Szilard Pafka on DataScience.LA

Goodbye DataScience.LA, goodbye California!

Thu, 01 Jul 2021 10:04:03 -0700

I (Szilard) started organizing meetups more than a decade ago (the LA R Users Group est. 2009 was the very first data meetup in the Los Angeles area). A few years later, a couple of us (Amelia, Leigh, Eduardo and I, and also several contributors) started a few more meetup groups (e.g. Data Science) and this very website DataScience.LA. However, in recent years my DataScience.LA Leadership Teammates relocated and now it’s my turn, I’m the last one to leave California (I’m very excited to move to Texas!). While we are ceasing all activities in LA now and this is the last update/post on this website, we will keep the existing/old content accessible for a while. It was a great pleasure running these events/this site and getting to know so many of you. LA has so many great data science folks! However, now it’s time to say goodbye, goodbye LA and California, and good luck to you all.

Overview of H2O's GBM implementation

Mon, 10 May 2021 09:13:53 -0700

Update: Video Recording:

▶ LA Data Science Meetup, June 8, 2021 - Michal Kurka: H2O's GBM

Slides: here

CatBoost: Distributed Training, Uncertainty Estimation and Other News

Wed, 10 Mar 2021 08:36:43 -0800

Update: Video Recording:

▶ LA Data Science Meetup, March 30, 2021 - Stanislav Kirillov: CatBoost

Slides: here

Recent Developments in LightGBM

Tue, 15 Dec 2020 01:53:23 -0800

Update: Video recording:

▶ LA Data Science Meetup, Jan 12, 2021 - James Lamb: Recent Developments in LightGBM

Slides and code: here.

2 talks: GBM Benchmark In-Depth | The State of XGBoost

Thu, 15 Oct 2020 23:31:01 -0700

Update: Video recordings:

Talk #1 (Szilard Pafka: GBM Benchmarks)

▶ LA Data Science Meetup, Nov. 10, 2020 - Talk #1 - Szilard Pafka: GBM Benchmarks

Slides here

Meetup: Machine Learning Best Algorithms: Gradient Boosting Machines (GBM)

Fri, 20 Jul 2018 17:43:00 -0700

Update_1: Slides for the 4 talks added below (at each talk section separately).

Update_2: Photos from the meetup and a short description of the event added below (at the bottom of the post).

Update_3: Video recording of the meetup here:

R Meetup with Hadley Wickham

Sat, 28 Oct 2017 12:57:13 -0700

Update: Video of the 2nd half of the talk is here (1st half was not recorded, sorry):

This video is no longer available on YouTube (original link).

In our next meetup, we’ll have Hadley (I think no introduction needed).

Packages made easy
by Hadley Wickham

Meetup: Machine Learning in Production with Szilard Pafka

Fri, 28 Apr 2017 00:55:25 -0700

Update: Video recording of the meetup here:

▶ Machine Learning in Production with Szilard Pafka

Slides here:

Meetup: Stream processing with R in AWS

Wed, 08 Mar 2017 09:29:48 -0800

Update: Slides click here.

Video recording here:

This video is no longer available on YouTube (original link).

Stream processing with R in AWS
by Gergely Daróczi

Abstract: R is rarely mentioned among the big data tools, although it’s fairly well scalable for most data science problems and ETL tasks. This talk presents an open-source R package to interact with Amazon Kinesis via the MultiLangDaemon bundled with the Amazon KCL to start multiple R sessions on a machine or cluster of nodes to process data from theoretically any number of Kinesis shards. Besides the technical background and a quick introduction on how Kinesis works, this talk will feature some stream processing use-cases at CARD.com, and will also provide an overview and hands-on demos on the related data infrastructure built on the top of Docker, Amazon ECS, ECR, KMS, Redshift and a bunch of third-party APIs.

Meetup: No-Bullshit Data Science

Fri, 17 Feb 2017 11:49:40 -0800

Update: Slides here:

Slides: https://speakerdeck.com/szilard/machine-learning-meetup-febr-2017

Our next meetup:

No-Bullshit Data Science
by Szilard Pafka

Abstract: While extracting business value from data has been performed by practitioners for decades, the last several years have seen an unprecedented amount of hype in this field. This hype has created not only unrealistic expectations in results, but also glamour in the usage of the newest tools assumably capable of extraordinary feats. In this talk I will apply the much needed methods of critical thinking and quantitative measurements (that data scientists are supposed to use daily in solving problems for their companies) to assess the capabilities of the most widely used software tools for data science. I will discuss in details two such analyses, one concerning the size of datasets used for analytics and the other one regarding the performance of machine learning software used for supervised learning.

Meetup: Machine Learning at Google

Thu, 24 Nov 2016 22:27:11 -0800

UPDATE: The meetup “sold out” in record time (35 minutes!) from announcing it on our mailing list. There are more than 250 people on the waiting list now.

Machine Learning at Google
#

Come and hear about a range of the work that is being done in Google’s Los Angeles office in the area of machine learning:

XGBoost workshop and meetup talk with Tianqi Chen

Mon, 06 Jun 2016 09:00:50 -0700

XGBoost is a fantastic open source implementation of Gradient Boosting Machines, a general purpose supervised learning method that achieves the highest accuracy on a wide range of datasets in practical applications. Deep learning is all the hype now, but apart from specific domains such as images, speech or text (i.e. problems with higher-level abstractions to be learnt and/or perception problems, where deep learning achieved some remarkable results indeed), it is usually outperformed by Gradient Boosting in a majority of general business domains and supervised learning applications. Proof of this and also because XGBoost has an easy-to-use interface from both R and Python, XGBoost has become a favorite tool in Kaggle competitions. Besides feature engineering, cross-validation and ensembling, XGBoost is a key ingredient for achieving the highest accuracy in many data science competitions and more importantly in practical applications.

XGBoost: meetup announcement

Thu, 19 May 2016 10:06:17 -0700

XGBoost is a fantastic open source implementation of Gradient Boosting Machines, one of the most accurate general purpose supervised learning algorithms. With interfaces from both R and Python among others, it has become a favorite tool in Kaggle competitions, and it’s also widely used in real-world applications. In this meetup we’ll have a talk from the best person on the topic,Tianqi Chen, main author of XGBoost.

Deep Learning @Whisper

Tue, 03 May 2016 11:37:29 -0700

Deep Learning @Whisper
talk by Nick Stucky-Mack

Video now available, thank you to community member Carl Mullins for providing video services:

▶ Deep Learning @Whisper THU, MAY 12 AT 6 00 PM, VENICE, CA

In this talk we will discuss how Whisper uses machine learning for natural language processing tasks. We will focus on how Whisper applies deep learning to moderate content created by its more than 20 million monthly active users. The talk will explore the problem of short text classification, and will cover Whisper’s choices in machine learning models, software development, and hardware.

What has Kaggle learned from 2 million machine learning models?

Fri, 05 Feb 2016 16:36:40 -0800

What has Kaggle learned from 2 million machine learning models?

Anthony Goldbloom, founder and CEO of Kaggle

UPDATE:Video recording of the talk available here

Kaggle is a community of almost 450K data scientists who have built almost 2MM machine learning models to participate in our competitions. Data scientists come to Kaggle to learn, collaborate and develop the state of the art in machine learning. This talk will cover some of the lessons on winning techniques we have learned from the Kaggle community.

Big RAM is eating big data - Size of datasets used for analytics

Wed, 18 Nov 2015 09:41:22 -0800

With so much hype about “big data” and the industry pushing for “big data” analytical tools for everyone, the question arises how many people have big data (for analytics) and how many of them really need these tools (which are more complex and often more immature compared to the traditional tools for analytics).

Winning Data Science Competitions

Mon, 19 Oct 2015 22:19:42 -0700

Our next Data Science meetup:

Winning Data Science Competitions

by Jeong-Yoon Lee

In this talk, I am going to share my experiences in data science competitions. After an overview of the competition structure and best practices, I will present the 1st prize winner’s solution for KDD Cup 2015 with the behind-the-scenes story.

Benchmarking Random Forest Implementations

Tue, 19 May 2015 08:30:44 -0700

I currently have the need for machine learning tools that can deal with observations of the order of 10 millions in the context of binary classification. That kind of data is a few GBs in size and it fits comfortably nowadays in the RAM of a decent single machine. It is a trivial task for linear models, as there are plenty of open source tools that can train a logistic regression with this amount of data on a single machine in a few seconds, even while using only 1 processor core (many of these tools are single-threaded). Linear models are also the gold standard of large-scale machine learning that can run on clusters, processing very large distributed datasets.

Data Science/Statistics/R @Google

Fri, 27 Feb 2015 11:50:48 -0800

This meetup will be hosted by Google and we’ll have Peter Lipman and Pete Meyer talk about the data science/statistics projects they have been working on at Google.

Human Evaluation Comparisons: Common Framework with Applications

We designed a study to determine whether being on device influenced a quality evaluator’s perception of ads quality. Here, we present a common framework, developed into an internal R package, that was used to analyze the study.

DW/BI/Analytics Meetup Summary: Inaugural Event

Sun, 15 Feb 2015 13:45:12 -0800

The LA Data Warehouse, Business Analytics and Analytics meetup had a fantastic first event with a great audience (full house), an awesome host (thanks Edmunds: Punnoose for taking the lead and the Team onsite and helping) and a great mix of 3 talks overviewing the field.

Secure your Shiny apps (against SQL injection)

Mon, 12 Jan 2015 09:25:12 -0800

Shiny takes inputs from UI elements and sends them to the server, where the application can access them as R variables. While Shiny has security measures in place, as in any typical web application, it remains the developer’s responsibility to sanitize the inputs before using them. For example, Shiny has no way to protect you if you are using an input in a SQL query such as select ... from ... where field = 'input'. Someone manipulating the websocket communication can craft a specially-formatted input that can force the database to execute a query that it is not supposed to do, termed an SQL injection. This might give an attacker access to private data or the ability to do other nefarious things, and it is a common security issue.

Data Science LA Meetup Summary: Data Science @ IRIS.TV

Thu, 08 Jan 2015 20:00:26 -0800

(Posting the slides and video recording from this event is long overdue - our apologies for the delay.)

At the September LA Data Science/Machine Learning meetup we had IRIS.TV’s Chief Data Scientist Tom Sullivan and VP of Engineering Joel Spitalnik presenting.

IRIS.TV is a video recommendation engine, and in their excellent talk Tom & Joel shared with us their approach to personalization and how they use machine learning to achieve their goals. They also shared the architecture of their systems, including how data is flowing between the various parts (i.e. the ETL pipeline). One thing that popped up as a question and I found interesting is that the usage of R and Python in their company is split 50-50. In fact, while Tom is using mainly R, Joel is using mainly Python. While this is perhaps unusual at a relatively small startup, our survey on software tools used for data science revealed that most data scientists in LA (at least those attending the meetups) are using R or Python, with a roughly equal split/small advantage for R. It just happens that for obvious reasons (such as network effects) that one tool dominates in most companies.

dplyr - some more reflections

Thu, 04 Dec 2014 09:30:00 -0800

Yesterday, I published a post here on DataScience.LA with a simple/basic benchmark for dplyr. It was the main part of a short talk at our last Los Angeles R meetup. Below, I continue my thoughts with some reflections on dplyr’s API and philosophy, AKA the other part of my talk.

dplyr and a very basic benchmark

Wed, 03 Dec 2014 09:35:05 -0800

Earlier this month I gave a short talk about dplyr at the Los Angeles R meetup. It was one of the 5 talks about the useR! 2014 conference, and you can see the summaries and slides from the other 4 talks here.

Data Science Meetup - January 13: Data Science @ Datapop

Tue, 25 Nov 2014 09:45:53 -0800

Data Science @ Datapop: The Marketing Knowledge Graph

presented by Dr. Ben Zamanzadeh, CTO at DataPop

Today’s eCommerce has evolved into a complex multi-dimensional optimization problem. DataPop’s semantic technology and Marketing Knowledge Graph is used to generate Omni-Channel advertising campaigns. This presentation will review our technology stack, machine learning models, discuss what worked what did not work for us and do a live demo of Marketing Knowledge Graph.

LA R meetup - January 21: RStudio's Shiny with Joe Cheng

Thu, 20 Nov 2014 10:04:38 -0800

At this meetup we’re fortunate to have RStudio’s lead developer Joe Cheng flying in from Seattle to talk about Shiny. Shiny makes it possible to develop interactive web applications by writing only a handful of R code. It lowers the barriers to constructing interactive dashboards that you can use to better explain your results to your boss and/or co-workers, or it can help you productionalize your analysis so that others in your company can make use of it regularly without the need to continually bother you.

LA R Meetup Summary: Highlights from useR! 2014 - Part 2

Tue, 18 Nov 2014 09:20:24 -0800

Last week the LA R meetup featured another round of 5 speakers each highlighting a few things they had found interesting at the useR! 2014 conference. This was the second such event after the first one in September - probably because useR! was awesome enough that it inspired 10 volunteers to stand up on stage and talk more about it.

Python Data Science Meetup Summary: Data Science with Python

Mon, 10 Nov 2014 10:02:46 -0800

Last week, the Python Data Science LA meetup debuted with a fabulous event. It was already much anticipated, with more than 250 people showing interest (RSVP+waiting list), and a lucky 100 converged upon the hip Venice Arts venue to hear our speakers. Our sponsor OpenMail has also done a fantastic job in getting us this venue, bringing food+drinks and taking care of all the details. Thanks OpenMail Team!

LA R Meetup - November 11: Highlights from the useR! 2014 conference - Part 2

Wed, 29 Oct 2014 09:16:21 -0700

At this meetup, five more LA R meetup members will present short talks of what they have learned at useR! 2014. This is the 2nd round of talks about useR! since we had twice as many volunteers to speak as we could accommodate in one meetup (indeed, useR! was that awesome). The first round of talks at our September meetup is summarized here (with slides).

Going (a bit more) public

Mon, 27 Oct 2014 09:48:53 -0700

I ♥ data. But I also ♥ privacy. Even though I have been running a few data meetups for the past few years, I have managed to keep myself out of public eye - even in my professional life. I must admit, I’m giving a bit away in an recent interview with Data Science Weekly. They had excellent questions to pose, and I’d like to take a moment here to summarize two main points from the interview: my thoughts on when and how much time it took me to became a data scientist and how I feel about the hype in the field today. If you’d like, you can read the full interview here.

Python Data Science Meetup: Data Science with Python

Wed, 08 Oct 2014 09:37:41 -0700

I’m pleased to announce the first event of our new Python Data Science LA meetup, started by two of us here at DataScience.LA (our very own Szilard and Eduardo).

We’ll have 5 speakers at this event, covering various aspects of the Python Data Science ecosystem (NumPy, SciPy, pandas, matplotlib, scikit-learn, NetworkX, NLTK, IPython notebook, etc.)

Data Science Toolbox Survey Results... Surprise! R and Python win

Wed, 24 Sep 2014 10:25:13 -0700

This is a re-publication of a blog post from a blog I created not long before we got the idea to start DataScience.LA, and in many aspects it is the genesis of DSLA (the blog’s name, the people getting together - thanks Eduardo, Amelia and Leigh). It was also the spark that lead to the creation of the Python Data Science LA meetup.

LA R Meetup Summary: Highlights from the useR! 2014 Conference

Wed, 10 Sep 2014 09:45:20 -0700

Last week the LA R meetup featured 5 speakers each highlighting a few things they had found interesting at the useR! 2014 conference (which I had the pleasure of helping to organize this year in Los Angeles). This meetup proved to be interesting even to those of us who attended the conference (which was about half of our audience), simply because there were so many cool things to hear and enough parallel sessions at the conference that no one could possibly capture all of the action.

Announcing Partnership with LA Big Data Community

Wed, 03 Sep 2014 09:54:50 -0700

Today I am happy to announce that we are expanding our partnership on several fronts with my friend Subash D’Souza, a leader of the Big Data community in LA.

During the past few years I have been organizing several data science meetups in Los Angeles (LA R, DataVis LA, Data Science/Machine Learning) and Subash has provided the same kind of leadership on the big data front (LA Hadoop, HBase, LA Big Data). While I think of big data as primarily technology and of data science as a blend of statistics and technology (and not only for large data sets), there is clearly a significant overlap between these two fields. Considering this overlap, we have already been collaborating for some time regarding these various meetups, e.g. organizing joint events or speaking at one another’s meetups.

Win Books and T-shirts in Our DataScience.LA Meetup Raffles, Powered by R and dplyr!

Tue, 02 Sep 2014 09:41:54 -0700

We have a few pieces of swag that we are raffling off to the community at our upcoming meetup events. Our stash consists of 25 data-oriented books, primarily from O’Reilly plus 25 T-shirts from useR! 2014 conference and Revolution Analytics (see picture above). Did we get your attention?

Announcing the New Python Data Science LA Meetup Group

Fri, 29 Aug 2014 09:01:19 -0700

I am excited to announce that we are starting a new meetup group - Python Data Science LA - to serve the needs of the LA data science community using Python!

At an earlier Data Science/Machine Learning meetup we conducted an informal survey on tools for Data Science which showed that a large majority of data scientists use R or Python, with R taking a slight lead. (I know, those attending the meetups bias the results towards open source tools.)

Data Science meetup - September 15: Data Science @ IRIS.TV

Tue, 19 Aug 2014 10:00:44 -0700

Data Science @ IRIS.TV

by Dr. Thomas Sullivan, Chief Data Scientist and Joel Spitalnik, VP Engineering

While video recommendations best serve the viewer experience when presented in real time, machine learning is a computationally intensive process that is often done on the back end. IRIS.TV’s utilizes a hybrid process to synchronize computational tasks for learning so that engineering and data science teams can shrink the latency between analyzing history and presentation of recommended videos to improve the experience.

LA R meetup - September 4: Highlights from the useR! 2014 Conference

Thu, 14 Aug 2014 13:46:12 -0700

Five LA R meetup members will present short talks of what they learned at useR! 2014
(plus we have 5 more volunteers for the following meetup!)

1. Timothy J. Triche, Jr., PhD
Fellow, Jane Anne Nohl Division of Hematology, USC/Norris Comprehensive Cancer Center

DataVis LA Meetup - August 26: Eyeo Festival Highlights

Tue, 12 Aug 2014 09:58:18 -0700

Eyeo festival highlights

Amelia McNamara

From the festival website, “Eyeo assembles an incredible set of creative coders, data designers and artists, and attendees – expect enthralling talks, unique workshops and interactions with open source instigators and super fascinating practitioners.” I’ll talk about some of the most inspiring talks and projects I saw at Eyeo this year, including work by Santiago Ortiz, Lillian Schwartz, Cod.Act, Kate Crawford and Nicholas Felton. Most of this work can be described best by the term “art,” so come expecting provocations, not prototypes. To learn more about the festival, visit eyeofestival.com

Meetup Groups: DataVis LA

Mon, 04 Aug 2014 18:49:08 -0700

Data visualization helps us understand data. The DataVis LA meetup discusses the many aspects of data visualization: exploratory data analysis, presentation graphics, infographics, design, art, etc., and brings together a diverse community of data scientists, statisticians, software developers, BI specialists, business analysts, journalists, designers and artists with the goal of learning more about the art and science of data visualization from each other.

Meetup Groups: LA Machine Learning

Mon, 04 Aug 2014 18:39:27 -0700

The LA Machine Learning Meetup began with events discussing a large variety of machine learning topics such as classification, clustering, neural networks, graphical algorithms, information retrieval, search, game theory, computational learning theory, reinforcement learning, collaborative filtering etc. More recently, a Data Science Track was launched with the focus on business applications and the entire process of data mining (e.g. business understanding, data collection, exploratory data analysis, data transformations, feature engineering, modeling, model validation, deployment, communication of results). While in fact Machine Learning is a part of Data Science and not the other way around, rather than starting a new meetup group, Data Science is featured within the already existing Machine Learning meetup.

useR! 2014 Conference Videos and Release Plan

Mon, 04 Aug 2014 18:11:48 -0700

Many of us here in the DataScience.LA Team were also involved in organizing the useR! 2014 conference, the annual get-together of the wonderful R community, which brought over 700 R users and developers from all over the world to Los Angeles this past July.

Meetup Groups: LA R Meetup

Mon, 04 Aug 2014 16:19:58 -0700

R is an open source software and programming language for data analysis, statistical modeling, visualization and data mining among other things. Recently, as the term “data science” has emerged to describe collectively these tasks, R has also become the primary tool of choice for data scientists. The LA R meetup began before this data science boom, back in 2009, by bringing together local users of R and featuring talks with world-class speakers while creating fruitful networking opportunities for its members. In retrospect, this group served as the very first data science meetup in Los Angeles and has significantly contributed to the development of our local data science community.

Welcome to Data Science LA!

Sat, 02 Aug 2014 21:12:52 -0700

Welcome! We are launching DataScience.LA to provide a home for all the content (slides, code, videos etc.) for several meetups in LA (Data Science/Machine Learning, R, DataVis etc.) and to engage the Los Angeles data science community in an open, active discussion about best practices and new developments in the field.