstyear.year_total > 0 then t_s_secyear.year_total / t_s_firstyear.year_total else 0.0 end
+ order by t_s_secyear.customer_id
+         ,t_s_secyear.customer_first_name
+         ,t_s_secyear.customer_last_name
+         ,t_s_secyear.customer_email_address
+limit 100;
+

resources/queries/q12.sql

@@ -0,0 +1,33 @@
+--TPC-DS Q12
+select  i_item_id
+      ,i_item_desc 
+      ,i_category 
+      ,i_class 
+      ,i_current_price
+      ,sum(ws_ext_sales_price) as itemrevenue 
+      ,sum(ws_ext_sales_price)*100/sum(sum(ws_ext_sales_price)) over
+          (partition by i_class) as revenueratio
+from	
+	web_sales
+    	,item 
+    	,date_dim
+where 
+	ws_item_sk = i_item_sk 
+  	and i_category in ('Jewelry', 'Books', 'Women')
+  	and ws_sold_date_sk = d_date_sk
+	and d_date between cast('2002-03-22' as date) 
+				and date_add(cast('2002-03-22' as date),30)
+group by 
+	i_item_id
+        ,i_item_desc 
+        ,i_category
+        ,i_class
+        ,i_current_price
+order by 
+	i_category
+        ,i_class
+        ,i_item_id
+        ,i_item_desc
+        ,revenueratio
+limit 100;
+

resources/queries/q13.sql

@@ -0,0 +1,51 @@
+--TPC-DS Q13
+select avg(ss_quantity)
+       ,avg(ss_ext_sales_price)
+       ,avg(ss_ext_wholesale_cost)
+       ,sum(ss_ext_wholesale_cost)
+ from store_sales
+     ,store
+     ,customer_demographics
+     ,household_demographics
+     ,customer_address
+     ,date_dim
+ where s_store_sk = ss_store_sk
+ and  ss_sold_date_sk = d_date_sk and d_year = 2001
+ and((ss_hdemo_sk=hd_demo_sk
+  and cd_demo_sk = ss_cdemo_sk
+  and cd_marital_status = 'U'
+  and cd_education_status = '4 yr Degree'
+  and ss_sales_price between 100.00 and 150.00
+  and hd_dep_count = 3   
+     )or
+     (ss_hdemo_sk=hd_demo_sk
+  and cd_demo_sk = ss_cdemo_sk
+  and cd_marital_status = 'S'
+  and cd_education_status = 'Unknown'
+  and ss_sales_price between 50.00 and 100.00   
+  and hd_dep_count = 1
+     ) or 
+     (ss_hdemo_sk=hd_demo_sk
+  and cd_demo_sk = ss_cdemo_sk
+  and cd_marital_status = 'D'
+  and cd_education_status = '2 yr Degree'
+  and ss_sales_price between 150.00 and 200.00 
+  and hd_dep_count = 1  
+     ))
+ and((ss_addr_sk = ca_address_sk
+  and ca_country = 'United States'
+  and ca_state in ('CO', 'MI', 'MN')
+  and ss_net_profit between 100 and 200  
+     ) or
+     (ss_addr_sk = ca_address_sk
+  and ca_country = 'United States'
+  and ca_state in ('NC', 'NY', 'TX')
+  and ss_net_profit between 150 and 300  
+     ) or
+     (ss_addr_sk = ca_address_sk
+  and ca_country = 'United States'
+  and ca_state in ('CA', 'NE', 'TN')
+  and ss_net_profit between 50 and 250  
+     ))
+;
+