Neglected optimization topic: set diversity

Posted on Categories Applications, data science, Expository Writing, Opinion, Practical Data Science, Pragmatic Data Science, Pragmatic Machine Learning, Statistics, TutorialsTags , , , , , Leave a comment on Neglected optimization topic: set diversity

The mathematical concept of set diversity is a somewhat neglected topic in current applied decision sciences and optimization. We take this opportunity to discuss the issue.

The problem

Consider the following problem: for a number of items U = {x_1, … x_n} pick a small set of them X = {x_i1, x_i2, ..., x_ik} such that there is a high probability one of the x in X is a “success.” By success I mean some standard business outcome such as making a sale (in the sense of any of: propensity, appetency, up selling, and uplift modeling), clicking an advertisement, adding an account, finding a new medicine, or learning something useful.

This is common in:

  • Search engines. The user is presented with a page consisting of “top results” with the hope that one of the results is what the user wanted.
  • Online advertising. The user is presented with a number of advertisements in enticements in the hope that one of them matches user taste.
  • Science. A number of molecules are simultaneously presented to biological assay hoping that at least one of them is a new drug candidate, or that the simultaneous set of measurements shows us where to experiment further.
  • Sensor/guard placement. Overlapping areas of coverage don’t make up for uncovered areas.
  • Machine learning method design. The random forest algorithm requires diversity among its sub-trees to work well. It tries to ensure by both per-tree variable selections and re-sampling (some of these issues discussed here).

In this note we will touch on key applications and some of the theory involved. While our group specializes in practical data science implementations, applications, and training, our researchers experience great joy when they can re-formulate a common problem using known theory/math and the reformulation is game changing (as it is in the case of set-scoring).


Rplot01

Minimal spanning trees, the basis of one set diversity metric.

Continue reading Neglected optimization topic: set diversity

Using PostgreSQL in R: A quick how-to

Posted on Categories Coding, data science, Expository Writing, Practical Data Science, Pragmatic Data Science, TutorialsTags , , , , , , , , 4 Comments on Using PostgreSQL in R: A quick how-to

The combination of R plus SQL offers an attractive way to work with what we call medium-scale data: data that’s perhaps too large to gracefully work with in its entirety within your favorite desktop analysis tool (whether that be R or Excel), but too small to justify the overhead of big data infrastructure. In some cases you can use a serverless SQL database that gives you the power of SQL for data manipulation, while maintaining a lightweight infrastructure.

We call this work pattern “SQL Screwdriver”: delegating data handling to a lightweight infrastructure with the power of SQL for data manipulation.

NewImageImage: Iainf, some rights reserved.

We assume for this how-to that you already have a PostgreSQL database up and running. To get PostgreSQL for Windows, OSX, or Unix use the instructions at PostgreSQL downloads. If you happen to be on a Mac, then Postgres.app provides a “serverless” (or application oriented) install option.

For the rest of this post, we give a quick how-to on using the RpostgreSQL package to interact with Postgres databases in R.

Continue reading Using PostgreSQL in R: A quick how-to

Prepping Data for Analysis using R

Posted on Categories Statistics, TutorialsTags , , Leave a comment on Prepping Data for Analysis using R

Nina and I are proud to share our lecture: “Prepping Data for Analysis using R” from ODSC West 2015.


Nina Zumel and John Mount ODSC WEST 2015

It is about 90 minutes, and covers a lot of the theory behind the vtreat data preparation library.

We also have a Github repository including all the lecture materials here. Continue reading Prepping Data for Analysis using R

A gentle introduction to parallel computing in R

Posted on Categories Coding, data science, Exciting Techniques, math programming, Programming, TutorialsTags , 4 Comments on A gentle introduction to parallel computing in R

Let’s talk about the use and benefits of parallel computation in R.


NewImage

IBM’s Blue Gene/P massively parallel supercomputer (Wikipedia).

Parallel computing is a type of computation in which many calculations are carried out simultaneously.”

Wikipedia quoting: Gottlieb, Allan; Almasi, George S. (1989). Highly parallel computing

The reason we care is: by making the computer work harder (perform many calculations simultaneously) we wait less time for our experiments and can run more experiments. This is especially important when doing data science (as we often do using the R analysis platform) as we often need to repeat variations of large analyses to learn things, infer parameters, and estimate model stability.

Typically to get the computer to work a harder the analyst, programmer, or library designer must themselves work a bit hard to arrange calculations in a parallel friendly manner. In the best circumstances somebody has already done this for you:

  • Good parallel libraries, such as the multi-threaded BLAS/LAPACK libraries included in Revolution R Open (RRO, now Microsoft R Open) (see here).
  • Specialized parallel extensions that supply their own high performance implementations of important procedures such as rx methods from RevoScaleR or h2o methods from h2o.ai.
  • Parallelization abstraction frameworks such as Thrust/Rth (see here).
  • Using R application libraries that dealt with parallelism on their own (examples include gbm, boot and our own vtreat). (Some of these libraries do not attempt parallel operation until you specify a parallel execution environment.)

In addition to having a task ready to “parallelize” you need a facility willing to work on it in a parallel manner. Examples include:

  • Your own machine. Even a laptop computer usually now has four our more cores. Potentially running four times faster, or equivalently waiting only one fourth the time, is big.
  • Graphics processing units (GPUs). Many machines have a one or more powerful graphics cards already installed. For some numerical task these cards are 10 to 100 times faster than the basic Central Processing Unit (CPU) you normally use for computation (see here).
  • Clusters of computers (such as Amazon ec2, Hadoop backends and more).

Obviously parallel computation with R is a vast and specialized topic. It can seem impossible to quickly learn how to use all this magic to run your own calculation more quickly.

In this tutorial we will demonstrate how to speed up a calculation of your own choosing using basic R. Continue reading A gentle introduction to parallel computing in R

Using Excel versus using R

Posted on Categories Opinion, Programming, Statistics, TutorialsTags , , , Leave a comment on Using Excel versus using R

Here is a video I made showing how R should not be considered “scarier” than Excel to analysts. One of the takeaway points: it is easier to email R procedures than Excel procedures.



Win-Vector’s John Mount shows a simple analysis both in Excel and in R.

A save of the “email” linking to all code and data is here.

The theory is the recipient of the email already had R, RStudio and the required packages installed from previous use. The package install step is only needed once and is:

install.packages(c('rpart','rpart.plot'))

Then all the steps are (in a more cut/paste friendly format):

cars <- read.table('http://www.win-vector.com/dfiles/car.data.csv',header=TRUE,sep=',')
library(rpart)
library(rpart.plot)
model <- rpart(rating ~ buying + maint + doors + persons + lug_boot + safety, data=cars, control=rpart.control(maxdepth=6))
rpart.plot(model,extra=4)
levels(cars$rating)

Note, you would only have to install the packages once- not every time you run an analysis (which is why that command was left out).

Some programming language theory in R

Posted on Categories Coding, Computer Science, Expository Writing, Programming, TutorialsTags , , , 1 Comment on Some programming language theory in R

Let’s take a break from statistics and data science to think a bit about programming language theory, and how the theory relates to the programming language used in the R analysis platform (the language is technically called “S”, but we are going to just call the whole analysis system “R”).

Our reasoning is: if you want to work as a modern data scientist you have to program (this is not optional for reasons of documentation, sharing and scientific repeatability). If you do program you are going to have to eventually think a bit about programming theory (hopefully not too early in your studies, but it will happen). Let’s use R’s powerful programming language (and implementation) to dive into some deep issues in programming language theory:

  • References versus values
  • Function abstraction
  • Equational reasoning
  • Recursion
  • Substitution and evaluation
  • Fixed point theory

To do this we will translate some common ideas from a theory called “the lambda calculus” into R (where we can actually execute them). This translation largely involves changing the word “lambda” to “function” and introducing some parenthesis (which I think greatly improve readability, part of the mystery of the lambda calculus is how unreadable its preferred notation actually is).


Opus hyp
Recursive Opus (on a Hyperbolic disk)
Continue reading Some programming language theory in R

An R function return and assignment puzzle

Posted on Categories Programming, TutorialsTags , , 1 Comment on An R function return and assignment puzzle

Here is an R programming puzzle. What does the following code snippet actually do? And ever harder: what does it mean? (See here for some material on the difference between what code does and what code means.)

f <- function() { x <- 5 }
f()

In R version 3.2.3 (2015-12-10) -- "Wooden Christmas-Tree" the code appears to call the function f() and return nothing (nothing is printed). When teaching I often state that you should explicitly use a non-assignment expression as your return value. You should write code such as the following:

f <- function() { x <- 5; x }
f()
## [1] 5

(We are showing an R output as being prefixed with ##.)

But take a look at the this:

f <- function() { x <- 5 }
print(f())
## [1] 5

It prints! Read further for what is really going on.

NewImage Continue reading An R function return and assignment puzzle

Fluid use of data

Posted on Categories data science, Practical Data Science, Pragmatic Data Science, Pragmatic Machine Learning, Statistics, TutorialsTags , , Leave a comment on Fluid use of data

Nina Zumel and I recently wrote a few article and series on best practices in testing models and data:

What stands out in these presentations is: the simple practice of a static test/train split is merely a convenience to cut down on operational complexity and difficulty of teaching. It is in no way optimal. That is, using slightly more complicated procedures can build better models on a given set of data.


CalTrainTest
Suggested static cal/train/test experiment design from vtreat data treatment library.
Continue reading Fluid use of data

Upcoming Win-Vector Appearances

Posted on Categories Administrativia, data science, Statistics, TutorialsTags , 1 Comment on Upcoming Win-Vector Appearances

We have two public appearances coming up in the next few weeks:

Workshop at ODSC, San Francisco – November 14

Both of us will be giving a two-hour workshop called Preparing Data for Analysis using R: Basic through Advanced Techniques. We will cover key issues in this important but often neglected aspect of data science, what can go wrong, and how to fix it. This is part of the Open Data Science Conference (ODSC) at the Marriot Waterfront in Burlingame, California, November 14-15. If you are attending this conference, we look forward to seeing you there!

You can find an abstract for the workshop, along with links to software and code you can download ahead of time, here.

An Introduction to Differential Privacy as Applied to Machine Learning: Women in ML/DS – December 2

I (Nina) will give a talk to the Bay Area Women in Machine Learning & Data Science Meetup group, on applying differential privacy for reusable hold-out sets in machine learning. The talk will also cover the use of differential privacy in effects coding (what we’ve been calling “impact coding”) to reduce the bias that can arise from the use of nested models. Information about the talk, and the meetup group, can be found here.

We’re looking forward to these upcoming appearances, and we hope you can make one or both of them.