by Robert A. Muenchen
Abstract: This article presents various ways of measuring the popularity or market share of software for advanced analytics software including: Alpine, Alteryx, Angoss, C / C++ / C#, BMDP, IBM SPSS Statistics, IBM SPSS Modeler, InfoCentricity Xeno, Java, JMP, KNIME, Lavastorm, Mathworks’ MATLAB, Megaputer’s PolyAnalyst, Minitab, NCSS, Python, R, RapidMiner, SAS, SAS Enterprise Miner, Salford Predictive Modeler (SPM) etc., SAP’S KXEN, Stata, Statistica, Systat, WEKA / Pentaho.
I don’t attempt to differentiate among variants of languages such as R vs. Revolution R Enterprise or TIBCO Enterprise Runtime for R; or SAS vs. the World Programming System (WPS) or Carolina, except when it is particularly easy such as comparing the company Pagerank figures.
Excluded from the list are products that focus on report writing (e.g. Cognos), or are tied to a specific database (e.g. Microsoft, Oracle, SAP), specific hardware (e.g. Teradata, IBM PureData) or a specific application field. I also exclude packages devoted more to visualization, such as Tableau, Spotfire, Origin, and SigmaPlot.
I announce the regular updates to this article on Twitter, where you can follow me as @BobMuenchen.
When choosing a tool for data analysis, now more commonly referred to as analytics, there are many factors to consider. Does it run natively on your computer? Does the software provide all the methods you use? If not, how extensible is it? Does that extensibility use its own language, or an external one (e.g. Python, R) that is commonly accessible from many packages? Does it fully support the style (programming vs. point-and-click) that you like? Are its visualization options (e.g. static vs. interactive) adequate for your problems? Does it provide output in the form you prefer (e.g. cut & paste into a word processor vs. LaTeX integration)? Does it handle large enough data sets? Do your colleagues use it so you can easily share data and programs? Can you afford it?
There are many ways to measure popularity or market share and each has its advantages and disadvantages. Here they are, in approximate order of usefulness:
- Job Advertisements – these are rich in information and are backed by money so they are perhaps the best measure of how popular each software is now, and what the trends are up to this point.
- Scholarly Articles – these are also rich in information and backed by significant amounts of effort. Since a large proportion come out of academia, the source of new college graduates, they are perhaps the best measurement of new trends in analytics.
- Books – the number of books that include a software’s name in its title is a particularly useful information since it requires a significant effort to write one and publishers do their own study of market share before taking the risk of publishing. However, it can be difficult to do searches to find books that use general-purpose languages which also focus only on analytics.
- Website Popularity – the PageRank measure is objective data, and for sites that clearly focus on analytics, it’s unbiased and especially useful for weeding out the weaker software. However, so much market consolidation has occurred that now focused analytic tools like SPSS are listed under corporations with much broader interests (IBM in that case). In addition, for general-purpose software like Java, many sites that discuss programming point to http://www.java.com, that have nothing to do with its use for analytics.
- Blogs – the number of bloggers writing about analytics software is an interesting measure. Blog posts contain a great deal of information about their topic, and although it’s not as time consuming as a book to write, maintaining a blog certainly requires effort. Unfortunately, this measure is very hard to collect except where sites exist to maintain such lists.
- Surveys of Use – these add additional perspective, but they are commonly done using “snowball sampling” in which the survey provider tries to widely distribute the link and then vendors vie to see who can get the most of their users to participate. So long as they all do so with equal effect, the results can be useful. However, the information is often limited, because the questions are short and precise (e.g. “tools data mining” or “program languages for data mining”) and responding requires just a few mouse clicks, rather than the commitment required to place a job advertisement or publish a scholarly article, book or blog post. As a result, it’s not unusual to see market share jump 100% or drop 50% in a single year, which is very unlikely to reflect changes in actual use.
- Discussion Forum Activity – these web sites or email-based discussion lists can be a very useful source of information because so many people participate, generating many tens of thousands of questions, answers and other commentary for popular software and virtually nothing for others. While talk may be cheap, it’s still a good indicator of popularity.
- Programming Activity – some software development is focused into repositories such as GitHub. That allows people to count the number lines of programming code done for each project in a given time period. This is an excellent measure of popularity since writing programs or changing them requires substantial commitment. However, very popular commercial software may not have much user development activity.
- Popularity Measures – some sites exist that combine several of the measures discussed here into an overall composite score or rank. In particular, they use programming activity and discussion forums.
- IT Research Firm Reports – these firms study the analytics market, interview corporate clients regarding how their needs are being met and/or changing, and write reports describing their take on where each software is now and where they’re headed. While I find the reports very interesting reading, they often focus on the company level so it’s harder to get package-level information from them.
- Sales or Download Measures – the commercial analytics field has undergone a major merger and acquisition phase so that now it is hard to separate out the revenue that comes specifically from analytics. Open source software plays a major role and even the few packages that offer download figures are dicey at best.
- Competition Use – organizations that sponsor analytic competitions occasionally report what the winners tend to use. Unfortunately this information is only sporadically available.
- Growth in Capability – while programming activity (mentioned above) is required before growth in capability can occur, actual growth in capability is a measure of how many new methods of analysis a software package can perform; programming activity can include routine maintenance of existing capability. Unfortunately, most software vendors don’t provide this information and, of course, simply counting the number of new things does not mean they are widely useful new things. I have only been able to collect this data for R, but the results have been very interesting.
One of the best ways to measure the popularity or market share of software for analytics is to count the number of job advertisements for each. Indeed.com is the biggest job site in the U.S. making its sample the best around. As their CEO and co-founder Paul Forster stated, Indeed.com includes “all the jobs from over 1,000 unique sources, comprising the major job boards – Monster, Careerbuilder, Hotjobs, Craigslist – as well as hundreds of newspapers, associations, and company websites.” To demonstrate just how dominant its lead is, a search for SPSS (on 2/19/14) showed more than ten times as many jobs on Indeed.com as on its well-known competitor, Monster.com. Indeed.com also has superb search capabilities and it even includes a tool for tracking long-term trends.
Searching for analytics jobs using Indeed.com can be easy, but it can also be very tricky. For many of the analytics software that required only a simple search on its name. However, for software that’s hard to locate (e.g. R) or that is general purpose (e.g. Java) it required complex searches and/or some rather tricky calculations which are described here. All of the graphs in this section use those procedures to make the required queries.
Figure 1a shows that Java is in the lead followed by SAS. Python or C, C++/C# are roughly tied for third place. The tie between C and Python is not surprising as many advertisements for analytics jobs that use programming mention both together. (The C variants are combined in a single search since job advertisements usually seek any of them).
R resides in an interestingly large gap between the other domain-specific languages, SAS and SPSS. R has not only caught up with SPSS, but surpassed it with around 50% more job postings. MATLAB has many similarities to R so it’s interesting to see that it has only around half the job postings. Note that these are specific to analtyics and MATLAB has many engineering jobs that are not counted in this total.
Much of the software had fewer than 250 jobs. When displayed on the same graph as the industry leaders, their job counts appeared to be zero. Therefore I have plotted them separately in Figure 1b. FICO comes out the leader of this group, followed by Enterprise Miner. Statistica and Alteryx are close to tied at around 55 jobs. From RapidMiner on down, the decline in jobs is fairly smooth. Megaputer’s Polyanalyst job count is actually zero.
It’s important to note that the values shown in Figures 1a and 1b are single points in time. The number of jobs for the more popular software do not change much from day to day. Therefore the relative rankings of the software shown in Figure 1a is unlikely to change much over the coming year. The less popular packages shown in Figure 1b have such low job counts that their ranking is likely to shift from month to month. In addition, each software has an overall trend that shows how the demand for jobs changes across the years. You can plot such trends using Indeed.com’s Job Trends tool. However, as before, focusing just on analytics jobs requires carefully constructed queries, and when comparing two trends at a time means they both have to fit in the same query limit allowed by Indeed.com. Those details are described here.
I’m particularly interested in trends involving R, so let’s look at a couple of comparisons. Figure 1c compares the number of analytics jobs available for R and SPSS across time. Analytics jobs for SPSS have not changed much over the years, while those for R have been steadily increasing. The jobs for R finally crossed over and exceeded those for SPSS toward the middle of 2012.
We know from Figure 1a that SAS is still far ahead of R in analytics job postings. How far does R have to go to catch up with SAS? Figure 1d provides one perspective. It would be nice to have the data to forecast when R’s growth curve will catch up with SAS’s, but Indeed.com does not provide the raw data. However, we can use the approximate slope of each line to get a rough estimate. If jobs for SAS stay level and those for R continue to grow linearly as they have since January 2010, then R will catch up in 3.35 years. If instead the demand for SAS jobs that started in January of 2012 continues, then R will catch up in 1.87 years.
A debate has been taking place on the Internet regarding the relative place of Python and R. Ironically, this debate about software to do data analytics has involved very little actual data. However it is possible now to at least study the job trends. Figure 1a showed us that Python is well out in front of R, at least on that single day the searches were run. What has the data looked like over time? The answer is in Figure 1e.
Note that in this graph, Python appears to have less of advantage in Figure 1e than it had in Figure 1a. The final point on the trend graph was done only a few days after the queries used in Figure 1a, and that data changed very little in the meantime. The difference is due to the fact that Indeed.com has a limit on query length. Here is the query used for Figure 1e, and the analytic terms it contains were fewer than the one used for Figure 1a.
R and ("big data" or "statistical analysis" or "data mining" or "data analytics" or "machine learning" or "quantitative analysis" or "business analytics" or "statistical software" or "predictive modeling") !"R D" !"A R" !"H R" !"R N" !toys !kids !" R Walgreen" !walmart !"HVAC R" !"R Bard" , python and ("big data" or "statistical analysis" or "data mining" or "data analytics" or "machine learning" or "quantitative analysis" or "business analytics" or "statistical software" or "predictive modeling")
One last trend I considered was for Megaputer’s PolyAnalyst. Using the string “Megaputer PolyAnalyst” (“or” is implied) the trend line was completely flat at zero. I only include it here because Gartner considered Megaputer worth including in their Magic Quadrant for Advanced Analytics Platforms report of February 19, 2014.
The detailed description regarding the construction of all the queries used in Figures 1a through 1e is located here.
The more popular a software package is, the more likely it will appear in scholarly publications as a topic or as a tool of analysis. The software that is used in scholarly articles is what the next generation of analysts will graduate knowing, so it’s a leading indicator of where things are headed. Google Scholar offers a way to measure such activity. However, no search of this magnitude is perfect and will include some irrelevant articles and reject some relevant ones. The details of the search terms I used are complex enough to move to a companion article, How to Search For Analytics Articles. Since Google regularly improves its search algorithm, each year I re-collect the data for all years.
Figure 2a shows the number of articles found for each software package for the most recent complete year, 2014. SPSS is by far the most dominant package, likely due to its balance between power and ease-of-use. SAS has around half as many, followed by MATLAB and R. The software from Java through Statgraphics show a slow decline in usage from highest to lowest. Note that the general purpose software C, C++, C#, MATLAB, Java and Python are included only when found in combination with analytics terms, so view those as much rougher counts than the rest.
From RapidMiner on down, the counts appear to be zero. That’s not the case, the counts are just very low compared to the more popular packages, used in tens of thousands articles. Figure 2b shows the software only for those packages that have fewer than 825 articles (i.e. the bottom part of Fig. 2a), so we can see how they compare. RapidMiner, KNIME, SPSS Modeler and SAS Enterprise Miner are packages that all use the powerful and easy-to-use workflow interface, but their use has not yet caught on among scholars. BMDP is one of the oldest packages in existence. Its use has been declining for many years, but it’s still hanging in there. The software in the bottom half of this figure contain the newcomers, with the notable exception of Megaputer, whose Polyanalyst software has been around for many years now.
I’m particularly interested in the long-term trends of the classic statistics packages. So in Figure 2c I’ve plotted the same scholarly-use data for 1995 through 2014, the last complete year of data when this graph was made. As in Figure 2a, SPSS has a clear lead, but now you can see that its dominance peaked in 2008 and its use is in sharp decline. SAS never came close to SPSS’ level of dominance, and it also peaked around 2008. Note that the decline in the number of articles that used SPSS or SAS is not balanced by the increase in the other software shown. This is likely due to the fact that those two leaders faced increasing competition from many more software packages than can be shown in this type of graph (such as those shown in Figure 2a).
Since SAS and SPSS dominate the vertical space in Figure 2c by such a wide margin, I removed those two packages and added the next two most popular statistics packages, Systat and JMP, with the result shown in Figure 2d. Freeing up so much space in the plot now allows us to see that the use of R is experiencing very rapid growth and is pulling away from the pack, solidifying its position in third place. If the current trends continue, the use of R may pass that of SPSS and SAS by the end of 2016. Note that current trends have shifted before as discussed here.
Stata has moved into fourth place, crossing above Statistica in 2014. The growth in the use of Stata is more rapid than all the classic statistics packages except for R. The use of Statistica, Minitab, Systat and JMP are next in popularity, respectively, with their growth roughly parallel to one another. [Note that in the plots from previous years, Statistica was displayed as a flat line at the very bottom of the graph. That turned out to be a search-related artifact. Many academics who use Statistica don’t mention the package by software name but rather say something like, “we used the statistics package by Statsoft.”]
It would be useful to have growth trend graphs for each of the analytics packages I track, but collecting such data is too time consuming since it must be re-collected every year (since search algorithms change). What I’ve done instead is collect data only for the past two complete years, 2013 and 2014. Figure 2e shows the percent change from 2013 to 2014, with the “hot” packages whose use is growing shown in red. Those whose use is declining or “cooling” are shown in blue. Since the number of articles tends to be in the thousands or tens of thousands, I have removed any software that had fewer than 100 articles in 2013. Going from one to five articles may represent 500% growth, but it’s not of much interest.
The three fastest growing packages are all free and open source: Python, R and KNIME. All three saw more than 25% growth. Note that the Python figures are strictly for analytics use as defined here. At the other end of the scale are SPSS and SAS, both of which declined in use by around 25%. Recall that Fig. 2a shows that despite recent years of decline, SPSS is still extremely dominant for scholarly use.
Three of the packages whose use is growing implement the powerful and easy-to-use workflow or flowchart user interface: KNIME, RapidMiner and SPSS Modeler. As useful as that approach is, it’s not sufficient for success as we see with SAS Enterprise Miner, whose use declined nearly 15%.
It will be particularly interesting to see what the future holds for KNIME and RapidMiner. The companies were two of only four chosen by the Gartner Group as having both a complete vision of the future and the ability to execute that vision (Fig. 7a). Until recently, both were free and open source. RapidMiner then started charging for its current version, leaving its older version as the only free one. Recent offers to make it free for academic use don’t include use on projects with grant funding, so I expect KNIME’s higher rate of growth to remain faster than RapidMiner’s. However, in absolute terms, scholarly use of RapidMiner is currently almost twice that of KNIME, as shown in Fig. 2b.
The number of books published on each software reflects their relative popularity. Amazon.com offers an advanced search method which works well for all the software except R. I configured it with the following parameters:
Title: SAS -excerpt -chapter -changes [using SAS as an example]
Subject: Computers & Internet
Format: All formats
Publication Date: After September, 2001 [i.e. 10 years before the search on 10/13/2011]
Since it’s difficult to determine how many books use a particular software in its examples, I searched for books that included the software in the title. SAS has many manuals for sale as individual chapters or excerpts. Luckily, they contain “chapter” or “excerpt” in their title so I excluded them using the minus sign, e.g. “-excerpt”. SAS also has short “changes and enhancements” booklets that the other packages release only in the form of flyers and/or web pages so I excluded “changes” as well.
SAS and SPSS both have many versions of the same book or manual still for sale. For example, Marija Norusis’ 3 books on SPSS appear 20 times for various versions of SPSS released in the last 10 years. The SAS and SPSS numbers are both somewhat inflated as a result. Limiting the search to books published in the last 10 years mitigated this problem somewhat, but the SAS and SPSS figures are probably both still somewhat exaggerated.
The count of R books came from http://www.r-project.org/doc/bib/R-books.html. This list does contain seven books on S that are older but still relevant. Version numbers do not appear in any book titles so R avoids the over-counting problem that plagued my count of SAS and SPSS manuals. The most surprising aspect of the result (Figure 3) was how extremely dominant the top few packages are and that three well known packages had no books at all written about them (BMDP, Statistica, Systat). Revolution R and R-PLUS have no books with their names in the titles, but of course the books on R apply to them as well.
Another measure of software popularity is the number of other web pages that contain links that point to the software’s main web site. Figure 4 provides those numbers, recorded using Google on January 5, 2012.
Now that SPSS is part of IBM, it dominates the results. This reflects the wide range of products that IBM sells, including computer hardware and services that have nothing to do with data analysis. However, the older SPSS.com website no longer shows up early in a web search and the IBM site that it redirects to has a tiny incoming link measure since it is not meant to be a direct link.
R is next in line with a little over half of IBM’s measure, followed by SAS with well less than R’s value. The other software follows in the order that I suspect is reflective of their respective market shares. Revolution R Enterprise and R-PLUS are commercial versions of R that are relatively quite new to the market. WPS is an implementation of the SAS Language and Carolina is a SAS-to-Java compiler.
The number of incoming links is an important part of Google’s famous PageRank algorithm (http://en.wikipedia.org/wiki/PageRank). PageRank is made more useful for searching by (among other things) weighting the importance of each link. Links from major sites like WikiPedia would carry far more weight than would a link from a professor’s course syllabus. The practical range of PageRank is from 1 to 10. Figure 9 plots this data (collected on on January 4, 2012). The software appear in tiers, with the two dominant players, SAS and SPSS (IBM), at the highest, and their well-known alternatives one level down. I find it odd that Stata is not in this level. At the very bottom are the World Programming System (WPS) and Carolina, two companies that use the SAS language. There have been quite a few changes in this ranking since last year, with SAS, SPSS and Revolution Analytics moving up one point and R, Stata and Carolina moving down one point. The R-PLUS site maintained its PageRank of 5 this year, which is a bit surprising given that many of its links are broken, and it is in its fourth year of saying, “Be the first to get R-PLUS 3.3″
On Internet blogs, people write about software that interests them, showing how to solve problems and interpreting events in the field. Blog posts contain a great deal of information about their topic, and although it’s not as time consuming as a book to write, maintaining a blog certainly requires effort. Therefore, the number of bloggers writing about analytics software has potential as a measure of popularity or market share. Unfortunately, counting the number of relevant blogs is often a difficult task. General purpose software such as Java, Python, the C language variants and MATLAB have many more bloggers writing about general programming topics than just analytics. But separating them out isn’t easy. The name of a blog and the title of its latest post may not give you a clue that it routinely includes articles on analytics.
Another problem arises from the fact that what some companies would write up as a newsletter, others would do as a set of blogs, where several people in the company each contribute their own blog, but they’re also combined into a single company blog. Statsoft and Minitab offer examples of this. So what’s really interesting is not company employees who are assigned to write blogs, but rather those written by outside volunteers. In a few lucky cases, lists of such blogs are maintained, usually by blog consolidators, who combine many blogs into a large “metablog.” All I have to do is find such lists and count the blogs. I don’t attempt to extract the few vendor employees that I know are blended into such lists. I only skip those lists that are exclusively employee-based (or very close to it). The results are shown in Table 1.
Number Software of Blogs Source R 550 R-Bloggers.com Python 60 SciPy.org SAS 40 PROC-X.com, sasCommunity.org Planet Stata 11 Stata-Bloggers.com
Table 1. Number of blogs devoted to each software package on April 7, 2014, and the source of the data.
R’s 550 blogs is quite an impressive number. For Python, I could only find that list of 60 that were devoted to the SciPy subroutine library. Some of those are likely cover topics besides analytics, but to determine which never cover the topic would be quite time consuming. The 40 blogs about SAS is still an impressive figure given that Stata was the only other company that even garnered a list anywhere. That list is at the vendor itself, Statacorp, but it consists of non-employees except for one.
While searching for lists of blogs on other software, I did find individual blogs that at least occasionally covered a particular topic. However, keeping this list up to date is far too time consuming given the relative ease with which other popularity measures are collected.
If you know of other lists of relevant blogs, please let me know and I’ll add them. If you’re a software vendor employee reading this, and your company does not build a metablog or at least maintain a list of your bloggers, I recommend taking advantage of this important source of free publicity.
Discussion Forum Activity
There are some stable and objective measures regarding analytic software. Schwartz (2009) suggested estimating relative popularity by plotting the amount of email discussion devoted to each. The most widely used packages all have discussion lists, or “listservs” devoted to them. The less popular ones either do not have such discussions or, like the lists for Minitab or S-PLUS, may have only a dozen or so emails per year. Some software packages have multiple discussion lists. For example, there are 25 devoted to using R (http://www.r-project.org/mail.html). Topics range from general help to various focused areas such as graphics, mapping, ecology, epidemiology, etc. . A broader list, including a version of R-Help in Spanish, lists 48 discussions (https://stat.ethz.ch/mailman/listinfo).
Figure 1a shows the level of activity on only each main discussion listserv in a typical month (i.e. forums, news groups and Google groups are excluded). Each point represents the sum of the 12 monthly counts that occurred in that year. This plot contains data through the end of 2012. If you read this article in previous years, this plot used to display the mean number of emails per month rather than the sum. Therefore the scale of the y-axis is different but the relative locations of the points are virtually identical. I made this change to enable better a better comparison to discussion forums (e.g. Fig. 5a).
We can see that discussion of R has grown the most rapidly and, for the past few years, R is the most discussed software by an almost two-to-one margin. In recent years, it is followed by Stata, SAS and SPSS, respectively.
Stata showed steady discussion growth until it passed SAS in 2010.
SAS saw rapid growth in its discussion until 2006 when it leveled off and then declined. That decline coincided with the strong growth of both R and Stata, offering competition to SAS.
SPSS held steady at a low rate across the time frame, which may be attributable to its great ease of use relative to the other packages. With both the interface and the documentation aimed at people who prefer GUIs over programming, there’s less need to ask how to do variations on an analysis. In fact, there’s less ability to do such variations. As a result, I doubt SPSS’ low showing in this graph is indicative of its popularity or market share.
It would be interesting to see what topics were most discussed on each list. The only such analysis of which I am aware was done by Arthur Tabachnek (2010) for the SAS list. The most popular topic in 2009 turned out to be…R! You can read his full analysis here under slides from the 2010 session.
From 2011 onward, R and Stata joined SAS in the decline in listserv discussion. Given the sharp increase in the popularity of business analytics, Big Data, and so on, it is unlikely that people are using or talking about these tools less. Instead, alternative forums of discussion have appeared. The site Stack Overflow (http://stackoverflow.com) covers a wide range of programming and statistical topics, while its sister site, Cross Validated (http://stats.stackexchange.com/), focuses only on statistical analysis. A third site, Talk Stats (http://www.talkstats.com), also focuses on statistical analysis. At all three sites, users tag their topics making it particularly easy to focus searches. Figure 5b shows the software people are discussing there.
We can see that the discussion of R is dramatically higher than the other packages, which don’t differ very much among themselves. Much of this difference is due to the influence of Stack Overflow, reflecting the vastly greater popularity of R as a programming language. However, even removing that effect, it is easy to see that R still dominates the discussions on the more statistically-oriented forums. This data is cumulative, but we can get a yearly view of just two of the tags: R and SAS (Figure 5c).
We see that discussion of SAS and R were roughly comparable until mid-2009 when the discussion of R began its very rapid climb. The page that provides this data does not display data for SPSS or Stata. The amount of data may be too low; no message provides the reason (see http://hewgill.com/~greg/stackoverflow/stack_overflow/tags).
Other popular discussion forum sites are LinkedIn.com and Quora.com. Neither of these sites make it easy to count number of posts, but they do display the number of people who have joined discussion groups (Figure 5d).
In Figure 1d we get a better view of corporate software use. I do not know the ratio of corporate to academic use of LinkedIn, but among the academics I do know (quite a few) they use it very little. In this world, SAS is the leader with R close behind. It’s interesting to see SPSS with a 50% lead over Stata; it was also slightly higher in Fig. 1b. Remember these are people who have joined a group, not necessary people who are talking as the previous two figures were. Still, group membership should be a reasonable proxy for popularity or market share.
7. Programming Activity
This section is planned for future expansion. Stay tuned.
The TIOBE Community Programming Index ranks the popularity of programming languages, but from a programming language perspective rather than as analytical software (http://www.tiobe.com). It extracts measurements from blogs, entries in Wikipedia, books on Amazon, and search engine results, and combines them into a single index. In January 2012, they ranked R in 24th place and SAS at 31st. However, by February 2014, the two had reversed positions with SAS in 21st place and R in 44th.
The only other language that focuses on data analysis that is ranked in the top 100 are S and S-PLUS (R is an implementation of the S language, as is S-PLUS). In previous years SPSS ranked in the 50-100 group but by February of 2013 it had dropped out (and is still out in February 2014.)
The Transparent Language Popularity Index is very similar to the TIOBE Index with except that its ranking software, algorithm and data are published for all to see. Their latest figures on 2/15/2014 were from July of 2013, at which time it ranked R in 14th place and SAS in 31st. This index also ranks R as a scripting language, where it is in 6th place after tools like PHP, Python and Perl. SAS is also ranked 5th in the “Other” category, when compared to languages such as like COBOL or PL/SQL. While these two additional areas may seen irrelevant to data analysis, it’s good to know both these tools have more flexibility than most other domain specific languages which focus on data analysis.
Langpop.com also ranks programming languages (http://langpop.com/) in a variety of interesting ways, but unfortunately their focus excludes statistical software.
Surveys of Use
One way to estimate the relative popularity of data analysis software is though a survey. Rexer Analytics does a survey every other year asking a wide range of questions regarding data mining. Figure 6a shows the results of the question about the tools that respondents reported using in 2013.
We see that R comes out on top by a wide margin, with 70% of data miners using it. SPSS, RapidMiner, SAS and Weka all follow with only around 30% of users. The entire report contained over 40 questions on topics such as algorithms used, fields, challenges, data, impact of the economy on the field, and more. It’s interesting to note that while this survey is aimed at data miners, SPSS and SAS are used more often than their more expensive products aimed specifically at data mining, IBM SPSS Modeler and SAS Enterprise Miner.
The results of a similar poll done by the data mining web site KDnuggets in 2013 are shown in Figure 6b. This one shows RapidMiner in first place with 39.2% of users reporting having used it for a real project. R follows closely behind with 37.4% of users. There’s quite a large gap in which Excel resides, with 28% of users. Weka/Pentaho and Python are tied at 14.3%, followed by the rest. Note that both RapidMiner and KNIME are listed twice, once in their free version and again in commercial. While it’s tempting to add these two, there may be overlap for organizations that use both.
It’s interesting to note that four of the top five packages used were open source.
The KDnuggets site conducted similar poll, this time asking, “What programming languages you used for data mining / data analysis in the past 12 months?” R dominated this poll with over 60% of respondents, as shown in Figure 6c. Python and SQL followed with around 37% each.
O’Reilly Media conducted a survey of conference attendees in 2012 and 2013 of the Strata Conference: Making Data Work and Strata + Hadoop World. The top bar in Figure 6d shows that 57% of respondents listed some form of data analysis as their primary job. SQL is listed as the top tool with 71% of respondents using it. This indicates that most attendees stored their data in relational databases. R came out as the top tool for advanced analytics, with 43% of respondents using it. Given that some respondents were attending Hadoop world, it’s not surprising that both Hadoop and the related Mahout came out higher here than in most other measures of popularity discussed in this paper. The fact that SAS/SPSS came out the bottom is another clear indication that this is not a random sample of analytics users.
Lavastorm, Inc. conducted a survey of analytic communities including LinkedIn’s Lavastorm Analytics Community Group, Data Science Central and KDnuggets. The results were published in March, 2013, and the bar chart of “self-service analytic tool” usage among their respondents is shown in Figure 6e. Excel comes out as the top tool, with 75.6% of respondents reporting its use. While other surveys show Excel use similarly high, some don’t include it at all, leaving us to wonder what survey researchers and respondents were thinking regarding this relatively low-powered tool.
R comes out as the top advanced analytics tool with 35.3% of respondents, followed closely by SAS. MS Access’ position in 4th place is a bit of an outlier as no other surveys include it at all. Lavastorm comes out with a much higher market share (3.4%) than the KDNuggests poll indicated (0.4%), but that’s hardly a surprise given than the survey was aimed at the Lavastorm’s LinkedIn community group.
IT Research Firms
IT research firms study software products and corporate strategies, they survey customers regarding their satisfaction with the products and service, and then provide their opinions on each in reports they sell to their clients. Each company has its own criteria for rating companies, so they don’t always agree. However, I find the reports extremely interesting reading. While the reports are expensive, you can usually find free copies by searching the internet for the report names in combination with the name of one of the companies that received a good review.
Gartner, Inc. is one of the companies that provides such reports. The KDnuggets web site combined two years of “Magic Quadrant” plots from from Gartner’s report, Advanced Analytics for Business Analysts, and the result is shown in Figure 7a. Gray circles show where Gartner rated each company in 2014 and blue ones show their 2015 rating. If the company improved, a green arrow points to their new position. If the company received a worse rating, a red arrow shows where they moved to. Black arrows show changes that are relatively neutral. Since Gartner rates companies, strictly open source software such as R, Python and Java are not shown.
For both years, IBM (SPSS), SAS, RapidMiner and KNIME are the companies in the Leaders quadrant, indicating that they have both “completeness of vision” and the ability to execute that vision. Of these, KNIME is the only one whose core desktop product is free and open source. RapidMiner offers an older version of their software for free.
Microsoft improved the most, especially in its completeness of vision. This may be due to the release of their Azure Machine Learning platform. Alpine, Alteryx and SAS also improved their positions. Angoss dropped quite a bit and a few companies were removed altogether for various reasons described in the report. The display shows Statsoft (Statistica) being bought by Dell and barely moving, but Microsoft’s acquisition of Revolution Analytics is not reflected in this plot.
Forrester Research, Inc. is another company that provides similar reports. The KDnuggets site overlaid the “Wave” plots from their two most recent reports, The Forrester Wave: Big Data Predictive Analytics Solutions, shown in Figure 7b. The lighter circles represent each company’s position in the previous report (2013) and the more solid white circles represent their position in 2015.
Again, IBM (SPSS) and SAS are the strongest companies, but that seems to be all that the two reports seem to agree on! The reports emphasize different aspects of the companies being rated, which accounts for the radically different plots. While the Gartner report showed Angoss losing strength, the Forrester analysts see it gaining strength! RapidMiner is not in the Leaders area here, but at least it’s close. KNIME on the other hand is barely inside the Strong Performer area.
Hurwitz & Associates released their Advanced Analytics: The Hurwitz Victory Index Report in mid 2014. Figure 7c shows their plot of strength of company strategy vs. viability. This is similar to the measures plotted in the Gartner Group’s Magic Quadrant plot (Fig. 7a). These two plots both show IBM and SAS in the best position, but after that there’s not much similarity. Gartner sees RapidMiner in the same ballpark as IBM and SAS, while Hurwitz shows it towards the opposite end. KNIME is also toward the top of Gartner’s plot and not covered by Hurwitz at all.
Sales & Downloads
Sales figures reported by some commercial vendors include products that have little to do with analysis. Many vendors don’t release sales figures, or they release them in a form that combines many different products, making the examination of a particular product impossible. For open source software such as R (Ihaka and Gentleman 1996) you could count downloads, but one confused person can download many copies, inflating the total. Conversely, many people can use a single download on a server, deflating it.
Download counts for the R-based Bioconductor project are located at http://www.bioconductor.org/packages/stats/. Similar figures for downloads of Stata add-ons (not Stata itself) are available at http://fmwww.bc.edu/fmrc/reports/Report.SSC.html. A list of Stata repositories is available at http://stata.com/links/resources2.html. The many sources of downloads both in repositories and individuals’ web sites makes counting downloads a very difficult task.
Kaggle.com is a web site that sponsors data analysis contests. People post data analysis problems there along the amount of money they are willing pay the person or team who solves their problem the best. Figure 8 shows the software used by the data analysts working on the problems. R is in the lead by a wide margin. R’s dominance is even greater among the contest winners, over 50% of whom used R. A potential source of bias in these figures is that the licenses of most proprietary software prohibits its use for the benefit of outside organizations (universities can help federal grant-providing agencies such as NSF and NIH, but cannot even solve problems for government agencies in general or nonprofits). However, I manage the research software site licenses at the University of Tennessee, and I can attest to the fact that people are often unaware of this limitation. (Note that as of 4/11/2014 this graph of 2011 data is still Kaggle’s most current graph.)
Growth in Capability
The capability of analytics software has grown significantly over the years. It would be helpful to be able to plot the growth of each software package’s capabilities, but such data are hard to obtain. John Fox (2009) acquired them for R’s main distribution site http://cran.r-project.org/. I collected the data for later versions following his method.
Figure 9 shows that the growth in R packages is following a rapid parabolic arc (quadratic fit with R-squared=.998). The right-most point is for version 3.0.2, the last version released in 2013.
To put this astonishing growth in perspective, let us compare it to the most dominant commercial package, SAS. In version, 9.3, SAS contains around 1,200 commands that are roughly equivalent to R functions (procs, functions etc. in Base, Stat, ETS, HP Forecasting, Graph, IML, Macro, OR, QC). In 2013, R added 835 packages, counting only CRAN, or approximately 17,390 functions. During 2013 alone, R added more functions/procs than SAS Institute has written in its entire history!
Of course SAS and R commands are not perfectly equivalent. Some SAS procedures have many more options to control their output than R functions do. However, R functions can nest inside one another, creating nearly infinite combinations. Also, SAS is now out with version 9.4 and I have not repeated the arduous task of recounting its commands. If SAS Institute would provide the figure, I would be happy to list it here. While the comparison is not perfect, it does provide an interesting perspective on the size and growth rate of R.
As rapid as R’s growth has been, these data represent only the main CRAN repository. R has eight other software repositories, such as Bioconductor, that are not included in
Figure 8. A program run on 4/11/2014 counted 7,380 R packages at all major repositories, 5,339 of which were at CRAN. So the growth curve for the software at all repositories would be roughly 38% higher on the y-axis than the one shown in Figure 8. The total growth in R functions for 2013 was approximately 17,390 * 1.38 or 23,998.
As with any analysis software, individuals also maintain their own separate collections typically available on their web sites. Those are not easily counted.
What’s the total number of R functions? The Rdocumentation site shows the latest figures counts of both packages and functions on CRAN. They indicate that there are an average of 20.826 functions per package. Since a program on 4/7/2014 counted 7,364 R packages at all major repositories, on that date there were approximately 153,696 total functions in R, over an order of magnitude more than commands in SAS.
I previously included on Google Trends. That site tracks not what’s actually on the Internet via searches, but rather the keywords and phrases that people are entering into their Google searches. That ended up being so variable as to be essentially worthless. For an interesting discussion of this topic, see this article by Rick Wicklin.
I’m interested in other ways to measure software popularity. If you have any ideas on the subject, please contact me at firstname.lastname@example.org.
If you are a SAS or SPSS user interested in learning more about R, you might consider my book, R for SAS and SPSS Users. Stata users might want to consider reading R for Stata Users, which I wrote with Stata guru Joe Hilbe. I also teach workshops quarterly on these topics with Revolution Analytics.
I am grateful to the following people for their suggestions that improved this article: John Fox (2009) provided the data on R package growth; Marc Schwartz (2009) suggested plotting the amount of activity on e-mail discussion lists; Duncan Murdoch clarified the pitfalls of counting downloads; Martin Weiss pointed out both how to query Statlist for its number of subscribers; Christopher Baum provided information regarding counting Stata downloads; John (Jiangtang) HU suggeseted I add more detail from the TIOBE index; Andre Wielki suggested the addition of SAS Institute’s support forums; Kjetil Halvorsen provided the location of the expanded list of Internet R discussions; Dario Solari and Joris Meys suggested how to improve Google Insight searches; Keo Ormsby provded useful suggestions regarding Google Scholar; Karl Rexer provided his data mining survey data; Gregory Piatetsky-Shapiro provided his KDnuggets data mining poll; Tal Galili provided advice on blogs and consolidation, as well as Stack Exchange and Stack Overflow; Patrick Burns provided general advice; Nick Cox clarified the role of Stata’s software repositories and of popularity itself; Stas Kolenikov provided the link of known Stata repositories; Rick Wicklin convinced me to stop trying to get anything useful out of Google Insights; Drew Schmidt automated the collection of the data in Figures 7a and 7b; Francois Briatte provided the link that creates Figure 1c; Rasmus Bååth provided the median number of functions in an R package.
J. Fox. Aspects of the Social Organization and Trajectory of the R Project. R Journal, http://journal.r-project.org/archive/2009-2/RJournal_2009-2_Fox.pdf
R. Ihaka and R. Gentleman. R: A language for data analysis and graphics. Journal of Computational and Graphical Statistics, 5:299–314, 1996.
R. Muenchen, R for SAS and SPSS Users, Springer, 2009
R. Muenchen, J. Hilbe, R for Stata Users, Springer, 2010
M. Schwartz, 1/7/2009, http://tolstoy.newcastle.edu.au/R/e6/help/09/01/0517.html
Alpine, Alteryx, Angoss, Microsoft C#, BMDP, IBM SPSS Statistics, IBM SPSS Modeler, InfoCentricity Xeno, Oracle’s Java, SAS Institute’s JMP, KNIME, Lavastorm, Mathworks’ MATLAB, Megaputer’s PolyAnalyst, Minitab, NCSS, Python, R, RapidMiner, SAS, SAS Enterprise Miner, Salford Predictive Modeler (SPM) etc., SAP’S KXEN, Stata, Statistica, Systat, WEKA / Pentaho are are registered trademarks of their respective companies.
Copyright 2010-2015 Robert A. Muenchen, all rights reserved.