Jamie's Junk : Excel

Data Mining Addins on Channel 9

JamieMac — Tue, 03 Jun 2008 11:48:00 GMT

Wee Hyong, a SQL Server MVP in Singapore discusses with Channel 9 how he improved the event experience for the Heroes Community launch using the Data Mining Addins. The first half of the video is the interview and then he presents a demo of the event data using the SQL Server 2008 Data Mining Addins for Office

SQL Data Mining

Preview the Model Documentation feature of the next version of the Data Mining Client for Excel

JamieMac — Sat, 20 Oct 2007 03:37:00 GMT

The attached document has a preview of the output of a new "Model Documentation" feature for our next version of the data mining addins. You just click on a button, select a model and recieve a report containing (hopefully) interesting and pertinent information about the mining model.

What do you think? Does the feature provide model documentation useful to you? What would you add? What would you remove? Let me know in the comments!

Data Mining Virtual Hands-on Lab Now Available! Also, in other news, Donald in a fishbowl!

JamieMac — Tue, 24 Jul 2007 01:49:00 GMT

For those of you who have been dying to try out the data mining addins we released earlier this year - here's your chance! Ok, scratch that, if you're reading my blog you've been there done that, but if there's that someone special who you know would love the addins and hadn't had the chance to get everything configured to give them a go, have I got a deal for you!

Since the Data Mining Addins hands-on lab was ranked in the top 10 of all labs at TechEd (it was, in fact, #2), it earned a special distinction of being made available as an online hands-on lab where you can reserve 90 minutes of time to remotely operate machine to walk through the exercises. Try it out today!

While you're waiting, you can watch our Principal Program Manager, Donald Farmer interview a customer (who had coincidentally just finished the lab) in the "Tech-Ed" fishbowl.

Important Update for the Data Mining Addins!

JamieMac — Fri, 23 Mar 2007 02:04:00 GMT

Due to a late found performance regression we decided to rerelease the data mining addins. A change we made in the product shortly before release was causing queries in the Data Mining Client for Excel to take several minutes instead of several seconds. With the fix, for example, I can do a prediction query against 10,000 rows in Excel and have the results populated back in to the worksheet in under 20 seconds on my laptop.

I recommend that everybody download the update and install the new version. In addition to the query performance fix, there are also performance fixes for the column selection wizard page and continuous valued scatter plots. We also made some fixes to ensure that users of SQL Server Standard Edition have a good user experience. Users of SQL Server Standard Edition will have to install the SP2 Cumulative Hotfix update in addition to the new addins.

As always keep in touch with the data mining team and ask questions through our MSDN forum - we're happy to help out and love to hear any suggestions to improve the product.

Data Mining Addins Released to Web!

JamieMac — Tue, 20 Feb 2007 22:52:00 GMT

The SQL Server 2005 Data Mining Add-ins for Office 2007 have finally released to web yesterday along with SP2 of SQL Server 2005. The DM team has done a great write-up on how to get the add-ins (and everything else necessary) and also a really nice whitepaper giving an overview of the tools.

While you're at it, you should check out the SP2 release of SQL Server 2005 - there are innumerable improvements to data mining and OLAP in Analysis Services that maybe I'll get around to numerating one of these days. Some notable are incredible OLAP calc performance increases and an interesting new DMX semantic.... I'll keep you guessing until I post again.

Enjoy the Addins and the rest of SP2! You're feedback is definately welcome!

update: Donald delivers a much more eloquent description of the value of the Add-ins

Wisconsin Breast Cancer Dataset available

JamieMac — Fri, 02 Feb 2007 01:50:00 GMT

Frequently I use the Wisconsin Breast Cancer Dataset for demonstrating the Data Mining Addins for Office - enough people asked, so I made it available as an Excel 2007 file (free login required). For purists, the original data is available at the Machine Learning repository, which is a great location for many sample datasets.

Here are some screenshots of the data mining add-ins applied to this dataset

Figure 1: Key Factor Analysis showing differences between benign and malignant tumors

Figure 2: Detect categories showing malignancy across detected groups. Note two purely malignant categories suggesting differing classes of malignant tumors.

Figure 3: Decision tree to predict diagnosis, with nodes shaded based on likelihood of malignancy.

Try out the Data Mining Addins for Office 2007 FREE for 60 days!

JamieMac — Sat, 30 Dec 2006 10:52:00 GMT

OK, I admit it's a wierd title, since the addins are free anyway, but you do have to have SQL Server 2005 and Office 2007 to use them. However, you can now get all the parts necessary for a free trail download and for the icing on the cake, download the always-free Data Minig addins!

First, you need to download the 180 day trial SQL Server 2005 Evaluation Edition and install SQL Server 2005 Analysis Services (you can install all the rest as well, but the other parts aren't needed for teh addins)

Next, upgrade the eval edition to SQL Server 2005 SP2 December Community Technical Preview (CTP 3) Technically, this isn't 100% necessary, but since you're busy downloading everything anyway, you might as well. If you have installed previous CTP's of SP2, this step is necessary.

Now download and install the 60 day trials for Office 2007 Professional and Visio 2007 from the Office Online site. You're going to want to make sure you install the .NET programmability pieces, which are installed by default if you already have .NET (hint - install .NET 2.0 first...)

Finally, you can download and install the Data Mining Addins CTP! By default just the Table Analytic Tools for Excel are installed - I recommend (of course) installing the Data Mining Client for Excel and the Data Mining Template for Visio as well - just select the options during install.

After you've gotten all this working - please provide feedback at http://connect.microsoft.com/ - we still have a few weeks before we cut the final version so your feedback will definately help! Even if there are ideas that can't get into this version, there's always v2!

Happy Holidays and thanks from me and the SQL Server DM team!

Your chance to see the Data Mining Office Addins for yourself!

JamieMac — Sat, 18 Nov 2006 01:29:00 GMT

I was happily surprised at the reception of the Addins at my presentation at PASS in Seattle yesterday - one report was that the audience was "drooling". If you're one that just couldn't make it to Seattle this week - no sweat! I will be presenting the Addins during a webcast on November 27. So if you're all filled up from a Thanksgiving weekend (in the US at least) you can sit down Monday morning and see what all the excitement is about! (just don't drool on your keyboard!). You can register online for the webcast here.

Data Mining Addins for Office 2007 Preview Build Now Available!

JamieMac — Wed, 08 Nov 2006 04:53:00 GMT

Download at your pleasure from http://www.microsoft.com/downloads/details.aspx?FamilyID=aa0c2623-b432-4a1f-9a3c-9d64df130a61&DisplayLang=en

Enjoy!

Important Excerpts from the download page:

If you have questions about the Data Mining Add-ins, visit the SQL Server Data Mining Forum on MSDN.

Help improve the Data Mining Add-ins by submitting bugs to the Connect Feedback Center.

Analyst comments on the upcoming SQL Server 2005 Data Mining Addins for Office 2007

JamieMac — Sat, 04 Nov 2006 20:29:00 GMT

A few weeks ago I did an analyst briefing with David Norris of Bloor research on Microsoft's data mining strategy. I wasn't really expecting any press out of it, but he wrote up this article on his impressions

Sometimes Microsoft does things very well

He also gave it a mention in a somewhat unrelated article the next day

SPSS continue to develop as a solutions provider

If you want to see what all the hubbub is about, watch this space! Our release of CTP2 of SQL Server 2005 SP2 is imminent, and with that you will be able to download and play with a preview release of these addins yourself!

Code from book and new XMLA template at SSDM

JamieMac — Tue, 15 Nov 2005 23:07:00 GMT

I just added a couple of new downloads on SQLServerDataMining.com

The first is the sample from chapter 16 (Forecasting in Excel) of my book, Data Mining with SQL Server 2005 which was misposted on the publisher's site (it will be updated there as well, but it's at SSDM for those of you who want it today).

The other download is a simple XMLA template that is surprisingly important since it fills a gap in our DMX language that was blocking common workflows.

DMX has great constructs for creating, training, and managing mining structures and models. Now that SQL Server Management Studio (SSMS) has a DMX editor, it's really nice to just open one up and start typing CREATE MINING STRUCTURE ... and do all of your mining right there. However, in general, once you got to INSERT INTO you were stuck (not to mention PREDICTION JOIN). Since we strongly encourage everyone to use OPENQUERY and a named datasource rather than OPENROWSET and a connection string, it would seem that there would be an easy way to create datasources in SSMS. Wrong.

The only "easy" way to create a datasource would be to fire up the BI Dev Studio, open the database, create a datasource in the UI and then switch back to SSMS - a user experience that leaves a bad taste in your mouth - essentially a big hole in the experience.

So the template I added allows you to easily create a datasource from SSMS by loading the template, setting some values (like a name, connection string, etc) and executing. Now you can perform your entire DM workflow directly in SSMS!

Enjoy! I welcome any feedback or many suggestions for new templates.

On PASS, PDC and new Downloadable Demos

JamieMac — Sat, 01 Oct 2005 00:24:00 GMT

I've just finished uploading some new demos that I've shown at PDC and PASS. Both of these demos show how to use VBA to integrate data mining functionality into Excel. Their pretty cool - you should check them out. Bogdan wrote the DMPredict function and I wrote the clustering sample.

As I'm writing this PASS is finishing up - I actually should be on the way to the airport, but I still have a couple minutes....

PASS was excellent as usual and I'm fired up about the response to the data mining tools in SQL 2005 - there's a whole new audience out there that has advanced research technology available to them for the first time. It will be exciting to see how these communities can push and pull this tech to do things that no one has ever imagined. A PDC'er that commented to be two weeks back in LA, called the advances in Data Mining and OLAP in SQL Server 2005 Analysis Services a "seismic" event. It's good to be in AS!

Go ahead - if you've downloaded the September CTP, check out those demos! Gotta catch my flight!