R and Data Science

Revolution Confidential
Revolution Analytics
R
and
Data Science
Joseph B Rickert
September 25, 2014

Revolution Confidential What is R?
 Most widely used data analysis
software
 Used by 2M+ data scientists,
statisticians and analysts
 Most powerful statistical
programming language
 Flexible, extensible and
comprehensive for productivity
 Platform for beautiful and unique
data visualizations
 As seen in New York Times, Twitter
and Flowing Data
 Thriving open-source community
 Leading edge of analytics research
www.revolutionanalytics.com/what-r

4
R’s popularity is growing rapidly
R Usage Growth
Rexer Data Miner Survey, 2007-2013
• Rexer Data Miner Survey • IEEE Spectrum, July 2014
#9: R
Language Popularity
IEEE Spectrum Top Programming Languages

Revolution Confidential Poll Question #1
 What are the statistical programming
languages/platforms you are most familiar
with? (choose all that apply)
 A) R
 B) SAS
 C) SPSS
 D) KXEN
 E) Statistica
5

Revolution Confidential Tools for Data Science
Source: O’Reilly Data Science Survey
6

7
R is among the highest-paid IT skills in the
US
Dice Tech Salary Survey, January 2014 O’Reilly Strata 2013 Data Science Salary Survey

8
Photo by Ksayer1 on flickr.

Revolution Confidential Why R for Data Science?
X <- if (!is.empty.model(mt))
model.matrix(mt, mf, contrasts)
else matrix(, NROW(Y), 0L)
weights <- as.vector(model.weights(mf))
if (!is.null(weights) && !is.numeric(weights))
stop("'weights' must be a numeric vector")
if (!is.null(weights) && any(weights < 0))
stop("negative weights not allowed")
offset <- as.vector(model.offset(mf))
if (!is.null(offset)) {
if (length(offset) != NROW(Y))
stop(gettextf("number of offsets is %d should equal %d (number of observations)",
length(offset), NROW(Y)), domain = NA)
}
mustart <- model.extract(mf, "mustart")
etastart <- model.extract(mf, "etastart")
fit <- eval(call(if (is.function(method)) "method" else method,
Algorithms
x = X, y = Y, weights = weights, start = start, etastart = etastart,
mustart = mustart, offset = offset, family = family,
control = control, intercept = attr(mt, "intercept") >
0L))
if (length(offset) && attr(mt, "intercept") > 0L) {
fit2 <- eval(call(if (is.function(method)) "method" else method,
x = X[, "(Intercept)", drop = FALSE], y = Y, weights = weights,
offset = offset, family = family, control = control,
intercept = TRUE))
if (!fit2$converged)
warning("fitting to calculate the null deviance did not converge -- increase 'maxit'?")
fit$null.deviance <- fit2$deviance
}
if (model)
fit$model <- mf
fit$na.action <- attr(mf, "na.action")
if (x)
fit$x <- X
if (!y)
fit$y <- NULL
fit <- c(fit, list(call = call, formula = formula, terms = mt,
data = data, offset = offset, control = control, method = method,
contrasts = attr(X, "contrasts"), xlevels = .getXlevels(mt,
mf)))
class(fit) <- c(fit$class, c("glm", "lm"))
fit
9
Task Views

Revolution Confidential R Growth
Put this astonishing growth in
perspective:
 SAS.V 9.3S contains ~
1,200 commands that are
roughly equivalent to R
functions
 R packages contain a
median of 5 functions
 Therefore R has ~ 36,820
functions
 During 2013 alone, R added
more functions than SAS
Institute has written in its
entire history!
Bob Muenchen
10
5882 packages 9/25/14

Visualizations
11

 Scripting
 Functional programming
 Parallel programming
 Data structures
 Objects
 Data Types
 Regular expressions
 Data connections
 Interfaces to other
Programming
languages
12

Data Manipulation
13
“It's often said that 80% of the effort of analysis is spent just getting the data
ready to analyse, the process of data cleaning. Data cleaning is not only a
vital first step, but it is often repeated multiple times over the course of an
analysis as new problems come to light.” Hadley Wickham Tidy Data

R Integrates
 Web applications
 Internet graphics
 D3
 Potly
 Other Languages
 C, C++
 Java
 BI Tools
 Data bases
 SQL
 MongoDB
14

 What are the data platforms that you are
connecting to regularly? (choose all that
apply)
 A) Hadoop
 B) Spark
 C) Cloud-based (Azure/AWS/Google)
 D) Data Warehouses
 E) Servers (Grid or Cluster)
15

Revolution Confidential Why R for Data Science
Hadoop
Servers &
Clusters
Data
Warehouses
R Scales

 What are the types of models that you are
working with most? (choose all that apply)
 A) Linear models / Regression / GLM
 B) Decision Trees / Random Forests
 C) Survival Models
 D) GBM
 E) Time Series models
17

Let’s look at some
code.
www.revolutionanalytics.com
1.855.GET.REVO
Twitter: @RevolutionR

19
Why is R Right for Data Science?
 R is open source
 R is a powerful language
 Data Manipulation
 Computational Statistics
 Machine Learning
 R is an innovation engine
 R has a rich and expanding ecosystem

20
Q&A / Resources
R Code and Markdown Files
https://github.com/joseph-rickert/DataScienceRWebinar
What is R?
revolutionanalytics.com/what-is-r
Companies using R
revolutionanalytics.com/companies-using-r
AcademyR training
revolutionanalytics.com/AcademyR
AcademyR Certification
revolutionanalytics.com/AcademyR-certification
Contact Revolution Analytics
revolutionanalytics.com/contact-us

Thank you
Revolution Analytics is the leading commercial
provider of software and support for the
popular open source R statistics language.
www.revolutionanalytics.com, 1.855.GET.REVO, Twitter: @RevolutionR 21

R and Data Science

More Related Content

What's hot (20)

Viewers also liked (6)

Similar to R and Data Science (20)

More from Revolution Analytics (20)

Recently uploaded (20)

R and Data Science

Editor's Notes