I have passed the 7 full years of my corporate work experience working at SAS. Then, when I heard that SAS released a free version (at the end of may), I was very excited! My initial reaction was that if SAS were available for free, would become the analytics tool of choice for people entering the industry.
It is easier to learn (compared to R), has the highest market share (in terms of number of jobs) with great customer service (read more details here). As usual, high cost is the biggest hindrance to its wide use among freelancers, consultants, trainers and data scientists. If SAS offers a free version, it would be like having the best of both worlds. Did it really turn out to be like this? Good, We'll find out in a few minutes!
The free offer: SAS Analytics U (the SAS University edition)
Let's take a look at what SAS has to offer in its free version and then try to understand what they were trying to achieve.. The free offer, which is called SAS Analytics U, can be downloaded free for teaching, learning and research.
This is what SAS says in its overview page:
Our new software for teaching, learning and research in higher education is now available to download for free. Gain access to the latest SAS software and programming environments for data analysis and reporting.
Sounds good! Despite this, not sure what is classified here as learning and research. I participate in Kaggle competitions for learning, then, Can i use it there? I'm not sure. I think you better check it. You can download the software here.
Components of SAS Analytics U:
Think, i will download it anyway and use the software to teach it to some people, used to train. I was expecting the next surprise as soon as I went into details.. These are the components that are available for download in SAS Analytics U:
- SAS base
- SAS / STAT
- SAS / IML
- SAS interface / ACCESS to PC files
- SAS Studio
My eyes were wide open when I first saw this list.. There is no SAS / GRAPH in this package! How to complete an analysis without the use of PROC GCHART? Who uses SAS without having access to SAS / GRAPH? In the beginning, this seemed like a serious limitation to me. Fortunately, SAS has included ODS charts in the package. Therefore, you should use PROC SGCHART instead of PROC GCHART. SGPLOT's output looked better compared to GPLOT and SAS has provided easy access to the GUI in SAS Studio, so that even a beginner can learn SGPLOT.
There are a few more components SAS could have added, as an example, SAS / ETS, SAS / OR o SAS / QC. SAS Enterprise Guide, Enterprise Miner or Visual Analytics would have been the icing on the cake, But for now, We will have to live with what SAS has provided! They told me more will come in July. Until then, my decision trees must wait!
Installation:
You must set up a virtual environment (via Oracle Virtualbox or VMware Player), which can be downloaded for free for non-commercial uses. Then, I went ahead and did. Virtualbox seemed to slow down even my high-end monster: Quad core i7, 16 GB of RAM and it didn't work for some reason. Besides, VMware worked fine and was activated as soon as I finished downloading more than 1,5 Installation GB.
I loved seeing the SAS graph on my screen. Launch SAS Studio through your browser. The interface is uncluttered and should be familiar to anyone who has used base SAS in the past.
I tried installing the same in Ubuntu 12.04, but SAS Studio failed to load, something to investigate at a later time.
Performance:
SAS has imposed limitations on the amount of memory / processing power you can use. You can only use a maximum of 1 O 2 GB of RAM with 2 processors. Then, clearly, SAS does not offer Analytics U for advanced learning. This was the second deciding factor for me (the first is the missing components)
Community:
A new initiative that is important to mention is the community SAS is trying to create with Analytics U. Has Facebook channels, Linkedin and YouTube. Despite this, the community is very small at the moment and lacks the quality of discussions you might see about R or Python in your communities. Let's see how it grows and if it becomes a meaningful community in the future.
General verdict:
It is encouraging to see SAS react to open source software and its rise in recent years. He has definitely made a good attempt to get the first product out. Despite this, the current product is aimed at new students. I think they have put too many limitations to attract serious students.
Having said this, not too far from a product that can provide a SAS career path for people entering the industry. If you can add the (few) missing key components, can become a springboard for future analysts / data scientists. Until that moment, R and Python continue to reign in this place. I will not be away from any of them in the near future.
It would be interesting to see what SAS comes out with in a few days. I'm following this space closely.
