### John Mount

Shared publicly -http://blog.revolutionanalytics.com/2015/07/efficient-accumulation-in-r.html

Start a hangout

John Mount

Works at Win-Vector LLC

156,317 views

AboutPostsPhotosVideos+1's

New Win-Vector LLC technical article: "Efficient accumulation in R"

http://blog.revolutionanalytics.com/2015/07/efficient-accumulation-in-r.html

http://blog.revolutionanalytics.com/2015/07/efficient-accumulation-in-r.html

by John Mount Data Scientist, Win-Vector LLC R has a number of very good packages for manipulating and aggregating data (plyr, sqldf, RevoScaleR, data.table, and more), but when it comes to accumulating results the beginning R user is often at sea. The R execution model is a bit exotic so many R users are very uncertain which methods of accumulating results are efficient and which are inefficient. Accumulating wheat (Photo: Cyron Ray Macey, some ...

1

Update: data.table is totally the way to go.

Nina Zumel's next Win-Vector LLC technical article: Working with sessionized data 2: variable selection http://www.win-vector.com/blog/2015/07/working-with-sessionized-data-2-variable-selection/

In our previous post in this series, we introduced sessionization, or converting log data into a form that's suitable for analysis. We looked at basic considerations, like dealing with time, choosi...

1

Today's one minute hate: OSX "my god its full of meh" https://www.youtube.com/watch?v=okmJ7IESJe8

1

New Win-Vector LLC technical finance article

What is a good Sharpe ratio?

http://www.win-vector.com/blog/2015/06/what-is-a-good-sharpe-ratio/

What is a good Sharpe ratio?

http://www.win-vector.com/blog/2015/06/what-is-a-good-sharpe-ratio/

We have previously written that we like the investment performance summary called the Sharpe ratio (though it does have some limits). What the Sharpe ratio does is: give you a dimensionless score t...

1

Neural net image salad again (with code)

http://www.win-vector.com/blog/2015/06/neural-net-image-salad-again-with-code/ (with Michael Witbrock and Scott Neal Reilly, plus a call-out to Scott Draves).

http://www.win-vector.com/blog/2015/06/neural-net-image-salad-again-with-code/ (with Michael Witbrock and Scott Neal Reilly, plus a call-out to Scott Draves).

Alexander Mordvintsev, Christopher Olah, and Mike Tyka, recently posted a great research blog article where they tried to visualize what a image classification neural net “wants to see.” They achieve this by optimizing the input to correspond to a fixed pattern of neural net internal node ...

1

In his circles

125 people

Text encoding is a convoluted mess

http://www.win-vector.com/blog/2015/07/text-encoding-is-a-convoluted-mess/

http://www.win-vector.com/blog/2015/07/text-encoding-is-a-convoluted-mess/

Modern text encoding is a convoluted mess where costs can easily exceed benefits. I admit we are in a world that has moved beyond ASCII (which at best served only English, and even then without ful...

1

5 comments

John Mount

+

1

2

1

2

1

Gotcha.

Anyone remember the correct text and source of this almost remembered maxim? "Laws/axioms/rule that are true are true in the extreme.” It is the mathematical idea that if a rule is correct than it is correct in all cases (even the cases that seem ridiculously hard).

1

New Win-Vector LLC technical article by Nina Zumel: "Working with Sessionized Data 1: Evaluating Hazard Models" http://www.win-vector.com/blog/2015/07/working-with-sessionized-data-1-evaluating-hazard-models/

When we teach data science we emphasize the data scientist's responsibility to transform available data from multiple systems of record into a wide or denormalized form. In such a “ready to analyze...

1

A/B test design via dynamic programming and R

http://blog.revolutionanalytics.com/2015/07/ab-testing-advertisements-with-r.html

http://blog.revolutionanalytics.com/2015/07/ab-testing-advertisements-with-r.html

by John Mount Ph. D. Data Scientist at Win-Vector LLC Win-Vector's last article on A/B testing described the scope of the realistic circumstances of A/B testing in practice and gave links to different standard solutions. In this article we will be take an idealized specific situation allowing us to show a particularly beautiful solution to one very special type of A/B test. For this article we are assigning two different advertising message to ou...

1

A bit about Win-Vector LLC

http://www.win-vector.com/blog/2015/06/a-bit-about-win-vector-llc/ #R #Rlang #datascience #consulting #training #analytics

(please share/re-Tweet)

http://www.win-vector.com/blog/2015/06/a-bit-about-win-vector-llc/ #R #Rlang #datascience #consulting #training #analytics

(please share/re-Tweet)

Win-Vector LLC is a consultancy founded in 2007 that specializes in research, algorithms, data-science, and training. (The name is an attempt at a mathematical pun.) Win-Vector LLC can complete your high value project quickly (some examples), and train your data science team to work much more ...

1

Why does designing a simple a/b test seem so complicated?

http://blog.revolutionanalytics.com/2015/06/why-does-planning-something-as-simple-as-an-ab-test-always-end-up-feeling-so-complicated.html

http://blog.revolutionanalytics.com/2015/06/why-does-planning-something-as-simple-as-an-ab-test-always-end-up-feeling-so-complicated.html

John Mount Ph. D. Data Scientist at Win-Vector LLC An A/B test is a very simple controlled experiment where one group is subject to a new treatment (often group "B") and the other group (often group "A") is considered a control group. The classic example is attempting to compare defect rates of two production processes (the current process, and perhaps a new machine). Illustration: Boris Artzybasheff (photo James Vaughan, some rights reserved) In...

1

People

In his circles

125 people

Work

Occupation

Principal Consultant, Win-Vector LLC

Employment

- Win-Vector LLCPrincipal Consultant, present

Links

Contributor to

- Win Vector blog (current)

Story

Introduction

I produce applied research, prototyping and training in information extraction, algorithms and data-mining for web-scale businesses, hedge funds and start ups. Right now I do this as a consultant at Win-Vector LLC.

Please check out our book Practical Data Science with R http://www.manning.com/zumel/ http://www.amazon.com/Practical-Data-Science-With-R/dp/1617291560

Also check out the Win-Vector LLC blog http://www.win-vector.com/blog/ our Twitter feed https://twitter.com/WinVectorLLC .

Basic Information

Gender

Male

John Mount's +1's are the things they like, agree with, or want to recommend.

A dynamic programming solution to A/B test design | StatsBlogs.com | All... www.statsblogs.com (This article was originally published at Win-Vector Blog » Statistics, and syndicated at StatsBlogs.) Our last article on A/B testing descr |

Estimating Generalization Error with the PRESS statistic www.r-bloggers.com As we’ve mentioned on previous occasions, one of the defining characteristics of data science is the emphasis on the availability of “large” |

Factors are not first-class citizens in R www.r-bloggers.com The primary user-facing data types in the R statistical computing environment behave as vectors. That is: one dimensional arrays of scalar v |

Frequentist inference only seems easy www.r-bloggers.com Two of the most common methods of statistical inference are frequentism and Bayesianism (see Bayesian and Frequentist Approaches: Ask the Ri |

Book Review: Practical Data Science with R - Fliptop Predictive Analytics blog.fliptop.com Book Review: Practical Data Science with R |

R style tip: prefer functions that return data frames www.r-bloggers.com While following up on Nina Zumel’s excellent Trimming the Fat from glm() Models in R I got to thinking about code style in R. And I realized |

Trimming the Fat from glm() Models in R www.r-bloggers.com One of the attractive aspects of logistic regression models (and linear models in general) is their compactness: the size of the model grows |

Save 45% on Practical Data Science with R (expires May 21, 2013) www.r-bloggers.com Please share this generous deal from Manning publications: save 45% on Practical Data Science with R through May 21, 2014. Please tweet, for |

R has some sharp corners www.r-bloggers.com R is definitely our first choice go-to analysis system. In our opinion you really shouldn’t use something else until you have an articulated |

Some R Resources for GLMs www.r-bloggers.com by Joseph Rickert Generalized Linear Models have become part of the fabric of modern statistics, and logistic regression, at least, is a “go |

You don’t need to understand pointers to program using R www.r-bloggers.com R is a statistical analysis package based on writing short scripts or programs (versus being based on GUIs like spreadsheets or directed wor |

Oldies but Goldies: Statistical Graphics Books www.r-bloggers.com I just wanted to plug for three classical books on statistical graphics that I really enjoyed reading. The books are old (that is, older tha |

I can haz buzzwords? biasedestimates.blogspot.com Catty title aside, this post takes a good swing at defining terms we hear thrown around about data these days and they mostly do a good job. |

Practical Data Science with R October 2013 update www.r-bloggers.com A quick status update on our upcoming book “Practical Data Science with R” by Nina Zumel and John Mount. We are really happy with how the bo |

[Book] Practical Data Science with R www.analyticbridge.com Nina Zumel and John Mount have been working very hard on producing an exciting new book called “Practical Data Science with R.” The book has |

Prefer = for assignment in R www.r-bloggers.com We share our opinion that = should be preferred to the more standard <- for assignment in R. This is from a draft of the appendix of our upc |

Win-Vector Blog » How to outrun a crashing alien spaceship www.win-vector.com Hollywood movies are obsessed with outrunning explosions and outrunning crashing alien spaceships. For explosions the movies give the optima |

Allen Bushnell, Fish Rap: Salmon on the prowl near the shore in Monterey... www.santacruzsentinel.com Allen Bushnell Fish Rap The weather forecasts a 4- to 6-foot northwest swell this weekend, but that shouldnt slow fishing down. |