15Nov/18

Meetup Machine Learning Aix-Marseille S04E02

Meetup Machine Learning Aix-Marseille
Tonight I am participating in the Machine Learning Aix-Marseille Meetup, for the second session of this fourth edition. I am speaking after Leonardo Noleto, senior data scientist at Bleckwen FinTech who is developing a solution to fight financial fraud with machine learning. I will present the project on which Enora Belz, Romain Gaté, Vincent Malardé, Jimmy Merlet, Arthur Charpentier and I worked on last summer for the 2018 Football World Cup (see a previous post). The idea was to use machine learning techniques to predict the outcome of football matches (win, draw or defeat).

The slides are available here (in French): http://www.egallic.fr/Recherche/Worldcup_2018/2018_meetup_ML/egallic_meetup.html

15Oct/18

Python course

Python logo
As part of a Python programming course for graduate students  (Magistère Ingénieur Économiste) at Aix-Marseille School of Economics, I have prepared course notes. These are available in different formats (in French):

These different documents were produced using the R package {bookdown}, all the files needed for compilation are available on a GitHub repository.

The documents may be updated from time to time.

06Jul/18

R (French) conferences 2018

Fifa World Cup 2018

Since Wednesday, I have been attending the 7th R (French) conferences, in Rennes, at Agrocampus Ouest.

On this occasion, before lunch, I will present our paper (working paper) co-authored with Arthur Charpentier on the use of collaborative genealogy data in historical demography. The presentation is a lightning talk: 14 slides that scroll every 24 seconds.

The slides are online (in French), and recall that the R codes are available on GitHub.

28Feb/18

(Français) Communes proches avec R

Rennes

Dans mes travaux actuels, j’ai besoin d’identifier pour une commune en particulier, quelles sont les autres communes proches, pour un rayon donné de 20km. Pour obtenir une telle information, je me suis appuyé sur les données de communes d’Open Street Map. L’idée est simple :

  • récupérer les frontières des communes ;
  • les étendre ;
  • regarder quelles communes sont en intersection avec les frontières étendues.
17Nov/16

Where’s Waldo? Here he is!


Yesterday, I came across a nice article untitled “Here’s Waldo: Computing the optimal search strategy for finding Waldo“, written by Randal S. Olson. I used the data he shared to apply a correction to the kernel density estimation of Waldo’s location.

In this article, Randal explains that he has devoted some time to try to compute the optimal search strategy for finding Waldo. To that end, he has used some machine learning techniques.
From an image provided by Slate (Here’s Waldo, 2013, by Ben Blatt), Randal S. Olson retrieved the coordinates of 68 different locations of Waldo, and kindly shared the data afterwards.

[…]

16Feb/15

Qui va gagner la Nouvelle Star ? À vos votes Twitter !

Cumul des votes par candidat au cours de la soirée

La chaîne de télévision D8 diffuse pour la troisième année consécutive l’émission Nouvelle Star. Si ma mémoire est bonne, je n’avais pas suivi ce programme depuis la saison 2006-2007, mais j’avoue m’être pris au jeu cette année, d’autant plus que la production propose une nouveauté par rapport aux saisons précédentes : les votes par Twitter !

Jeudi dernier, le 12/02, lors du quatrième prime, je me suis diverti avec l’API de Twitter pour récupérer les tweets postés pendant l’émission.

Les résultats de ma petite analyse laissent penser que les votes par SMS et par téléphone pratiqués durant l’émission ne sont pas négligeable, et ne reflètent pas exactement ce qui se dit sur le réseau social Twitter.

Aussi, après un bref rappel du déroulement des primes, ce billet présentera quelques observations réalisées autour des tweets extraits pendant l’émission de jeudi. Une troisième partie s’adressant à ceux désirant récupérer eux-même les tweets et effectuer leur propre analyse, fournira quelques codes R.

03Nov/14

French dates in R – From Mac OS to Windows

Station Clock - By derivative work: FischX (talk) Station_Clock.jpg: User:JuergenG, User:AlMare (Station_Clock.jpg) [CC-BY-SA-2.5-2.0-1.0 (http://creativecommons.org/licenses/by-sa/2.5-2.0-1.0) or CC-BY-SA-2.5-2.0-1.0 (http://creativecommons.org/licenses/by-sa/2.5-2.0-1.0)], via Wikimedia Commons
The other day during my R lecture, something I did not expect happen… I should have known, or at least guess that it would not work… But I wanted to believe it would. When I gave examples on how to read both English and French formatted dates in R, what was working perfectly on Mac OS X did not on Windows Seven. The example was the following:

d_char_fr <- "Mer 04 Fév 2015"
d_char <- "Wed 04 Feb 2015"
as.Date(d_char_fr, format = c("%a %d %b %Y"))
as.Date(d_char, format = c("%a %d %b %Y"))
30Oct/14

Coordinates of “hot-spots”


Last week I uploaded a note about the paper @freakonometrics and I have submitted again after we added quite a few revisions. We have already made available most of the R code to reproduce our applications (on this GitHub repository). However, we did not share our method to obtain the coordinates of the “hot-spots” areas