Get started with Azure Machine Learning

Today, Microsoft is announcing and offering general availability for Azure Machine Learning.  Many of the features are listed at http://azure.microsoft.com/en-us/services/machine-learning/

AzureMLFeatures 2014 07 14 10 20 39 206x300 Get started with Azure Machine Learning

With this launch, I will be releasing more information on this new technology as the service becomes more available to the public.  This blog post has the links and information to get started in three steps.

GetStartedAzureMachineLearning 20140714 273x300 Get started with Azure Machine Learning
Continue reading “Get started with Azure Machine Learning” »

Microsoft Azure Machine Learning

Yesterday, Microsoft publicly announced a new technology for machine learning called Microsoft Azure Machine Learning.  This cloud-based technology promises ease in building data-driven analytics applications.  Based on my MVP status and relationship with key Microsoft people, I have been aware of this technology for about two years:  I have been keeping silent on this topic and will be only commenting on what is publicly available as it becomes available.  This blog post has more of the publicly-announced details.
Continue reading “Microsoft Azure Machine Learning” »

How does SAS performance compare with Julia?

I have been a SAS programmer and architect for years:  I did my first professional work in the 1990s.  I also have made friends among people who focus on SAS.  I had mentioned in a SAS Consultants forum in Google Groups that the open source Julia language was delivering impressive results compared with the R language.    The testing involves several math problems which could be translated into most any language.  Previous results (and code) has been already shared on http://julialang.org/

I had wanted to try SAS to see how it does against Julia, but I did not have a machine where I could load both software applications.  However, Dom Pazzula not only tested it on his machine, but also provided the comparison code.  This blog post has the results of the test and the SAS code for you to try the comparison yourself.

SASvsJulia How does SAS performance compare with Julia?
Continue reading “How does SAS performance compare with Julia?” »

Free eBooks from Microsoft

Microsoft Program Manager Eric Ligman has been posting lists of free eBooks from his blog.  I have not mentioned these books in past blog postings.  So, this posting is a catch-up for the three lists he has already mentioned and subsequently summarized.  I will be commenting on free books which help for Microsoft data analytics and data science.
Continue reading “Free eBooks from Microsoft” »

Is SPSS better than SQL Server Data Mining?

I was recently asked this question by someone who works for Microsoft, and who was sincerely trying to understand the differences.  I first used SPSS in the early 1990s on the mainframe, just after I had started using SAS on UNIX.  Over my career, I have seen SPSS in different environments, and I also published a paper once about SPSS options for stratified sample analysis (previously those functions were not available but now they are available as an option).

This post will have my response on how to evaluate SPSS versus SQL Server Data Mining.

SPSSvsSSAS Is SPSS better than SQL Server Data Mining?
Continue reading “Is SPSS better than SQL Server Data Mining?” »

Presenting at SQL Saturday Charlotte October 19

I will be speaking at the second Charlotte BI Edition SQL Saturday (in Charlotte, NC) on October 19.  I will be at the PASS Summit as a volunteer (previous to the SQL Saturday), but will be talking at this Saturday conference about data mining.  This post has the details.

sqlsat237 web Presenting at SQL Saturday Charlotte October 19
Continue reading “Presenting at SQL Saturday Charlotte October 19” »

Presenting at Silicon Valley Code Camp October 5-6

I am honored to be speaking on the PASS (Professional Association for SQL Server) track at this year’s Silicon Valley Code Camp (in Los Altos Hills, CA).  Annually, this user event is (currently) the largest Code Camp in the United States.  Also, I have been a presenter at some past SQL Saturday events in Mountain View, and I know that passion for data mining runs deep in this technology hub.  This post has details on the two presentations I will be giving.

 Presenting at Silicon Valley Code Camp October 5 6
Continue reading “Presenting at Silicon Valley Code Camp October 5-6” »

Sponsoring and Presenting at SQL Saturday 226 South Florida June 29

I am happy to be a sponsor (via MarkTab Inc) and presenter at SQL Saturday 226 South Florida.  I have been to this event in the past, and many of my presenter friends will also be at this excellent event.  Also, I will giving away some great prizes:  five passes (value US$1495) for data mining training to be held on September 10-12, 2013 (winners must be present at the end of the event to win).  I also will be giving three separate one-hour presentations, two on data mining, and one for professional development.  This blog post has the details, and links to the presentations.

SQLSaturday226SouthFlorida Sponsoring and Presenting at SQL Saturday 226 South Florida June 29

SQL Saturday 226 South Florida

Continue reading “Sponsoring and Presenting at SQL Saturday 226 South Florida June 29” »

Presenting a Best Practices Framework for Data Mining June 2013

I copresented (with Artus Krohn-Grimberghe) a session called “A Best Practices Framework for Data Mining” for the June 13, 2013 PASS Virtual Business Analytics Group.  This talk marks my third for this relatively new group, and I’m glad to work with leader Melissa Demsak on these quality presentations.  For this talk, we had about 40 people, and seamlessly delivered the talk from both North America (myself) and Europe (Artus, who is in Germany).  This post has the details and the links to the slides and recorded presentation.

PASS VirtualChapter BusinessAnalytics 300x119 Presenting a Best Practices Framework for Data Mining June 2013

Continue reading “Presenting a Best Practices Framework for Data Mining June 2013” »

Sponsoring and Presenting at SQL Saturday 220 Atlanta GA May 18

MarkTab Inc. is a sponsor for SQL Saturday 220, Atlanta, GA (May 18), and will be giving away five passes to the three-day Experience Data Mining training on September 10-12, 2013.  I will also be presenting two topics at SQL Saturday:  first, Secrets of Enterprise Data Mining, and second, Applied Enterprise Semantic Mining.  This post has the details.

SQLSaturday220 Sponsoring and Presenting at SQL Saturday 220 Atlanta GA May 18

Continue reading “Sponsoring and Presenting at SQL Saturday 220 Atlanta GA May 18” »

Presenting Data Analysis with R and Julia for PASS Virtual Business Analytics May 9

I will be presenting a talk titled Data Analysis with R and Julia for the PASS Virtual Business Analytics Conference on May 9 (12 PM, UTC -4).  I had previously presented this talk at the PASS Business Analytics Conference in Chicago.  This talk will even be better:  I will be enhancing the presentation based on feedback people had during that time.  As well, I am inviting people from the new Meetup group, Atlanta Julia Users, to both attend and see this talk.  This blog post has the details.

PASS VirtualChapter BusinessAnalytics 300x119 Presenting Data Analysis with R and Julia for PASS Virtual Business Analytics May 9

Continue reading “Presenting Data Analysis with R and Julia for PASS Virtual Business Analytics May 9” »

Tips on Improving WordPress 3.5.1 Speed with GoDaddy Shared Hosting

Query:  How can I improve the performance speed of WordPress with GoDaddy?

Response:

I have been happily using WordPress since 2010.  I have found myself doing plug-in trial-and-error with different solutions to improve the speed.  Anyone could open a blog at wordpress.com and leave the management issues to experts.  However, I desired to have my blog hosted at marktab.net, so I installed the software myself on a GoDaddy shared Windows hosting platform.  The tips I have in this post will likely work also for Linux-based installation, though as with any change, you need to experiment yourself.

In this post, I will be outlining what I did to improve my website speed on http://marktab.net/datamining (running WordPress 3.5.1 on Windows shared hosting at GoDaddy).   Consider these tips for any WordPress 3.x version.

I have been using two tools to judge speed.  The first one is called Pingdom Tools http://tools.pingdom.com/fpt/ which (currently) test speeds using one of their three source servers.  This test shows how fast a site might load, but I have found the results to be variable (upon repeat tests in the same session with no changes) and I assume likely influenced by the server’s general load and current network traffic.  The second, and what I consider better test, comes from Google’s PageSpeed tools https://developers.google.com/speed/pagespeed/.  Google is a major source of hits on my domains, and they have been supporting all web developers with a variety of tools to measure traffic.  If you are running a website and are not using Google Webmaster tools, you should look at the benefits.

Google’s Page Speed scores websites between 0 and 100, where higher numbers are better.  Their analysis show what the issues are, but how to improve them depends on software used since the service will score any type of website, not just ones running WordPress.  Finding out what to do is a matter of trial and error.  To achieve my own results I had to try a number of different things given the options available with WordPress 3.5.1 and GoDaddy shared Windows hosting.  This post describes a combination which took my WordPress blog from a score in the mid 70′s to over 90.

Continue reading “Tips on Improving WordPress 3.5.1 Speed with GoDaddy Shared Hosting” »