RBelgium Meetup

Hello RBelgium community,

We are pleased to invite you to our next RBelgium meetup on wednesday the 21st of October in Brussels (Paleizenstraat 153, close to gare du nord (Brussels north train station)).

For this Meeting we would like to offer the possibility to members of the RBelgium community to hold a talk and present their project/work/Analysis with R. This gives members the chance to see what is happening with R within the RBelgium community and also to bounce ideas and help one another.

So if any of you would like to describe her/his R work at the next Rbelgium meetup for a 15 to 30 minutes presentation, please give a shout and let us know...

AGENDA UPDATE:

-Stephanie Locke from Mango Solutions (London) will be presenting "Analytical Web Services" : "In your day job, you built some awesome bit of analysis in R but now people want this information available real time and against everything that comes into the business. Help! You need an R web service but not being a developer you have no clue how to go about it. This session takes you through how to convert your analysis into a web service and how to take into account important stuff like security, scalability and error handling."

-Wannes Rosiers from Infofarm will be presenting "SparkR": "In June 2015 SparkR was integrated in Spark-1.4.0. The power of distributed computing and Big Data available via R! At InfoFarm we like to stay on top of new technologies, hence we’ve tried it out immediately. Machine learning algorithms of Spark MLlib were not available yet and R algorithms don’t run in a distributed way: the full power was not yet unleashed. Hence we decided to implement our own machine learning algorithms: naive Bayes (classification), kmeans (clustering) and apriori (recommendations). We’ll give a short introduction and demo, talk about lessons learned and future SparkR plans."

• There will be a presentation of a function "mstatby" which is a quick and easy "all into one" descriptive statistics function aiming at providing, in one single output, all necessary descriptive stats about a dataset that the analyst needs to see first. The function will be made available online after the meeting (feedback welcome).