Scribd Analytics

I really liked Scribd Analytics feature (and that we have racked up 3200 reads in 11 months for Poets and Hackers). I think Google Docs /Drive should really incorporate more Scribd like document sharing features including social (now that Slideshare is off the market for a relatively cheap $119m) and turn on analytics by default

I really liked the heatmap on the document feature in the second screenshot.

Anyways nice to see someone out there cares for Poets &….



Understanding OAuth 1.0 for #rstats

The lovely lovely diagram at   is worth a thousand words and errors.

Very useful if you are trying to coax rCurl to do the job for you.

Credits-Idan Gazit



Also a great slideshare in Japanese (no! Google Translate didnt work on pdf’s and slideshares and scribds (why!!) but still very lucid on using OAuth with R for Twitter.

Why use OAuth- you get 350 calls per hour for authenticated sessions than 150 calls .

I tried but failed using registerTwitterOAuth

There is a real need for a single page where you can go and see which social netowork /website is using what kind of oAuth, which url within that website has your API keys, and the accompanying R Code for the same. Google Plus,LinkedIn, Twitter, Facebook all can be scraped better by OAuth. Something like this-


Topic Models

Some stuff on Topic Models-

In machine learning and natural language processing, a topic model is a type of statistical model for discovering the abstract “topics” that occur in a collection of documents. An early topic model was probabilistic latent semantic indexing (PLSI), created by Thomas Hofmann in 1999.[1] Latent Dirichlet allocation (LDA), perhaps the most common topic model currently in use, is a generalization of PLSI developed by David Blei, Andrew Ng, and Michael Jordan in 2002, allowing documents to have a mixture of topics.[2] Other topic models are generally extensions on LDA, such as Pachinko allocation, which improves on LDA by modeling correlations between topics in addition to the word correlations which constitute topics. Although topic models were first described and implemented in the context of natural language processing, they have applications in other fields such as bioinformatics.

In statistics, latent Dirichlet allocation (LDA) is a generative model that allows sets of observations to be explained by unobserved groups that explain why some parts of the data are similar. For example, if observations are words collected into documents, it posits that each document is a mixture of a small number of topics and that each word’s creation is attributable to one of the document’s topics. LDA is an example of a topic model

David M Blei’s page on Topic Models-

The topic models mailing list is a good forum for discussing topic modeling.

In R,

Some resources I compiled on Slideshare based on the above- Continue reading “Topic Models”

Thursday is for fun reading

Thats the world’s most widely read marketing textbook in slideshare format slides. You think you are a marketing guru expert at selling or promoting software- well spend 10 minutes flipping for a fun reading

and a presentation trying to be the worlds best presentation by putting social causes, geeky languages, hot looks in the same slides – Hi It is BO (not Barack Obama)

and if you are like me and suck at presentations , but unlike me would like to get better at presentations

if you are still reading this you probably have too much time on a Friday, so here is one YouTube poetry video I created while in a graphics design course in Vol State- it’s a mashuo of 12 poems, some Prezi, some music by  that big proft making Google machine called You Tub

Search, Sports,Social Media,SlideShares, Scribd

An image of a house fly eye surface by using S...
Image via Wikipedia

Some presentations I really liked.

A tutorial on SEO and SEM-

Carole Ann Matignon deals with optimization and scheduling, rules in the…….NFL!



Carole, We are waiting for the sequel on  analytics on football and the beer game.

Social Media Screw-Ups

Social Media doesnt matter at all- Social Media matters a lot- Still undecided? Take a look

Slideshare is a great VISUAL interface on sharing content. I liked Google Docs embedding as well, but Matt Mullenberg and Matt Cutts seemed to have stopped talking. Mullenberg is going like Zuckenberg, not willing to align with Sergey Mikhaylovich Brin. or maybe they are afraid of Big Brother Brin. Google loves Java and Javascript (even when they are getting sued for it)- while Matt M  hates it- bad for RIA I guess.

Scribd also is a great way to share content- and probably is small enough for. to allow embedding

Thats the reason why I sometimes prefer Scribd for sharing my poetry to Slideshare and Google Docs. Also I like the enhanced analytics and the much easier and evolved interface for reading. Slideshare is much more successful than Scribd because it is open to sharing with everyone- scribd tries to get you to register …;)

(* Also see MIT’s beer game at which is ahem different from Duke’s beer games).



Going Deap : Algols in Python

Logo of PyPy
Image via Wikipedia

Here is an important new step in Python- the established statistical programming language (used to be really pushed by SPSS in pre-IBM days and the rPy package integrates R and Python).

Well the news  ( ) is the release of Distributed Evolutionary Algorithms in Python. If your understanding of modeling means running regression and iterating it- you may need to read some more.  If you have felt frustrated at lack of parallelization in statistical software as well as your own hardware constraints- well go DEAP (and for corporate types the licensing is ).


DEAP is intended to be an easy to use distributed evolutionary algorithm library in the Python language. Its two main components are modular and can be used separately. The first module is a Distributed Task Manager (DTM), which is intended to run on cluster of computers. The second part is the Evolutionary Algorithms in Python (EAP) framework.


DTM is a distributed task manager that is able to spread workload over a buch of computers using a TCP or a MPI connection.

DTM include the following features:




EAP includes the following features:

  • Genetic algorithm using any imaginable representation
    • List, Array, Set, Dictionary, Tree, …
  • Genetic programing using prefix trees
    • Loosely typed, Strongly typed
    • Automatically defined functions (new v0.6)
  • Evolution strategies (including CMA-ES)
  • Multi-objective optimisation (NSGA-II, SPEA-II)
  • Parallelization of the evaluations (and maybe more) (requires python2.6 and preferably python2.7) (new v0.6)
  • Genealogy of an evolution (that is compatible with NetworkX) (new v0.6)
  • Hall of Fame of the best individuals that lived in the population (new v0.5)
  • Milestones that take snapshot of a system regularly (new v0.5)



See the eap user’s guide for EAP 0.6 documentation.


The most basic features of EAP requires Python2.5 (we simply do not offer support for 2.4). In order to use multiprocessing you will need Python2.6 and to be able to combine the toolbox and the multiprocessing module Python2.7 is needed for its support to pickle partial functions.

Projects using EAP

If you want your project listed here, simply send us a link and a brief description and we’ll be glad to add it.

and from the blog (funny how people like but not anymore) at

EAP is part of the DEAP project, that also includes some facilities for the automatic distribution and parallelization of tasks over a cluster of computers. The D part of DEAP, called DTM, is under intense development and currently available as an alpha version. DTM currently provides two and a half ways to distribute workload on a cluster or LAN of workstations, based on MPI and TCP communication managers.

This public release (version 0.6) is more complete and simpler than ever. It includes Genetic Algorithms using any imaginable representation, Genetic Programming with strongly and loosely typed trees in addition to automatically defined functions, Evolution Strategies (including Covariance Matrix Adaptation), multiobjective optimization techniques (NSGA-II and SPEA2), easy parallelization of algorithms and much more like milestones, genealogy, etc.

We are impatient to hear your feedback and comments on that system at .


François-Michel De Rainville
Félix-Antoine Fortin
Marc-André Gardner
Christian Gagné
Marc Parizeau

Laboratoire de vision et systèmes numériques
Département de génie électrique et génie informatique
Université Laval
Quebec City (Quebec), Canada

and if you are new to Python -sigh here are some statistical things (read ad-van-cED analytics using Python) by a slideshare from Visual numerics (pre Rogue Wave acquisition)

Also see,