Sample worksheets

sql/data_challenge/README.md

@@ -0,0 +1,7 @@
+Exasol Data Challenge Sample Data.   
+
+The tutorial.sql contains  
+exercises on loading data,  
+writing queries,  
+and applying Python functions  
+for analysis.

sql/data_challenge/import.sql

@@ -0,0 +1 @@
+SELECT 1;

sql/data_challenge/tutorial.sql

@@ -0,0 +1,68 @@
+/*
+EXASOL DATA CHALLENGE
+*/
+
+-- let's create a schema for our data as well as some empty tables
+CREATE SCHEMA DATA_CHALLENGE;
+CREATE TABLE DATA_CHALLENGE.ITEM (I_ITEM_SK SMALLINT , I_ITEM_ID CHAR(16) , I_REC_START_DATE DATE, I_REC_END_DATE DATE, I_ITEM_DESC VARCHAR(200), I_CURRENT_PRICE DECIMAL(7,2), I_WHOLESALE_COST DECIMAL(7,2), I_BRAND_ID INTEGER, I_BRAND CHAR(50), I_CLASS_ID INTEGER, I_CLASS CHAR(50), I_CATEGORY_ID INTEGER, I_CATEGORY CHAR(50), I_MANUFACT_ID INTEGER, I_MANUFACT CHAR(50), I_SIZE CHAR(20), I_FORMULATION CHAR(20), I_COLOR CHAR(20), I_UNITS CHAR(10), I_CONTAINER CHAR(10), I_MANAGER_ID INTEGER, I_PRODUCT_NAME CHAR(50), DISTRIBUTE BY I_ITEM_SK);
+CREATE TABLE DATA_CHALLENGE.CUSTOMER (C_CUSTOMER_SK SMALLINT , C_CUSTOMER_ID CHAR(16) , C_CURRENT_CDEMO_SK SMALLINT, C_CURRENT_HDEMO_SK SMALLINT, C_CURRENT_ADDR_SK SMALLINT, C_FIRST_SHIPTO_DATE_SK SMALLINT, C_FIRST_SALES_DATE_SK SMALLINT, C_SALUTATION CHAR(10), C_FIRST_NAME CHAR(20), C_LAST_NAME CHAR(30), C_PREFERRED_CUST_FLAG CHAR(1), C_BIRTH_DAY INTEGER, C_BIRTH_MONTH INTEGER, C_BIRTH_YEAR INTEGER, C_BIRTH_COUNTRY VARCHAR(20), C_LOGIN CHAR(13), C_EMAIL_ADDRESS CHAR(50), C_LAST_REVIEW_DATE_SK SMALLINT, DISTRIBUTE BY C_CUSTOMER_SK);
+CREATE TABLE DATA_CHALLENGE.HOUSEHOLD_DEMOGRAPHICS (HD_DEMO_SK SMALLINT , HD_INCOME_BAND_SK SMALLINT, HD_BUY_POTENTIAL CHAR(15), HD_DEP_COUNT INTEGER, HD_VEHICLE_COUNT INTEGER, DISTRIBUTE BY   HD_DEMO_SK);
+CREATE TABLE DATA_CHALLENGE.WEB_SALES (WS_SOLD_DATE_SK SMALLINT, WS_SOLD_TIME_SK SMALLINT, WS_SHIP_DATE_SK SMALLINT, WS_ITEM_SK SMALLINT , WS_BILL_CUSTOMER_SK SMALLINT, WS_BILL_CDEMO_SK SMALLINT, WS_BILL_HDEMO_SK SMALLINT, WS_BILL_ADDR_SK SMALLINT, WS_SHIP_CUSTOMER_SK SMALLINT, WS_SHIP_CDEMO_SK SMALLINT, WS_SHIP_HDEMO_SK SMALLINT, WS_SHIP_ADDR_SK SMALLINT, WS_WEB_PAGE_SK SMALLINT, WS_WEB_SITE_SK SMALLINT, WS_SHIP_MODE_SK SMALLINT, WS_WAREHOUSE_SK SMALLINT, WS_PROMO_SK SMALLINT, WS_ORDER_NUMBER INTEGER , WS_QUANTITY INTEGER, WS_WHOLESALE_COST DECIMAL(7,2), WS_LIST_PRICE DECIMAL(7,2), WS_SALES_PRICE DECIMAL(7,2), WS_EXT_DISCOUNT_AMT DECIMAL(7,2), WS_EXT_SALES_PRICE DECIMAL(7,2), WS_EXT_WHOLESALE_COST DECIMAL(7,2), WS_EXT_LIST_PRICE DECIMAL(7,2), WS_EXT_TAX DECIMAL(7,2), WS_COUPON_AMT DECIMAL(7,2), WS_EXT_SHIP_COST DECIMAL(7,2), WS_NET_PAID DECIMAL(7,2), WS_NET_PAID_INC_TAX DECIMAL(7,2), WS_NET_PAID_INC_SHIP DECIMAL(7,2), WS_NET_PAID_INC_SHIP_TAX DECIMAL(7,2), WS_NET_PROFIT DECIMAL(7,2), DISTRIBUTE BY   WS_ITEM_SK);
+
+-- also let's create a connection to S3
+CREATE OR REPLACE CONNECTION S3_DATA_CHALLENGE
+TO 'http://exa-data-challenge.s3-eu-central-1.amazonaws.com';
+
+/*
+now it's your turn
+
+1. load data into the tables. Data is stored under the previously defined S3_DATA_CHALLENGE connection.
+Files are called customer.csv, item.csv, household_demographics.csv and web_sales.csv
+There is a single CSV file per table, files contain a header and are separated by semicolon. 
+Rows are terminated by Unix LF, file are UTF-8 encoded
+*/
+
+
+/*
+2. Now that we have loaded the data, let's familiarize ourselves and write some queries.
+You can find the ER diagram for the data here (2.3.5): https://www.tpc.org/TPC_Documents_Current_Versions/pdf/TPC-DS_v4.0.0.pdf
+*/
+
+/*
+Q1: Get the first and last name of customers that have at least one vehicle in the household.
+Hint: you can join the customer and household data on C_CURRENT_HDEMO_SK = HD_DEMO_SK  
+*/
+
+
+/*
+Q2: Now let's refine Q1 and additionally filter down to those customers that had web sales of at least 250$ of list price
+Hint: you can join customer and web_sales data on ws_bill_customer_sk=c_customer_sk
+*/
+
+
+/*
+Q3: Now let's extend Q3 and add the item category to the order
+Hint: you can join web_sales and item data on WS_ITEM_SK=I_ITEM_SK
+Make sure that the categories returned are NOT NULL
+*/
+
+
+/*
+3. Let's apply some Python to the data. Write a Python UDF to determine the Levenshtein distance between two strings.
+*/
+
+
+/*
+4. Now let's bring our Python function and Q3 together.
+We want to obtain the results from Q3 and want to add a column for the Levenshtein distance between I_CATEGORY and the word "Shoe".
+Hint: Make sure to trim I_CATEGORY
+*/
+
+/*
+5. Final challenge, let's count the results of our previous query that have a Levenshtein distance of 1.
+*/
+
+
+/*
+You have mastered the challenge, congratulations!
+*/

sql/retail_mini/README.md

@@ -0,0 +1,9 @@
+Sample data used in EXAcademy.   
+
+The data consists of   
+some sample sales data.
+
+The tutorial.sql contains  
+some queries used 
+in the course  
+"Exasol Performance Management".

sql/retail_mini/import.sql

@@ -0,0 +1,80 @@
+create schema retail;
+
+CREATE TABLE CITIES (
+               CITY_ID      DECIMAL(9,0),
+               COUNTRY_CODE VARCHAR(2) UTF8,
+               ZIP_CODE     VARCHAR(20) UTF8,
+               CITY_NAME    VARCHAR(200) UTF8,
+               DISTRICT     VARCHAR(50) UTF8,
+               AREA         VARCHAR(50) UTF8,
+               AREA_SHORT   VARCHAR(50) UTF8,
+               LAT          DECIMAL(9,6),
+               LON          DECIMAL(9,6)
+           );
+
+CREATE TABLE ARTICLE (
+            ARTICLE_ID         DECIMAL(9,0),
+            DESCRIPTION        VARCHAR(100) UTF8,
+            EAN                DECIMAL(18,0),
+            BASE_SALES_PRICE   DECIMAL(9,2),
+            PURCHASE_PRICE     DECIMAL(9,2),
+            PRODUCT_GROUP      DECIMAL(9,0),
+            PRODUCT_CLASS      DECIMAL(9,0),
+            QUANTITY_UNIT      VARCHAR(100) UTF8,
+            TMP_OLD_NR         DECIMAL(9,0),
+            PRODUCT_GROUP_DESC VARCHAR(100) UTF8,
+            DISTRIBUTION_COST  DECIMAL(9,2)
+          );
+
+CREATE TABLE MARKETS (
+            MARKET_ID   DECIMAL(9,0),
+            LONGITUDE   DECIMAL(9,6),
+            LATITUDE    DECIMAL(9,6),
+            POSTAL_CODE CHAR(5) UTF8,
+            CITY        VARCHAR(50) UTF8,
+            AREA        VARCHAR(50) UTF8,
+            CITY_ID     DECIMAL(9,0),
+            POPULATION  DECIMAL(18,0)
+           );
+
+CREATE TABLE SALES (
+            SALES_ID                DECIMAL(18,0),
+            SALES_DATE              DATE,
+            SALES_TIMESTAMP         TIMESTAMP,
+            PRICE                   DECIMAL(9,2),
+            MONEY_GIVEN             DECIMAL(9,2),
+            RETURNED_CHANGE         DECIMAL(9,2),
+            LOYALTY_ID              DECIMAL(18,0),
+            MARKET_ID               DECIMAL(9,0),
+            TERMINAL_ID             DECIMAL(9,0),
+            EMPLOYEE_ID             DECIMAL(9,0),
+            TERMINAL_DAILY_SALES_NR DECIMAL(9,0),
+            DISTRIBUTE BY SALES_ID
+          );
+
+CREATE TABLE SALES_POSITIONS (
+            SALES_ID    DECIMAL(18,0),
+            POSITION_ID DECIMAL(9,0),
+            ARTICLE_ID  DECIMAL(9,0),
+            AMOUNT      DECIMAL(9,0),
+            PRICE       DECIMAL(9,2),
+            VOUCHER_ID  DECIMAL(9,0),
+            CANCELED    BOOLEAN,
+            DISTRIBUTE BY SALES_ID
+          );
+
+CREATE TABLE DIM_DATE (
+           SALES_DATE DATE
+          );
+
+
+
+CREATE OR REPLACE CONNECTION S3_SAMPLE_BUCKET TO 'https://exasol-test-sample-worksheet.s3.eu-central-1.amazonaws.com';
+
+IMPORT INTO CITIES from CSV at S3_SAMPLE_BUCKET file 'retail_mini/CITIES.csv';
+IMPORT INTO ARTICLE from CSV at S3_SAMPLE_BUCKET file 'retail_mini/ARTICLE.csv';
+IMPORT INTO MARKETS from CSV at S3_SAMPLE_BUCKET file 'retail_mini/MARKETS.csv';
+IMPORT INTO SALES from CSV at S3_SAMPLE_BUCKET file 'retail_mini/SALES.csv';
+IMPORT INTO SALES_POSITIONS from CSV at S3_SAMPLE_BUCKET file 'retail_mini/SALES_POSITIONS.csv';
+IMPORT INTO DIM_DATE from CSV at S3_SAMPLE_BUCKET file 'retail_mini/DIM_DATE.csv';
+

sql/retail_mini/tutorial.sql

@@ -0,0 +1,28 @@
+OPEN SCHEMA RETAIL;
+-- DISTRIBUTE SALES_POSITIONS and SALES by sales_id, which is our join column
+ALTER TABLE SALES_POSITIONS DISTRIBUTE BY SALES_ID;
+ALTER TABLE SALES DISTRIBUTE BY SALES_ID;
+
+-- Verify if tables are well distributed
+SELECT iproc(), count(*) FROM sales_positions GROUP BY iproc();
+SELECT iproc(), count(*) FROM sales GROUP BY iproc();
+
+-- Enable profiling
+ALTER SESSION SET PROFILE = 'on';
+
+-- Run first query
+SELECT SUM(sp.amount) FROM SALES s JOIN sales_positions sp ON S.sales_id = sp.sales_id WHERE sales_date = '2015-03-05';
+
+FLUSH STATISTICS;
+
+-- Show query details
+SELECT * FROM EXA_USER_PROFILE_LAST_DAY WHERE session_id=current_session AND stmt_id=current_statement-4;
+
+-- Run second query
+SELECT S.market_id, SUM(P.amount) AS total_amount FROM SALES_POSITIONS P JOIN SALES S ON P.sales_id = S.sales_id GROUP BY S.market_id;
+
+FLUSH STATISTICS;
+
+-- Show query details
+SELECT * FROM EXA_USER_PROFILE_LAST_DAY WHERE session_id=current_session AND stmt_id=current_statement-4;
+

sql/tpc-h-10GB/README.md

@@ -0,0 +1,3 @@
+# TPC-H Tutorial
+
+Description of the tutorial 

sql/tpc-h-10GB/import.sql

@@ -0,0 +1,3 @@
+/*
+Import TPC-H 10GB
+*/