- Highlights from the useR! 2019 conference
HUN summary: A useR! 2019 konferencia (http://www.user2019.fr) idén Toulouse-ban került megrendezésre, amely 5 magyarországi résztvevője tart fényképes élménybeszámolót, amelyet követően sörözünk és kötetlenül beszélgetünk. Előadók: Alex Trickey, Bérczi András, Czeller Ildikó, Tarnói Csenge és Daróczi Gergely. A találkozót az R Ladies (https://www.meetup.com/R-Ladies-Budapest/) meetuppal együtt szervezzük, és sok szeretettel várunk minden érdeklődőt. Az előadások várhatóan vegyesen magyar vagy angol nyelven lesznek megtartva. Be prepared to recall some slides of the most inspiring talks of the useR! 2019 conference (http://www.user2019.fr) from Toulouse, see featured photos taken at the networking events, hear some backstage stories of the R gurus shared with us in person after the conference hours but not on Twitter yet. Most talks will be in English. Speakers: Alex Trickey, András Bérczi, Ildikó Czeller, Csenge Tarnói and Gergely Daróczi. Detailed schedule and location TBD. Previous events on useR! conference retrospects: - 2014: https://www.meetup.com/Budapest-Users-of-R-Network/events/185043252 - 2015: https://www.meetup.com/Budapest-Users-of-R-Network/events/222568646 - 2016: https://www.meetup.com/Budapest-Users-of-R-Network/events/232088178 - 2017: https://www.meetup.com/Budapest-Users-of-R-Network/events/241089389 - 2018: https://www.meetup.com/Big-Data-Meetup-Budapest/events/252743344/ This is a joint event with the local chapter of R Ladies: https://www.meetup.com/rladies-budapest/events/264021758/
- Data Summer Night meetup
Join us for a Data Summer evening and chat with fellow data people! No presentations this time, just free discussions, food and drinks (pay for your own) -- co-organized with the Big Data and Analytics meetup: http://bit.ly/2JTCUbm This event is English & Hungarian speaking.
- Better than Deep Learning: Gradient Boosting Machines (GBM) – with 2019 updates
This event is co-organized with the Data Science Meetup: https://www.meetup.com/budapest_data_science/events/261610625/ With all the hype about deep learning and “AI”, it is not well publicized that for structured/tabular data widely encountered in business applications it is actually another machine learning algorithm, the gradient boosting machine (GBM) that most often achieves the highest accuracy in supervised learning/prediction tasks. In this talk we’ll review some of the main GBM implementations such as xgboost, h2o, lightgbm, catboost, Spark MLlib (all of them available from R) and we’ll discuss some of their main features and characteristics (such as training speed, memory footprint, scalability to multiple CPU cores and in a distributed setting, prediction speed etc). If you have seen an earlier version of my talk with the same title (for example at eRum or Crunch, or the video recording from several other conferences/meetups in the USA), this talk will have plenty of updates from as recent as a few weeks ago that will make it worth hearing it (for example more details on the GPU implementations, new results on catboost, or exciting updates on Spark MLlib). Speaker: Szilard Pafka, Phd, Chief Scientist at Epoch (USA) Szilard studied Physics in the 90s and obtained a PhD by using statistical methods to analyze the risk of financial portfolios. He worked in finance, then more than a decade ago moved to become the Chief Scientist of a tech company in Santa Monica, California doing everything data (analysis, modeling, data visualization, machine learning, data infrastructure etc). He is the founder/organizer of several meetups in the Los Angeles area (R, data science etc) and the data science community website datascience.la. He is the author of a well-known machine learning benchmark on github (1000+ stars), a frequent speaker at conferences (keynote/invited at KDD, R-finance, Crunch, eRum and contributed at useR!, PAW, EARL, H2O World, Data Science Pop-up, Dataworks Summit etc.), and he has developed and taught graduate data science and machine learning courses as a visiting professor at two universities (UCLA in California and CEU in Europe). LinkedIn: https://www.linkedin.com/in/szilard Twitter: @DataScienceLA https://twitter.com/datasciencela Github: https://github.com/szilard/
- machineRy leaRning
It's been a while since we were discussing stats / ML models, but here we are again! Emarsys is kindly hosting this event -- see you at the end of May with the below two talks: > Zsuzsanna Szabó: Preparing concrete with the help of R Concrete is the second most human used substance after water. Therefore, being able to predict the properties of differently prepared and exposed concretes is important in economic, environmental and human safety point of view. In an ongoing academic research project our aim is to improve methods to support designing environmental-friendly and long-term safe building materials. In this talk, one of the applied pathways is presented. I use data analysis and machine learning to get to know what preparation parameters determine concrete strength, porosity and permeability. > Andras Berczi: Understanding black-box model predictions with LIME As algorithms become more complex it gets harder to understand what features influenced the predictions most. LIME is a technique/framework which helps you to understand the outcome of any kind of model for single predictions – not just for tabular data, but also image classification or text models. In this talk I will explain how you can do this with the help of the R package based on this framework and why I think that black-box models should be easily interpretable and explainable.
- Villámelőadások R csomagokról, trükkökről és egyebekről
Hosszú idő után újra magyar nyelven és újra a BME-én jelentkezünk villámelőadásokkal készülve -- lesz szó hasznos R csomagokról és trükkökről, vagy bármi más R-hez kapcsolódó témákról. A már megerősített eladások listája (folyamatosan bővül): - Markó Tamás: Ábrakötet készítés egyszerűen, avagy ggplot vizualizációk használata R tudás nélkül is - Sali Andras: Managing user expectations in Shiny: simple loader animations - Tóth Dénes: Shiny-alkalmazások csomagolása - Koncz Tamás: Optikai karakterfelismerés (OCR) R-ben, a Tesseract segítségével - Böjte Berta: R Ladies, 2 év 10 percben További részletek hamarosan, addig is előadásötleteiteket a [masked] címre küldjétek el március 3-ig. Köszönettel, Gergő
- Data Christmas 2018
Join us for the last meetup of the year, where we look back at the most significant and interesting events of 2018 and have a drink together with your fellow data people. There will be a talk jam where short, 5-10 min presentations will be given on many different but data-related topic. Current list of talks: - Welcome to the Data Christmas! - Gergely Daróczi & Bence Arató - Data wisdom we teach to students. Now in Vienna - Gábor Békés, CEU - State of the (R) 2018 - Gergely Daróczi, Budapest Users of R Network - What happened to Big Data: a year in review - Bence Arató, Big Data Meetup - Crowdsourced general intelligence - Andras Lorincz, ELTE - Why are you, Julia? - Csaba Hoch, Cursor Insight - Gendered behavior as a disadvantage in OSS development - Orsolya Vasarhelyi, CEU Schedule: 18:00 Doors open, refreshments 18:30 Talk Jam! 20:00 Afterparty in the atrium of CEU This is shared community event, jointly organized by the data meetups in Budapest. - Budapest BI Meetup http://bit.ly/2EbYtDL - Budapest Big Data Meetup http://bit.ly/2DZz9zM - Budapest Data Science meetup http://bit.ly/2DXIU1w - Budapest Machine Learning Meetup https://bit.ly/2rke8rZ - Budapest Julia User Group http://bit.ly/2EjIkfd - Budapest Spark Meetup: http://bit.ly/2DZE9o2 - Budapest Users of R Network http://bit.ly/2DZX1Dk - HUG-MSSQL http://bit.ly/2SIliCe - PyData Budapest Meetup https://bit.ly/2Qxt3NU - R-Ladies Budapest https://bit.ly/2QhWaW7 Due to the parallelly organized, distributed nature of the meetup, RSVPs will be closed when the combined number of RSVPs from all participating meetups hits the limit. This is an English speaking event. Venue and catering will be provided by CEU.
- RRR: Renitent Rcoholics Reunion
This is an experimental therapy co-organized with R Ladies to help R users speak about their passion -- how they got to know R, how they started to use R, and what are they doing with R, and maybe what they love or hate (duh) about R. We will go around, anyone who is willing to contribute their stories is welcome! Please volunteer to share your story by signing up at https://goo.gl/forms/nHPyYU3fEfhbA5DT2. Talks limited to 5 mins each, can be either in English or Hungarian. No expectations or judgment. --- Rendhagyó kiadással jelentkezik az R Ladies és a BURN decemberi kiadása: R-függő tagjaink arról mesélnek majd, hogy hogyan ismerkedtek meg az R nyelvvel, mióta és miért használják, mit szeretnek és gyűlülnek benne. Az előadások max 5 percesek, és az AA mintájára a hallgatóság elvárásoktól és ítéletektől mentesen érkezik / távozik majd. A magyar vagy angol nyelvű előadásra / vallomásra jelentkezők legyenek kedvesek feliratkozni a https://goo.gl/forms/nHPyYU3fEfhbA5DT2 címen. --- This meetup is hosted at and sponsored by CEU. Food and (soft) drinks will be served after the talks to help networking. Related R Ladies event page: https://www.meetup.com/R-Ladies-Budapest/events/256244385/
- "Full-Stack Data Science with R" (Crunch Edition) with Ajay Gopal
Ajay Gopal is the Chief Data Scientist at Deserve (Menlo Park, CA), ex VP of Growth and Data Science at CARD.com (Los Angeles, CA) -- having built diverse teams for cloud data science infrastructures at fintech startups heavily relying on R. The talk will focus on how to use R in production at various parts of the data workflow. Schedule: - 18:30 door opens, pizza & beer time - 19:00 main talk and Q&A - 20:00 networking time + planning to grab a beer ot two at a nearby pub Thanks to the organizers of Crunch (https://www.crunchconf.com) for inviting Ajay to Budapest! This meetup is free and will be hosted at an off-site location, but we highly suggest you to check out the full program of the conference and register with the "crunchr" promo code ($50 off).
- 5 year anniversary with Hadley Wickham
The Hungarian R Meetup / Budapest Users of R Network (BURN) was founded 5 years ago, when a dozen of enthusiast R users came together in a small room to figure out if there's any interest in organizing monthly meetings, what is meetup.com and how on earth we should deal with the 5 kgs of cheese scone (pogácsa) that was ordered for this very first event. Time passed quickly, and now we have over 1300 members, and Hadley Wickham himself is visiting the Hungarian R User Group in September! Schedule: - 18:00 🍕door opens & pizza time (sponsored by Prezi) - 18:30 🎤 talks start promptly - 19:30 🎂 anniversary cakes (sponsored by CEU) - 20:00 🍻 door closes but planning to stay a bit longer in the nearby Apacuka
- Data Summer Meetup
Join us for a Data Summer evening and chat with fellow data people! No presentations this time, just merry discussions. This event is English & Hungarian speaking and co-organized with the Big Data folks (https://www.meetup.com/Big-Data-Meetup-Budapest/events/253615981/).