Preparing for Exam 70-774 – Perform Cloud Data Science with Azure Machine Learning

There are a number of reasons why you might want to take a Microsoft cert exam. Maybe you want to focus your studies on a tangible thing, or you think it will help further your career, or you work for a Microsoft Partner and they required a certain number of people to pass the exam to maintain their current partner status.  I am not going to get into the long argument regarding whether or not a cert will help you in your career, or not, I can tell you why you might want to take the 70-774 exam. Machine Learning, or Data Science if you prefer, is an important analytic skill to have to analyze data.  I believe that it will only become more useful overtime. Azure Machine Learning is a good tool for learning the analysis process.  Once you have the concepts down, then should you need to use other tools to perform analysis it is just a matter of learning a new tool.  I talk to a number of people who are trying to learn new things, and the study them in their spare time.  It’s very easy to spend time vaguely studying something, but you may find that having a target set of items to study will focus your time, and as a bonus you get a neat badge and some measure of proof that you were spending time on the computer learning new things and not just watching cat videos.

Exam 70-774 Preparation Tips


While you could always buy the book for the exam (shameless plug as I was one of the authors), the book will not be enough and you will still need to write some code, and do some additional studying. This exam one of two needed for the MCSA in Data Science and you an take the exams in any order. The best place to start is by first looking at the 70-774 exam reference page from Microsoft.  There are four different sections in the exam, and I have created some links for each section which will help you prepare for the exam. In studying for exams in the past, the best way I have found to prepare is to look at everything on the outline and make sure that I know it.

Prepare Data for Analysis in Azure Machine Learning and Export from Azure Machine Learning

Normalizing Data
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/normalize-data

TanH
https://reference.wolfram.com/language/ref/Tanh.html

ZScore
http://stattrek.com/statistics/dictionary.aspx?definition=z-score
http://howto.commetrics.com/methodology/statistics/normalization/

Min Max
https://www.quora.com/What-is-the-meaning-of-min-max-normalization

PCA
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/principal-component-analysis
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/principal-component-analysis
https://stackoverflow.com/questions/9590114/importance-of-pca-or-svd-in-machine-learning

SVD
http://andrew.gibiansky.com/blog/mathematics/cool-linear-algebra-singular-value-decomposition/

Canonical-correlation analysis (CCA)
https://en.wikipedia.org/wiki/Canonical_correlation

Singular Value Decomposition (SVD)
http://andrew.gibiansky.com/blog/mathematics/cool-linear-algebra-singular-value-decomposition/

Develop Machine Learning Models

Team Data Science
https://docs.microsoft.com/fi-fi/azure/machine-learning/team-data-science-process/python-data-access

K-Means
https://www.datascience.com/blog/k-means-clustering

Confusion Matrix
http://www.dataschool.io/simple-guide-to-confusion-matrix-terminology/
https://en.wikipedia.org/wiki/Confusion_matrix
https://en.wikipedia.org/wiki/F1_score

Ordinal Regression
https://en.wikipedia.org/wiki/Ordinal_regression

Poisson regression
https://en.wikipedia.org/wiki/Poisson_regression

Mean Absolute Error and Root Mean Squared Error
http://www.eumetrain.org/data/4/451/english/msg/ver_cont_var/uos3/uos3_ko1.htm

Cross Validation
https://towardsdatascience.com/cross-validation-in-machine-learning-72924a69872f

Operationalize and Manage Azure Machine Learning Services

Connect to a published Machine Learning web service
https://docs.microsoft.com/en-us/azure/machine-learning/studio/publish-a-machine-learning-web-service
https://docs.microsoft.com/en-us/azure/machine-learning/studio/consume-web-service-with-web-app-template
https://docs.microsoft.com/en-us/azure/machine-learning/studio/manage-new-webservice

Use Other Services for Machine Learning

Microsoft Cognitive Toolkit
https://www.microsoft.com/en-us/cognitive-toolkit/

BrainScript
https://docs.microsoft.com/en-us/cognitive-toolkit/brainscript-basic-concepts

Streamline development by using existing resources
https://docs.microsoft.com/en-us/azure/machine-learning/studio/gallery-how-to-use-contribute-publish
Perform database analytics by using SQL Server R Services on Azure
https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/provision-vm
https://docs.microsoft.com/en-us/machine-learning-server/install/r-server-vm-data-science
https://journal.r-project.org/archive/2009-2/RJournal_2009-2_Williams.pdf
http://blog.revolutionanalytics.com/2017/07/xgboost-support-added-to-rattle.html
https://github.com/JohnLangford/vowpal_wabbit/wiki

I hope you have found this test preparation material helpful.  If you passed the exam, let me know by sending me a comment.

Yours Always,

Ginger Grant

Data aficionado et SQL Raconteur

MSCA, Part 3 the final countdown, Exam 70-463

MCSA_2013(rgb)_1457

If you wait until 2 minutes into this 80s hair band song, you will get what comes to mind when I started studying for this test. I think I first heard it when I was introduced to the band Metal Rose last year, but I can’t find their cover of it. Anyway, this is the last exam of the series, the Data Warehouse one. This is the test that online all of the DBA types don’t like because you have to know about Building a Data Warehouse, SSIS, and ETL. Here’s a link to the http://www.microsoft.com/learning/en-us/exam-70-463.aspx

I thought this was the most fun. After all this is the BI exam, which is what I like to do and as an added bonus I thought the Microsoft training book was really good. If you are studying for the exam or interested in Data warehousing in SQL Server, I think it is a good read.

Is it worth it?

The question I get asked about certifications is: Are they worth it? I have been thinking about that and I the answer I have is, I don’t know. Personally, I find that if I have a reason to go learn something, I will. Studying for an exam provides a reason. The exam is like a bowling pin, it is a target to knock down. If I didn’t study for this test would I have become interested figuring out how to apply Master Data Management? Probably not, but that’s the sort of thing I got out of it. A test is just a reason to learn new things about SQL Server and the piece of paper and the logos, is an added bonus. I downloaded my Official Logos and Paper copy of the cert just to make it official. I even framed it.

The Process

I now have a process for how I can pass the tests, which involves me creating my own book in word, and studying it. This is the first time that I found the book to be the best source on the topic, so I just wrote down the pages that I thought I should study in my notes. This time I remembered to list all of the web pages that I copied so that anyone could see where the original text came from. I thought I’d share it, as I am feeling good about being done with this as cert. If you find it helpful, let me know.

Design and implement a data warehouse (11%)

http://technet.microsoft.com/en-us/library/ms141715.aspx
http://technet.microsoft.com/en-us/library/ms161956.aspx
http://msdn.microsoft.com/en-us/library/ms175439.aspx
http://msdn.microsoft.com/en-us/library/ms175669.aspx
http://msdn.microsoft.com/en-us/library/gg492088.aspx

Extract and transform data (23%)

http://technet.microsoft.com/en-us/library/ms137786.aspx
http://msdn.microsoft.com/en-us/library/bb522511.aspx
http://msdn.microsoft.com/en-us/library/cc895212.aspx
http://msdn.microsoft.com/en-us/library/ms140203.aspx
http://msdn.microsoft.com/en-us/library/ms140080.aspx
http://msdn.microsoft.com/en-us/library/ms141715.aspx

Load data (27%)

http://technet.microsoft.com/en-us/library/ms135993.aspx
http://technet.microsoft.com/en-us/library/ms345156.aspx
http://technet.microsoft.com/en-us/library/hh230986.aspx
http://technet.microsoft.com/en-us/library/ms140246.aspx
http://technet.microsoft.com/en-us/library/ms135965.aspx
http://technet.microsoft.com/en-us/library/ms345156.aspx
http://technet.microsoft.com/en-us/library/ms135896.aspx
http://technet.microsoft.com/en-us/library/ms135948.aspx
http://technet.microsoft.com/en-us/library/ms141150.aspx
http://technet.microsoft.com/en-us/library/ms141747.aspx
http://technet.microsoft.com/en-us/library/ms140355.aspx
http://technet.microsoft.com/en-us/library/ms137728.aspx
http://technet.microsoft.com/en-us/library/hh479592.aspx
http://technet.microsoft.com/en-us/library/ms141003.aspx
http://technet.microsoft.com/en-us/library/cc280502.aspx
http://technet.microsoft.com/en-us/library/ms141724.aspx
http://technet.microsoft.com/en-us/library/ms139733.aspx
http://technet.microsoft.com/en-us/library/ms140226.aspx
http://technet.microsoft.com/en-us/library/ms141809.aspx
http://technet.microsoft.com/en-us/library/ms137640.aspx
http://technet.microsoft.com/en-us/library/ms137944.aspx
http://msdn.microsoft.com/en-us/library/ms137690.aspx
http://msdn.microsoft.com/en-us/library/ms135965.aspx
http://msdn.microsoft.com/en-us/library/hh213214.aspx

Configure and deploy SSIS solutions (24%)

http://technet.microsoft.com/en-us/library/ms403356.aspx
http://technet.microsoft.com/en-us/library/hh213230.aspx
http://technet.microsoft.com/en-us/library/ms140246.aspx
http://technet.microsoft.com/en-us/library/ff878036.aspx
http://technet.microsoft.com/en-us/library/hh479588.aspx
http://technet.microsoft.com/en-us/library/hh231191
http://technet.microsoft.com/en-us/library/hh213373.aspx
http://technet.microsoft.com/en-us/library/hh231187.aspx
http://technet.microsoft.com/en-us/library/ms180378.aspx
http://msdn.microsoft.com/en-us/library/ms137625.aspx
http://msdn.microsoft.com/en-us/library/ms345184.aspx
http://msdn.microsoft.com/en-us/library/ms140246.aspx

Build data quality solutions (15%)

http://technet.microsoft.com/en-us/sqlserver/jj737674.aspx
http://technet.microsoft.com/en-us/library/ee633737.aspx
http://technet.microsoft.com/en-us/library/ee633759.aspx
http://msdn.microsoft.com/en-us/library/ff487006.aspx
http://technet.microsoft.com/en-us/library/ee633884.aspx
http://technet.microsoft.com/en-us/library/ff487040.aspx
http://technet.microsoft.com/en-us/library/ee633808.aspx
http://technet.microsoft.com/en-us/library/ee633854.aspx
http://technet.microsoft.com/en-us/library/ee633772.aspx
http://technet.microsoft.com/en-us/library/hh213045.aspx
http://msdn.microsoft.com/en-us/library/gg492277.aspx
http://technet.microsoft.com/en-us/library/ee633752.aspx
http://technet.microsoft.com/en-us/library/hh231022.aspx

Yours Always

Ginger Grant

Data aficionado et SQL Raconteur

MCSA – Part Deux, Exam 70-462

If you haven’t seen Charlie Sheen’s cinematic triumph Hot Shot’s Part Deux, you’re missing out, which is why I made sure to include the link for it. If you have seen the movie you will wonder how it missed out on an Oscar nomination, or maybe better understand why it is on cable non-stop in reruns. It was also the first thing that came to mind when I thought about Part Deux. So having taken the first exam 70-461, without the book, I felt compelled to go out and get the Official Microsoft Press study book for 70-462 . This was the first book made available for any of the SQL Server MCSA Exams. Yea! That will make studying for the test so much easier, right? No. Wrong. Dead wrong.

So about the book.

If all you do is follow it, make sure you check out this web site http://www.microsoft.com/learning/en-us/second-shot.aspx as you will be doing a Part Deux yourself. This exam covers the administration part of the exam. This is the exam that DBAs should be more familiar with, although I doubt in your environment that they have set up every form of replication and high availability option in SQL Server 2012, so I bet you will have to study too. I set up a server and thumped around the exercises. It wasn’t enough. The book does offer a coupon in the back for a discount on the exam cost as well as practice exams. After I failed the practice exams, I thought hmm this isn’t working. I went back to what I did on the last exam, after all I passed that one. Here is everything you need to know to pass the 70-462 exam. What I did was made a word document out of all the material it said you needed to know by copying things off of MSDN and books online. I made two documents, after all this is part two, and it got sorta long and I didn’t want to blow up Word.

After making sure that I could really do the stuff listed that I didn’t have a chance to mess with when I played DBA, I drove my rolling purse over to the testing center and took the exam. I brought my running watch which has a handy stopwatch which is also fun to set when standing in TSA lines in the airport to see how much of your time is really being wasted. You should try that sometime as generally you will be surprised that it seems like you are spending a lot more time in line than you actually are. The test was like that, as it seemed like it was taking forever but I actually had more time than I needed. I had 30 minutes to spare so I could go get ice cream before I had to be at my next appointment.

Yours Always

Ginger Grant

Data aficionado et SQL Raconteur

MCSA, Act 1 Exam 70-461

The MCSA is really a play in three acts, one for each test. For SQL Server 2012, Microsoft changed up the whole exam game. Now you have to take three tests, count them three 461, 462 and 463, to get a certification, the Microsoft Certified Solutions Associate [MCSA]. Gone are the good old days when you could take the first exam 461 and then stick Microsoft Certified Professional on your business cards. That was sweet, and in all candor I have done something kinda similar. Unfortunately, these days you will receive nada until you take and pass all three exams. Only then will you receive two logos and a certificate, which I now have ensconced upon my office wall in an exceedingly tasteful and exceedingly stylish frame.

A bit more branding for a lot more work.

So let’s start at the beginning and talk about 461. Unofficially speaking, this test isn’t terrible. Check out the link to see what’s on it http://www.microsoft.com/learning/en-us/exam-70-461.aspx. You just have to make sure you know all the stuff that they tell you on this page. For me the hardest part was learning all of the new stuff on 2012 which I hadn’t gotten around to playing with yet and the XML which no one has asked me to play with for years.

I wish I could comment on the book for it, but I got all motivated and took the test before the book came out. Itzik Ben-Gan is really an impressive guy when it comes to SQL stuff, so I bet it is good. I can tell you this, you can pass the test without it. What I did was took every topic listed in the study guide on Microsoft’s 70-461 site, and made up my own reference from links online. I played around writing code in adventure works too. I ordered the material I studied based on the emphasis that topic had on the test. The topic Work with data has the highest percentage of the material at 27% so I studied that one the most and the rest of them in percentage order. I made sure that I could write the sql code covered and that pretty much did it.

For those of you who wonder what it is like to actually take the test, just follow the process. First off, you make an appointment at a testing site, show up 10 minutes before your time, and sign in. If you bring anything with you other than your two ids and keys, you will have to lock it up there, so empty your pockets and leave all the stuff you usually carry around with you in your car, or as I like to refer to my car, the rolling purse. The proctor will hand you a laminated piece of paper and a dry erase marker and then walk you over to a library carrel with a computer they will sign in. The test is timed, so take a watch as the computer won’t show you what time it is. Whenever I don’t know what time it is, I find a strange fixation to know the time. Yes I get that this makes no sense and a waste brain power, but this is what I am thinking about when I am sitting there. As soon as you hit enter on the last question, sit there for a minute and you will find out if you passed or not. Be kind to the other people taking the test and don’t start banging on the desk because I don’t need your personal issues to mess with my brain, which is still mode locked over not knowing what time it is. You will get a printed copy of your results which show how you did in each section with a Gantt chart. If it is all black you got that section 100% correct. I am dying to know what a blank 1/3 of an inch means, but Microsoft doesn’t really disclose how it is scored, so I guess I’ll never know but I did pass it. Note to self, next time, bring a watch.

Yours Always

Ginger Grant

Data aficionado et SQL Raconteur