• R Benutzer Treffen Köln / R user meeting in Cologne

    For organisational reasons: please only RSVP "yes" if you actually plan to attend and don't forget to update your RSVP if needed! No-shows are not cool. Otherwise: same place, same time, same spirit :) Agenda: 19:00 Talk Radmila Velichkovich - essurvey package presentation and analysis essurvey is an R package created for easier access to ESS (European Social Survey) data. We will discuss how this package helps social scientists work with ESS data. We will choose one data set to do data wrangling using dplyr and ggplot2 to visualise the ESS data. More about Radmila: https://about.me/radmila.velichkovich Pizzas and drinks will be provided.

  • Get started with R - Data wrangling workshop with tidyverse

    We have announced it many times and we finally managed to get it organised: Our first hands-on workshop for beginneRs! David will cover many important aspects of data cleaning and wrangling and will introduce us to the fabulous world of... Hadley Wickham with his tidyverse. Find out why data people praise the "tidy data god", what tidy data looks like, how you get there and how you can do (nearly) everything with it. The workshop will be a mixture of presentation mode with slides and hands-on mode with exercises. You can also bring your own data and questions. Roll up your sleeves and join the fun :D CONTENT 1) tidyverse and Pipes 2) data_frames and readr (data I/O) 3) Tidy Data and tidyr 4) Dplyr and Joins AGENDA 17:45 Arrival 18:00 Kick-off 21:00 The End ABOUT DAVID LinkedIn: https://www.linkedin.com/in/david-zimmermann-76a737a4 Blog: https://datashenanigan.wordpress.com/ REQUIREMENT Bring your own laptop with R and RStudio installed.

    3
  • R Benutzer Treffen Köln / R user meeting in Cologne

    For organisational reasons: please only RSVP "yes" if you actually plan to attend and don't forget to update your RSVP if needed! No-shows are not cool. Otherwise: same place, same time, same spirit :) Agenda: 18:00 Welcome 18:15 Talks Markus Gesmann - Models are about what changes, and what doesn't How do you motivate and build a model from first principles? This talk will provide is a step by step guide. The purpose of most models is to understand change, and yet, considering what doesn’t change and should be kept constant can be equally important. Using differential equations to describe the data, I will show how various regression models can be motivated and demonstrate how limitations of generalised linear models can be overcome with a full Bayesian approach. Along the way I will emphasise the value of domain knowledge and share my experience of engaging with domain experts. Jo-Fai Chow - OsloBnB - Where to stay in Oslo? Two weeks ago, Joe visited Oslo for H2O meetup and other events. Not sure where to stay, he asked his friend Dmytro for help. Dmytro created a fun project combining both spatial and text analysis in R based on open data for Joe. In this talk, Joe will walk you through some of the interesting steps in Dmytro’s analysis. Joe will also give away special H2O gifts to all participants. Joe Chow (https://twitter.com/matlabulous) on behalf of Dmytro Perepolkin (https://twitter.com/dmi3k) From 19:30 Klönen & Kölsch Pizzas and drinks will be provided.

    1
  • R Benutzer Treffen Köln / R user meeting in Cologne

    Thanks to everyone who participated in the topics survey! It's been a while since our last meetup and it's definitely time to gather again. Same time same place, this time with two top speakers from overseas, that is, if you consider the English Channel a sea ;) Jo has been with us before, he will present LIME. Aimee will share a cool data analysis/visualization presentation with us. Her presentation is gonna be a remote presentation, fingers crossed the technology god is with us and everything works out smoothly! Agenda: 18:00 Welcome 18:15 Short and crisp presentation of the results of the topics survey: Which topics interest you most? 18:30 Talks: Jo-Fai Chow from H2O (https://www.h2o.ai/) - Making Multimillion-dollar Baseball Decisions with H2O AutoML and Shiny Joe recently teamed up with IBM and Aginity to create a proof of concept "Moneyball" app for the IBM Think conference in Vegas. The original goal was to prove that different tools (e.g. H2O, Aginity AMP, IBM Data Science Experience, R and Shiny) could work together seamlessly for common business use-cases. Little did Joe know, the app would be used by Ari Kaplan (the real "Moneyball" guy) to validate the future performance of some baseball players. Ari recommended one player to a Major League Baseball team. The player was signed the next day with a multimillion-dollar contract. This talk is about Joe's journey to a real "Moneyball" application. Aimee Gott from Mango Solutions (https://www.mango-solutions.com/) - Around the world in 80 lines of R Abstract tba From 19:30 Klönen & Kölsch Pizzas and drinks will be provided.

    5
  • R Benutzer Treffen Köln / R user meeting in Cologne

    Agenda: 18:00 Welcome 18:15 Talks Jessica Peterka-Bonetta: Social media and sentiment analysis with emojis This talk focuses on the pitfalls encountered when analyzing emojis in R, workarounds that help overcome the problems and provides examples of how emojis can be used in a social media analysis context. Hello encoding hell! These little, digital images that add so much nuances to our text messages and often enough determine their whole meaning have become so incredibly popular that they even made their way up to the Oxford English Dictionary in 2015. Whoever does social media analysis has to think about extracting meaning from them sooner or later. What’s Paris Hilton’s favorite emoji? Which emojis are often used in a specific context? Are emojis better suited for sentiment analysis than words? Before being able to tackle those questions in R, a major obstacle has to be overcome first: putting the data containing the emojis in a format that can actually be dealt with. Spoiler: it’s not as easy as it sounds. Timothy Wong: Text Mining for Preventative Maintenance Large-scale industrial processes are normally comprised of thousands and thousands of individual components which are vulnerable to breakdown. Maintenance of these components is the key to reduce unplanned outages. The repair log dataset contains unstructured, free-format text description detailing the issues. We applied text mining algorithms to this dataset and turned it into an analysable format. A combination of techniques were used including tf-idf scheme and n-grams approach. Groups of vulnerable components can be visualised as a graph network. From 20:00 Klönen & Kölsch Pizzas will be provided.

    4
  • R Benutzer Treffen Köln / R user meeting in Cologne

    Fans and friends of R, let's meet again to talk about our favorite language for statistical programming, anything related to data and the purpose of life. Agenda: 18:00 Welcome 18:15 Talks Hans W. Borchers: Optimization with R -- Tips and Trick There are almost 100 packages listed on the CRAN optimization task view. We will discuss some of the more important packages in areas such as nonlinear optimization with and w/o constraints, least-squares problems, non-smooth and global optimization, and mixed integer programming. Tips and tricks will be provided for high precision or high-dimensional problems, for equality constraints, for minimax problems, etc. Frederik Aust: papaja -- Prepare APA Journal Articles reproducibly with R Markdown Reproducible workflows and dynamic documents have attained great popularity in the R community. The packages knitr and rmarkdown provide a great infrastructure to develop and customize document templates for specific purposes. papaja is an R package in the making that provides document templates and helper functions that facilitate writing computationally reproducible scientific reports according to the style guidelines of the American Psychological Association. I will showcase some of the package's features and try to provide an overview on how to create custom R Markdown templates. From 20:00 Klönen & Kölsch Pizzas will be provided.

    3
  • R Benutzer Treffen Köln / R user meeting in Cologne

    Fans and friends of R, let's meet again to talk about our favorite language for statistical programming, anything related to data and the purpose of life. Agenda: 18:15 Welcome 18:30 Talks Markus Gesmann: Generalised Linear Models in R Generalised linear models (GLMs) are a flexible generalization of linear models, with applications in many disciplines. This talk will give an introduction to GLMs from a distribution-centric point of view. Using a small toy data set we will discuss how different assumptions about the data generating process lead to different assumptions about the distribution of the data (response variable) and therefore different GLMs. Stephan Porz: Is R fit to create reproducible results? We've probably all experienced it: We need to work with some code from over a year ago that at the time perfectly ran and yielded proper results. Now, a bunch of OS and R updates later, everything falls to pieces. Sometimes we get a proper error message and immediatly solve the issue. But sometimes changes manifest in a more subtle way. Maybe some of the results get spoiled. Maybe this goes unnoticed until it's too late. In this talk I'll share some of our experiences and explore various ways of how reproducibility can be achieved. From 20:00 Klönen & Kölsch Beers, snacks and pizzas will be provided.

    11
  • R Benutzer Treffen Köln / R user meeting in Cologne

    It's this time of the year again! Let's meet, listen to talks and exchange thoughts afterwards while having a bite together. Also, it's gonna be our 20. R user meeting, Whoop-Whoop! Agenda: 18:00 Welcome 18:15 Talks Jo-Fai Chow (http://www.jofaichow.co.uk/) (H2O (http://www.h2o.ai/)): H2O Deep Water - Making Deep Learning Accessible to Everyone Deep Water is H2O's integration with multiple open source deep learning libraries such as TensorFlow, MXNet and Caffe. On top of the performance gains from GPU backends, Deep Water naturally inherits all H2O properties in scalability. ease of use and deployment. In this talk, I will go through the motivation and benefits of Deep Water. After that, I will demonstrate how to build and deploy deep learning models with or without programming experience using H2O's R/Python/Flow (Web) interfaces. Dubravko Dolic (dsquare (http://www.dsquare.de/)): Analyze Traffic Hot Spots using R (and a little bit of Python) Getting data from the traffic maps provided by Google is a piece of cake with Python. I will present some examples time-based analysis performed on this data in R. From 20:00 Klönen & Kölsch Beer, pizza and snacks will be provided. The event is hosted at eyeo, the company behind Adblock Plus.

    9
  • R Benutzer Treffen Köln / R user meeting in Cologne

    Agenda • Introduction to the tidyverse tools - Jiddu Alexander • Performance profiling and improvement in R - Nils Glück • Stapelverarbeitung von R-Scripten mit Hilfe von Excel - Klaus Jacobi The event is hosted by Eyeo, the company behind Adblock Plus.

    21
  • R Benutzer Treffen Köln / R user meeting in Cologne

    Microsoft Deutschland GmbH

    Agenda Introduction to SparkR - Dubravko Dolić R at Microsoft - Stefan Cronjaeger English Version (Deutsch unten) The venue is close to the Schokoladenmusem next to the Rhein. Car parking spaces are available near by. Please visit the Microsoft page (https://www.microsoft.com/de-de/ueber-uns/standorte-directions.aspx) for further details. German version (English above) Das Gebäude ist in der Nähe des Schokoladenmuseums am Rhein. Parkplätze gibt es in der Nähe. Bitte besucht die Microsoft Seite (https://www.microsoft.com/de-de/ueber-uns/standorte-directions.aspx) für mehr Details.

    12