Posit, formerly RStudio, is a modular data science platform, combining open source and commercial products.
N/A
SAS Enterprise Miner
Score 8.2 out of 10
N/A
SAS Enterprise Miner is a data science and statistical modeling solution enabling the creation of predictive and descriptive models on very large data sources across the organization.
In the space of data science tools, code is king. It enables use of standard version control systems like git, access to a wealth of expertise via StackOverflow and others, is commonly used in modern education programs, and more. Other solutions in this space are built on …
In my humble opinion, if you are working on something related to Statistics, RStudio is your go-to tool. But if you are looking for something in Machine Learning, look out for Python. The beauty is that there are packages now by which you can write Python/SQL in R. Cross-platform functionality like such makes RStudio way ahead of its competition. A couple of chinks in RStudio armor are very small and can be considered as nagging just for the sake of argument. Other than completely based on programming language, I couldn't find significant drawbacks to using RStudio. It is one of the best free software available in the market at present.
SAS Enterprise Miner is world-class software for individuals interested in developing reproducible models in a reasonable amount of time. Perhaps the most useful part of SAS Enterprise Miner is the ability to compare models with other models without writing code. The ensemble modeling capabilities is the easiest way to do ensemble modeling I have come across. SAS Enterprise Miner is well-suited for beginning to advanced analysts who know something about advanced analytics. The software is not well-suited for analysts or companies that have little interest in advanced modeling.
The support is incredibly professional and helpful, and they often go out of their way to help me when something doesn't work.
The one-click publishing from RStudio Connect is absolutely amazing, and I really like the way that it deploys your exact package versions, because otherwise, you can get in a terrible mess.
Python doesn't feel quite as native as R at the moment but I have definitely deployed stuff in R and Python that works beautifully which is really nice indeed.
Enterprise Miner is really visual and lets you do a whole lot without actually going into the detailed options. For decent results, you should really explore the different advanced options though.
The recent versions of Miner allow users to use R code in Miner. You can then compare several models and approach to get the best performing model.
The resulting data is really well displayed and easy to understand (ex: the lift graph, score ranking, etc.)
Miner has the ability to integrate custom SAS code which allows the user to add functionalities that are specific to the project.
Python integration is newer and still can be rough, especially with when using virtual environments.
RStudio Connect pricing feels very department focused, not quite an enterprise perspective.
Some of the RStudio packages don't follow conventional development guidelines (API breaking changes with minor version numbers) which can make supporting larger projects over longer timeframes difficult.
With large data sets, SAS Enterprise Miner sometimes takes a long time to run. Sometimes you have to just leave your computer running while Enterprise Miner does its thing.
If you want complete control over the modeling framework, you have to take what Enterprise Miner does and customize it. SAS seems to be working hard on making things easier to customize, but it's not completely there yet.
The graphic capabilities of SAS Enterprise Miner leave a lot to be desired, especially in the era of self-service business intelligence software.
There is no viable alternative right now. The toolset is good and the functionality is increasing with every release. It is backed by regular releases and ongoing development by the RStudio team. There is good engagement with RStudio directly when support is required. Also there's a strong and growing community of developers who provide additional support and sample code.
I think it's a quick and easy to use tool. The IDE is very intuitive and easy to adapt to. You do not need to learn a lot of things to use this tool. Any programmer and a person with knowledge or R can quick use this tool without issues.
RStudio is very available and cheap to use. It needs to be updated every once in a while, but the updates tend to be quick and they do not hinder my ability to make progress. I have not experienced any RStudio outages, and I have used the application quite a bit for a variety of statistical analyses
Since R is trendy among statisticians, you can find lots of help from the data science/ stats communities. If you need help with anything related to RStudio or R, google it or search on StackOverflow, you might easily find the solution that you are looking for.
I have contacted SAS twice in the past year and they have been super responsive both times. They solved my problem. I am also registered for an in-person class next month and they called today to tell me that it will be an online-only session. They apologized for the change and registered me for the online version. Super helpful!
RStudio was provided as the most customizable. It was also strictly the most feature-rich as far as enabling our organization to script, run, and make use of R open-source packages in our data analysis workstreams. It also provided some support for python, which was useful when we had R heavy code with some python threaded in. Overall we picked Rstudio for the features it provided for our data analysis needs and the ability to interface with our existing resources.
SAS EM has a very great set of machine learning and predictive analytics toolsets, which helped our organization achieve its goals. We used other tools, but for us, SAS EM was the most intuitive and easy to learn the tool and it provides greater data exploration and data preparation capabilities compared to the other tools we used.
RStudio is very scalable as a product. The issue I have is that it doesn't necessarily fit in nicely with the mainly Microsoft environment that everybody else is using. Having RStudio for us means dedicated servers and recruiting staff who know how to manage the environment. This isn't a fault of the product at all, it's just part of the data science landscape that we all have to put up with. Having said that RStudio is absolutely great for running on low spec servers and there are loads of options to handle concurrency, memory use, etc.
Using it for data science in a very big and old company, the most positive impact, from my point of view, has been the ability of spreading data culture across the group. Shortening the path from data to value.
Still it's hard to quantify economic benefits, we are struggling and it's a great point of attention, since splitting out the contribution of the single aspects of a project (and getting the RStudio pie) is complicated.
What is sure is that, in the long run, RStudio is boosting productivity and making the process in which is embedded more efficient (cost reduction).
