InstantForum.NET v2.9.0SQLServerCentralhttp://www.sqlservercentral.com/Forums/notifications@sqlservercentral.comWed, 19 Jun 2013 19:47:54 GMT20http://www.sqlservercentral.com/Forums/Topic1457502-2797-1.aspxHi,I am new to Data Mining and would like to understand the output thet gets generated with different data mining model structure such as Decision Tree orClustering or Naive Bayes.Not getting how to analyze the data in model viewer.I used AdventureworksDW2008 data base.Can anybody explain in detail.Tue, 28 May 2013 13:55:09 GMTsej2008http://www.sqlservercentral.com/Forums/Topic1455313-2797-1.aspxHello All,Long time reader, first time writer!!I am having some trouble with SSAS and data mining - specifically the Microsoft Clustering package.I intend to ultimately do my work in AMO and MDX, but for now, just happy to understand how it works in the BIDS via Visual Studio. One step at a time!The whole problem is around clustering both "vertically" and "horizontally" (separately) from a table that is organized vertically. My main source data table in my OLTP database looks like =>[b]ID_NUM[/b][i]{numbers 1 - 20,000}[/i][b]TECK_ID[/b][i]{numbers 1-500, {for each ID_NUM}}[/i][size="1"](though just grabbed a few of these for playing around with the data in the screencaps)[/size][b]TECK_VALUE[/b][i]{a double, the 'fact' bit}[/i]So- 10 million rows, of two ints and a double.Which looks like this- [url=http://i.imgur.com/KG1LhaJ.jpg]http://i.imgur.com/KG1LhaJ.jpg[/url]So I create a new Analysis Services project in Visual Studio, set up a Data Source, and bring in the above table, as well as two "dimension tables" (identity of what id_num is, names of what each teck_id is) into a Data Source View and link it up, matching up the appropriate keys.Which looks like this- [url=http://i.imgur.com/Q0vgwIc.jpg]http://i.imgur.com/Q0vgwIc.jpg[/url]Next I want to manipulate how my data is represented, so I go to set up a cube from this Data Source View. I create dimensions based on my two "dimension" tables (the above "id_num" primary key one, and the "teck_id" primary key one), and create a single measure (as sum) of the teck_value column from my main table. This all seems to compile successfully.Which looks like this- [url=http://i.imgur.com/y5pUSjh.jpg]http://i.imgur.com/y5pUSjh.jpg[/url]The reason I think everything has worked well is I can arrange my data how I want by browsing the cube. I am able to define my "rows" as both the id_num, or as the "teck_id", with the other one filling up the columns. The measure "Teck_value" always makes up the dataset of the table. This is exactly how I want it, the flexibility to arrange my data both ways. Which looks like this- [url=http://i.imgur.com/ugLUkgg.jpg]http://i.imgur.com/ugLUkgg.jpg[/url]And this- [url=http://i.imgur.com/RwQgj58.jpg]http://i.imgur.com/RwQgj58.jpg[/url]Beautiful! Now I wish to do some mining on this basis!I wish to, quite simply, using Microsoft Clustering to (separately) - - Assign each TECK_ID a cluster number based on how it varies on each ID_NUM - Assign each ID_NUM a cluster based on how it varies on each TECK_IDSeemingly a simple requirement - just changing what is represented as "rows" and what as "columns" - which I already appear to be able to do through the cube browser. This seems to be one of the main points of OLAP rather than OLTP from my uneducated perspective!Yet when I try to set this up I fail utterly!The Clustering Wizard leaves me confounded and I come up with nonsense results. I am given the option of selecting a key (for which I can choose either of the above), but no option to parse by the other dimension. Indeed, the only thing I can choose to mine on is TECK_VALUE, which isn't any good as that doesn't separate out the different fields!My wizard looks like this- [url=http://i.imgur.com/lHfasv0.jpg]http://i.imgur.com/lHfasv0.jpg[/url]So, I am left in a pickle. I really don't want to go back and line up my OLTP databases horizontally because 1) this would mean having 20k columns when I try to categorize my TECK_IDs. and 2) I was hoping SSAS and OLAP can give me the flexibility I need to mine the fields that I want - isn't that part of the reason you set up a cube "chop up the data how you like" ?SQL Server Central - Please help an OLAP noob make his first steps into this dangerous new world!!:arrow:Tue, 21 May 2013 23:51:07 GMThardcore.ninjahttp://www.sqlservercentral.com/Forums/Topic1410429-2797-1.aspxWhat is Spatial data mining?For more Data Mining Interview Questions & Answers visit http://www.coolinterview.com/type.asp?iType=811Wed, 23 Jan 2013 02:51:00 GMTsajisharmahttp://www.sqlservercentral.com/Forums/Topic1373061-2797-1.aspxCoz Its analyzing only what we pushed data and shows diagrammatically.. not for Future year , If possible can any one suggest me to do...Tue, 16 Oct 2012 01:15:45 GMTSaravanan_tvrhttp://www.sqlservercentral.com/Forums/Topic1391380-2797-1.aspxHello everyone,I am wondering, is it possible to have data mining on a single table with a large amount of data?The given table is about sales and contains all the needed info (SellerType, ShopLocation, ItemCategory, ItemCondition, Sold, Price, ShippingCost).I tried to create a data cube but I can only get one dimension.What I want to exam is the affect shipping cost has on sales based on category, or the price based on condition and category, etc.Any thoughts?Thank you in advance.Fri, 30 Nov 2012 08:46:02 GMTChriz L.http://www.sqlservercentral.com/Forums/Topic1387485-2797-1.aspxI am working through 70-448 book and am now in the Data Mining chapters. I think I must have modified some data along the way because some of the citical built in views return no rows. I am looking for a clean BAK file to restore. Does anyone know where I can get one?Wed, 21 Nov 2012 09:28:00 GMTrmatthias001http://www.sqlservercentral.com/Forums/Topic1000386-2797-1.aspx Hi All As I am very new to Data Mining. I like to know 1. What is Data Mining. 2. How it is different from Business Intelligence. 3. What are way's to implement it. 4. How is market (Job) for the same. ThanksThu, 07 Oct 2010 06:47:10 GMTsaurabh.deshpandehttp://www.sqlservercentral.com/Forums/Topic1269585-2797-1.aspxHi all, I'm looking for more education in data mining / predictive analytics, and am considering the online MS in Predictive Analytics at Northwestern University. Does anyone have any experience with this program, and care to share their thoughts on it? It's fairly expensive, and so I'm looking to gather as much info on it before committing to it. I did take an online course in data mining at Central Connecticut State, which wasn't that bad, but I'm considering other programs. Any info appreciated. If there's a better place to post this question, please let me know.Thanks, SteveTue, 20 Mar 2012 08:13:16 GMTzintphttp://www.sqlservercentral.com/Forums/Topic1216664-2797-1.aspxHello -I have a design question and want to understand whether my problem could be solved using SSAS data mining and if yes, which algorithm will be useful.I have a revenue fact table with dimension keys for say, dim A, dim B, dim C and dim D along with date dim. ( I have already built a cube for this) I want to predict my revenue for dim A and also simultaneously see effect of dim B, dim C and dim D on the behavior of this prediction. so, for example I want to see prediction of my revenue by region. But then I should be able to select a product and see the prediction by region for that product and so on for other dimensions.I tried time series algorithm but found that i can have one time series with one date dim and one other dimension only. I can't have dim A and dim B simultaneously on time series along with dim date. (Is it true? or I'm missing something).What other possible algorithms i can use for this kind of scenario and how to model that in SSAS?Any help is appreciated.Thanks,AmeyMon, 05 Dec 2011 13:31:20 GMTamy3672http://www.sqlservercentral.com/Forums/Topic1323426-2797-1.aspxI want to know exactly what does data ware administrator do,what is the role of their job and what i need to study for that , I had studied a subject called "Data ware housing and data mining" still i have no idea about this position please do reply your valuable comments:-)Sat, 30 Jun 2012 03:02:21 GMTzaid4ehttp://www.sqlservercentral.com/Forums/Topic1313509-2797-1.aspxI am trying to build and run a dmx linear regression to predict some data. data is in the format: key_id, 1979,1980 - 2010, sales2010, sales2011 example 1,100,200, ... , 500,600 (many rows of this). the x values are 1979 - 2010 numbers. the y value would be sales2010 How would you write this in dmx language? (how do you designate x and y value data?)Sat, 09 Jun 2012 10:32:44 GMTfoxjazzGhttp://www.sqlservercentral.com/Forums/Topic1276362-2797-1.aspxI have a data base (testmining) with 2 tables in my engine service,these 2 table are connected with customer_id column as a primary key in customer and foreign key in purchaseand i have a database (mining) in my analyses service on my sql server 2008 ,so i create a mining model in my mining database on analyses services :Create mining model MarketBasketModel(CustomerId long key,Gender text discrete,Income long continuous,MemberCard text discrete,Purchases table Predict_Only (ProductName text key,Quantity long continuous))Using Microsoft_Decision_Treesso when i want to execute this command :Insert into MarketBasketModel_Structure( CustomerId, Gender, Income, MemberCard,Purchases( ProductName, Quantity) )OpenRowset('SQLOLEDB', 'Server=EHSAN-PC;Integrated Security=SSPI','Shape{ Select Customer_id, Gender, Income, member_cart From testmining.dbo.Customer }Append ({ Select Product_Name, Quantity From testmining.dbo.Purchase }Relate testmining.dbo.Customer.Customer_Id to testmining.dbo.Purchase.Customer_id ) as Purchase')i got this error :OLE DB error: OLE DB or ODBC error: Syntax error or access violation; 42000Sun, 01 Apr 2012 08:36:32 GMTLarry Page(Ehsan.Akbar)http://www.sqlservercentral.com/Forums/Topic1268741-2797-1.aspxI am totally new to this data-mining business. I would like for someone to point me in the right direction, plese. In my business - I will have a database with several tables (let's assume MS SQL Server). For the sake of example, I have a 'person' table and an 'purchases' table (each person can make several different purchases).Here is an example of the 'person' table:* ID* First Name* Last Name* Address*Date of BirthHere is an example of the 'purchase' table:* Date of Purchase* Time of Purchase* Store Location* Number of Items Purchased* Total Purchase AmountWhat I would like to do is:I would like to perform 'data-mining' in order to find out the "categories", or "clusters" of characteristics, that define each [b]'purchase amount'[/b].Meaning - my target 'column' is the 'purchase amount' column.Now I want to know all the different clusters of fields that produce each 'amount' in this column.For example - I would like to know what is common for all the people who bought between 2,000$ and 2,500$ ?Maybe they all came from the same neighbourhood ?Maybe all of them were young & came from the same neighbourhood?Maybe there are 2 distinct different groups that fit the '2000$-2500$' spending group ?I am almost sure there are different categories (or distinct clusters) that match each price group...one might be old people that come to buy at night, another might be middle-aged people who buy more than 10 items, and another might be middle-aged people who buy one Sundays.From what I understand, this falls under the 'data-mining' region ([b]clustering maybe?[/b])Is this true ? and if so, what are the tools I must use in order to find out these set of parameters that define the different groups for each pricing category?As you can see, I have no idea which tools \ applications I should use.Someone recommended installing an add-in for Excel that could do the trick, but this seems rather too simple.Someone else mentioned BI (don't know what exactly to do there)...I know there is also the 'Microsoft Analysis Services'. Does that help me in any way ?Thank you very much !JohnSun, 18 Mar 2012 10:47:52 GMTjsminer2011http://www.sqlservercentral.com/Forums/Topic1265906-2797-1.aspxAny of you guys tried mining system logs pushed to a DB to correlate events across a network? I hoping to find someone who has tried this as to learn from their mistakes. Let me know if you guys have any ideas.ThanksTue, 13 Mar 2012 07:40:51 GMTcw.izatthttp://www.sqlservercentral.com/Forums/Topic1253974-2797-1.aspxI basically want this thread to be a good way for the newbs like me to get up to speed with some of the knowledge the veterans have. For example did you guys find books or web posts that when you read them helped you understand data mining better than before? If so post them up. I am trying to get myself up to speed on Data mining because i think the business is going to want it in the future. Any help in that process from you guys would be awesome and i thank you ahead of time. ChrisFri, 17 Feb 2012 09:14:57 GMTcw.izatthttp://www.sqlservercentral.com/Forums/Topic1253479-2797-1.aspxI'm still fairly new with drillthrough actions. I want to create an action that runs a query and extracts columns from a table which is related by key but for which it's not practical to create a dimension. Is there a way to have a drillthrough query? Say, for example, I have a location dimension and user dimension and I aggregate and show that I have 1500 people living in my region and I want to right-click and drillthrough to a query that takes those associated userID's and pulls back the associated addresses and phone numbers (which is NOT in it's own dimension).Ideas?DonalithThu, 16 Feb 2012 14:55:43 GMTErin Ramsayhttp://www.sqlservercentral.com/Forums/Topic1235426-2797-1.aspxCan we fing clusters of following data?Id P1 P2x 5.6 4.5x 1.6 4.5y 5.6 4.5having 2 clusters?Fri, 13 Jan 2012 01:28:45 GMTvnjhttp://www.sqlservercentral.com/Forums/Topic1176943-2797-1.aspxI have a Virtual Machine withServer 2003SQL Server 2008 R2Office 2007Visual Studio 2008... which worked fine for a while...Like a knucklehead, I installed 2010 on it, and the data mining extensions for Excel failed. (Big surprise!)Uninstalled 2010, reinstalled 2007, but still no joy. It seems that the 2010 install overwrote something and now the Data Mining Extensions in Excel no longer work.Right now I'm thinking my best option is to rebuild the VM.Sorry if this is more an Excel question... I'm just kind of baffled! Any pointers would help!ThanksSat, 17 Sep 2011 19:26:03 GMTpietlindenhttp://www.sqlservercentral.com/Forums/Topic1176209-2797-1.aspxIs any one know about Clustering methods.. 1.Scalable EM 2.Non-Scalable EM 3.Scalable k-means 4.Non-Scalable k-means..Fri, 16 Sep 2011 00:30:11 GMTmiriyalasriharihttp://www.sqlservercentral.com/Forums/Topic1173250-2797-1.aspxin my Microsoft Association RuleAccountID as key,YardID as Predictable Column..by using MS Association rule, i created one mining structure that containsItemset as YardID < 29size as 1support as 8793here i don't know how to calculate this support...plz help me...Mon, 12 Sep 2011 03:33:30 GMTmiriyalasriharihttp://www.sqlservercentral.com/Forums/Topic1145165-2797-1.aspxI got an error while deploying my report: The permissions granted to user machineNameuserName are insufficient for performing this operation. After reading the posts in the forum, I realized that my RS setup may be incorrect. On http://localhost/reports, Contents and Properties tabs are missing... Please let me know how I can correct the problems. I am using SQL Server 2008, and I have admin rights on my local machineWed, 20 Jul 2011 09:34:10 GMTasrananthahttp://www.sqlservercentral.com/Forums/Topic1047887-2797-1.aspxHas anyone read the book [url=http://www.amazon.com/Data-Mining-Microsoft-Server-2008/dp/0470277742/ref=sr_1_1?s=books&ie=UTF8&qid=1295014131&sr=1-1]Data Mining with Microsoft SQL Server 2008[/url]?If yes, it it worth the read? Or should I avoid it?Fri, 14 Jan 2011 07:11:13 GMTKoen Verbeeckhttp://www.sqlservercentral.com/Forums/Topic1057035-2797-1.aspxI have been trying to get opinions on how to handle this issue and have gotten various opinions.I have multiple databases (5) that have similar information in them. They all have vendors (sony), retailers (walmar) and stores (Sears store#100). I am setting up a data warehouse (dimensions and fact tables) that will be using SSAS, SSIS and SSRS to build, maintain and report from.I have been researching this and have gotten good information including Vincent Rinardis book on building data warehouses with SQL Server.My issue is in how to best handle entities (vendors, retails, stores) that span the multiple databases and each have their own primary keys. In Vincents book, he talks about setting up a SourceID that tells where the data for each record came from. This seems fine for the Fact table but I am not sure how to handle this in the dimensions. If I were to use the sourceID for the Sears Retailer, I could have 5 different records in the DimRetailer table - one from each database where the sourceID would be something like: 1 for DB1, 2 for DB2 etc.I want to report on a retailer (Sears for example) or for a particular Vendor (i.e. Sony). Wouldn't having multiple records for the same Vendor or Retailer be an issue with any cubes I set up or reports I generate from the cubes?I would assume that we would want only one record per vendor in my DimVendor and one record per retailer in my DimRetailer tables. If I had multiple records for each retailer or vendor, wouldn't that screw up the cubes?I had thought about having cross reference tables for them with the PK as the surrogate key.For example:RetailerXref table1) PK (identity) - This would then be the Surrogate Key for the DimRetailer table2) RetailerID (from a Source and would be your TransactionalID)3) Source ID (1 for DB1, 2 for DB2, etc)VendorXref table1) PK (identity) - This would then be the Surrogate Key for the DimVendor table2) VendorID (from a Source and would be your TransactionalID)3) Source ID (1 for DB1, 2 for DB2, etc)In my ETL, I would use the RetailerXref table with my RetailerID that I get from my DB to get the Surrogate key which I would use in the Fact tables. This Surrogate key would also be the key for the DimRetailer and DimVendor tables.So in this case, I assume a sourceID would not be used in the Dimension table as it would always come from the XRef tables.I want the reports to reports by Vendor or by Retailer combined not segment the report by database.Is this the best way to handle this?Thanks,TomTue, 01 Feb 2011 13:09:19 GMTtshadhttp://www.sqlservercentral.com/Forums/Topic1103406-2797-1.aspxWhen I create an advanced mining structure and a linear regression to the structure, initially I get a "browse" summary with a graph as well as a histogram. Beneath the histogram there is a an equation that gives the factors and the coeffiecents. These numbers are different than what is provided when I go to the "model usage" tab and document model. Any clue what the difference in equations is from? Is it in sample vs total population?Wed, 04 May 2011 12:26:58 GMTrojovinohttp://www.sqlservercentral.com/Forums/Topic1081736-2797-1.aspxhelp me on how i calculate my online examination multiple choices<html><body><table align='center'><div><b>Question 1:</b></div><div>What do the letter "MS" in MSNBC stand for?</div><ul><input type='radio' name=1' />A.Mothersky</ul><ul><input type='radio' name=1' />B.Microsoft</ul><ul><input type='radio' name=1' />C.Macrosoft</ul><ul><input type='radio' name=1' />D.Mediashare</ul><div><b>Question 2:</b></div>";<div>Which operating system was developed by a college student name Linus Torvalds.</div><li><input type='radio' name=1' />A.Linux</li><li><input type='radio' name=1' />B.Ubuntu</li><li><input type='radio' name=1' />C.Microsoft</li><li><input type='radio' name=1' />D.Kubuntu</li><div><b>Question 3:</b></div><div>What does the letter "A" in RAM stand for.</div><ul><input type='radio' name=1' />A.Accelerate</ul><ul><input type='radio' name=1' />B.Alternative</ul><ul><input type='radio' name=1' />C.Access</ul><ul><input type='radio' name=1' />D.Action</ul></table></body></html>Mon, 21 Mar 2011 22:39:50 GMTjustin0550http://www.sqlservercentral.com/Forums/Topic1062448-2797-1.aspxHi,I need to give a proposal for a project where i need to suggest SQL server data mining. I need some information on the pros and cons of SQL server data mining like how much data it can handle , performance , flexibility , which business scenarios it will not help etc.Any information on comparison of SQL server data mining with other data mining tools in market like SAS , Clementine , Intelligent Miner etc.Fri, 11 Feb 2011 03:57:57 GMTMitra_Misrahttp://www.sqlservercentral.com/Forums/Topic1062447-2797-1.aspxHi,I need to give a proposal for a project where i need to suggest SQL server data mining. I need some information on the pros and cons of SQL server data mining like how much data it can handle , performance , flexibility , which business scenarios it will not help etc.Any information on comparison of SQL server data mining with other data mining tools in market like SAS , Clementine , Intelligent Miner etc.Fri, 11 Feb 2011 03:57:15 GMTMitra_Misrahttp://www.sqlservercentral.com/Forums/Topic1057999-2797-1.aspxHere is a nice article for decision tree. [b][url=http://www.mindtools.com/dectree.html]Click here[/url][/b]Thu, 03 Feb 2011 05:42:53 GMTRaunak Jhawarhttp://www.sqlservercentral.com/Forums/Topic1018819-2797-1.aspxA great article on how one can use data mining for something else than the traditional data mining purposes:[url]http://www.applefritter.com/bannedbooks[/url]A very entertaining read! :-)Wed, 10 Nov 2010 11:01:35 GMTKoen Verbeeckhttp://www.sqlservercentral.com/Forums/Topic1004926-2797-1.aspxThe initial post on Data Mining has recieved till date more than 800 hits.:-)This is another post which will feature the life cycle of any Data Mining ProjectStep 1: A mining model is built which consists of a sample data. The sample data is the source data using which the business has to conduct any predictive analytical process.Step 2: The mining model is then exposed to a training model. The training model is the sort of sample data which will be used to extact patterns from the underlying mining model using the Data Mining Engine.Step 3: The refined mining model is now exposed to a set of data which is to be predicted. the Data Mining engine will then produce the "Predicted Data" for a relative scenario.The process of Data Mining is gradual and a continuous learning model. The sole target is to refine the mining model to produce crispier and reliable model.Fri, 15 Oct 2010 00:42:22 GMTRaunak Jhawarhttp://www.sqlservercentral.com/Forums/Topic1018816-2797-1.aspxI've come across this excellent blog post of Chris Webb about using data mining to add forecast values to a cube:[url]http://cwebbbi.wordpress.com/2008/10/01/using-as-data-mining-to-add-forecast-values-to-a-cube/[/url]A very interesting read...Wed, 10 Nov 2010 10:59:47 GMTKoen Verbeeckhttp://www.sqlservercentral.com/Forums/Topic1001034-2797-1.aspxCan you feel, people accept SSIS only because of their cost concern of Informatica/Data Stage?Fri, 08 Oct 2010 00:48:41 GMTsaurabh.deshpande