Tag Archives

6 Articles

Adding sequence numbers using R in Azure ML

When going through data preparation sometimes sequence numbers need to be added. If you are like me, you probably spent some time looking for a component in Azure ML to do this. I never found it.

Turns out it is really easy to do this in R and as a result also very easy to do in Azure ML.

In your experiment, add an Execute R Script component and connect it to the data flow.

Edit the script and add a column to the dataset that equals:

See my code example:


On the third line the column is added and defined as a sequence number. The resulting dataset indeed has an extra column (called time) that like this:

The small histogram at the top and the details that right confirm it has only unique values and starts at 1; our sequence column has been added!

Azure Machine Learning pricing explained

Many customers asked me questions on Azure Machine Learning (Microsoft’s fully managed machine learning and data mining solution) and more specifically on it’s pricing. In this post I will try to explain how the pricing works and what components you need to be aware of.

Azure Machine Learning is offered in two tiers: Free and Standard. The Free tier is obviously, well, free. It is however as you could expect limited compared to Standard. Differences are mostly in performance (multiple nodes for execution in standard vs. just one node in free) or storage (10 gb in free, unlimited in standard). There is no SLA for the free version, you cannot set up a production Web API to automate experiments in free and the staging web API is throttled.

For the standard tier, the following items need to be taken into consideration:

  • Seat; Azure ML has a monthly fee per seat, which translates to a user (mostly your data scientist) using the Azure ML web interface to develop and tune experiments. This price is per month per subscription/seat.
  • Studio usage; This is an hourly price for running experiments. You will pay this according to the number of hours your experiments run and thus claim computing resources.
  • API Usage; Azure ML allows you to bring an experiment online through the use of RESTful web services. This means you can automate score and training and have applications, websites, etc. use the experiment without human interference. With this you could do an automated credit scoring, recommendation or churn prediction directly from your app or website. In order to make this work you will need to create a web service in Azure ML (also called API). Azure ML charges per hour for compute used in an API that is production, so that is the fee you will need to pay per hour the web service / API is ‘online’ and usable. Also, you will need to pay per 1000 transactions. Transactions in this case are interactions with the API, such as one recommendation, one churn or one credit score.


Hope this clarifies a bit. Please refer to the official page linked above for more details and for the pricing details.


R package for Azure Machine Learning

A little while ago an R package for AzureML was released, which enables R users to interface with Azure Machine Learning (Azure ML). Specifically, it enables you to easily use one of the coolest features of Azure ML: publishing and consuming algorithms / experiments as web services.

Check it out: https://cran.r-project.org/web/packages/AzureML/vignettes/AzureML.html.

First Look: Cortana Analytics Suite

The First Look series focusses on new products, recent announcements, previews or things I have not had the time to provide a first look at and serves as introduction to the subject. First look posts are fairly short and high level.

Cortana Analytics Suite is Microsoft’s connecting and integrating suite of products for Big Data and Advanced Analytics. It combines a number of technologies Microsoft had before into one suite and adds new, ready to use capabilities for business solutions such as churn analysis.

For more information on Cortana Analytics Suite see http://www.microsoft.com/en-us/server-cloud/cortana-analytics-suite/overview.aspx.

Also, please note that there will be a Cortana Analytics Workshop 10/11 september 2015: https://microsoft.eventcore.com/caw2015 .

Webinar on Azure Machine Learning

Last week I did a live webinar on Azure Machine Learning. The webinar can serve as a introduction into the subject of machine learning, data mining, predictive analytics as well as Microsoft’s solution for it: Azure Machine Learning.

Watch the recording here (in Dutch, sorry).

First look: Project Oxford – powerful face, vision, language and speech APIs

Just announced: Project Oxford (http://www.projectoxford.ai), a project that aims at providing powerful APIs for developers that are looking to use face, speech and language recognition capabilities to their applications. The site of Project Oxford provides a way to interact with the APIs currently available.

In this first look we will focus on the Face APIs that can be used for face detection (finding faces in photos, determining gender and age), age verification (checking that a person in two photos is the same), similar face searching, face grouping and face identification.

Here is a sample result of the Face Detection API (you can do this yourself too!) using a photo of me:

This is actually quite good, this picture was made a while ago and I was 29 at the time, so not too far off.

The Face Verification API allows you to check if the person in two photos is the same. Here is the result of my test (again, do this yourself!):

Have a look at that, I turn out to be the same person in both photos J

This is very powerful stuff, I am looking forward to start using this in projects. Will keep you posted on that.

%d bloggers like this: