Saturday, March 25, 2017

Loading Data Script for Snowflake type Date Dimension

Update: If you need the script for the same with financial year elements, read the new post.

Date dimension is the most common dimension in data warehousing and it is generally designed as a single table. However, if it needs to be used with multiple Fact Tables with different levels, Date dimension table should be broken into multiple tables that creates a Snowflake Schema. If the table is broken into multiple tables such as Year, Quarter, Month and Date, loading them is bit difficult. A script for loading a single table is available in many sites but it is bit difficult to find a script for loading multiple tables. I had a same requirement and could not find a proper script, hence wrote one.

Here is the script if you need the same;

Here is the script for creating tables;
CREATE TABLE dbo.DimYear
(
 YearKey smallint 
 , Year smallint not null
 , Constraint pk_DimYear Primary Key (YearKey)
);
GO

CREATE TABLE dbo.DimQuarter
(
 QuarterKey smallint 
 , YearKey smallint not null
 , Quarter smallint not null
 , YearQuater varchar(20) not null
 , QuarterName varchar(20) not null
 , Constraint pk_DimQuarter Primary Key (QuarterKey)
 , Constraint fk_DimQuarter_DimYear Foreign Key (YearKey)
  References dbo.DimYear (YearKey)
);
GO

CREATE TABLE dbo.DimMonth
(
 MonthKey int 
 , QuarterKey smallint not null
 , MonthNumber smallint not null
 , MonthName varchar(20) not null
 , YearMonth varchar(20) not null
 , MonthShortName char(3) not null
 , Constraint pk_DimMonth Primary Key (MonthKey)
 , Constraint fk_DimMonth_DimQuarter Foreign Key (QuarterKey)
  References dbo.DimQuarter (QuarterKey)
);
GO

CREATE TABLE dbo.DimDate
(
 DateKey int 
 , MonthKey int not null
 , Date date not null
 , WeekDayNumber smallint not null
 , WeekDayName varchar(20) not null
 , DayOfMonth smallint not null
 , DayOfYear smallint not null
 , IsWeekend bit not null
 , IsHoliday bit not null
 , WeekNumberOfYear smallint not null
 , Constraint pk_DimDate Primary Key (DateKey)
 , Constraint fk_DimDate_DimMonth Foreign Key (MonthKey)
  References dbo.DimMonth (MonthKey)
);
GO


And the script for loading all tables.
SET DATEFIRST 1;

DECLARE @StartDate date = '2010-01-01';
DECLARE @EndDate date = '2019-12-31';
DECLARE @YearKey smallint;
DECLARE @Quarter smallint, @QuarterKey smallint;
DECLARE @Month int, @MonthKey int;
DECLARE @Date int, @DateKey int;

WHILE (@StartDate <= @EndDate)
BEGIN

 -- Inserting years
 SET @YearKey = YEAR(@StartDate);
 IF NOT EXISTS (SELECT * FROM dbo.DimYear WHERE YearKey = @YearKey)
  INSERT INTO dbo.DimYear (YearKey, [Year]) VALUES (@YearKey, @YearKey);


 -- Inserting quarters
 SET @QuarterKey = Convert(smallint, Convert(varchar(4), YEAR(@StartDate)) + Convert(varchar(1), DATEPART(q, @StartDate)))
 SET @Quarter = DATEPART(q, @StartDate);

 IF NOT EXISTS (SELECT * FROM dbo.DimQuarter WHERE QuarterKey = @QuarterKey)
  INSERT INTO dbo.DimQuarter (QuarterKey, YearKey, [Quarter], YearQuater, QuarterName) 
  VALUES (@QuarterKey, @YearKey, @Quarter, Convert(varchar(4), YEAR(@StartDate)) + 'Q' + Convert(varchar(4), @Quarter)
   , CASE @Quarter WHEN 1 THEN 'First Quarter' WHEN 2 THEN 'Second Quarter' WHEN 3 THEN 'Third Quarter' ELSE 'Forth Quarter' END);
  

 ---- Inserting months
 SET @MonthKey = Convert(int, Convert(varchar(4), YEAR(@StartDate)) + (CASE LEN(MONTH(@StartDate)) WHEN 1 THEN '0' ELSE '' END) + Convert(varchar(2), MONTH(@StartDate)));
 SET @Month = MONTH(@StartDate)
 IF NOT EXISTS (SELECT * FROM dbo.DimMonth WHERE MonthKey = @MonthKey)
  INSERT INTO dbo.DimMonth (MonthKey, QuarterKey, MonthNumber, MonthName, YearMonth, MonthShortName) 
  VALUES (@MonthKey, @QuarterKey, @Month, DATENAME(MONTH, @StartDate)
  , Convert(varchar(4), YEAR(@StartDate)) + ' ' + LEFT(DATENAME(MONTH, @StartDate), 3)
  , LEFT(DATENAME(MONTH, @StartDate), 3));
  
 ---- Inserting dates
 SET @DateKey = Convert(int, Convert(varchar(8), @StartDate, 112))
 IF NOT EXISTS (SELECT * FROM dbo.DimDate WHERE DateKey = @DateKey)
  INSERT INTO dbo.DimDate (DateKey, MonthKey, Date, WeekDayNumber, WeekDayName, DayOfMonth
   , DayOfYear, IsWeekend, IsHoliday, WeekNumberOfYear) 
  VALUES (@DateKey, @MonthKey, @StartDate, DatePart(WEEKDAY, @StartDate), DateName(WEEKDAY, @StartDate), DatePart(DAY, @StartDate)
   , DatePart(DAYOFYEAR, @StartDate), CASE WHEN DatePart(WEEKDAY, @StartDate) IN (6, 7) THEN 1 ELSE 0 END, 0
   , DatePart(WEEK, @StartDate));

 SET @StartDate = DATEADD(dd, 1, @StartDate);
END;
GO


No comments: