• Autonomous Object Detection and Understanding SHAP values

    This event is co-sponsored by DataPhilly, The Data Lab, and Philly PUG. Please RSVP to only one of the meetup groups.

    Event Schedule:
    1. Meeting opens at 5:45pm
    2. Introductions (Starts at 6pm)
    3. Speaker Event -1
    Topic: Autonomous Object Detection
    Speaker: Ridwan Alam
    4. Speaker Event -2
    Topic: Understanding SHAP values for better model interpretation
    Speaker: Dan Pfeffer
    5. Networking Event (30 minutes)
    Hang around for an online networking event after the speaker event.

    Speaker Event - 1: Autonomous Object Detection
    With autonomous vehicles taking off in the past several years, it is good to explore the aspect that is instrumental in creating a good autonomous vehicle system: Object Detection. The vehicles’ cameras are feeding the autonomous system what objects it is observing (traffic lights, traffic signs, and other vehicles). The autonomous system then utilizes the information to make a decision to turn left, go straight, and etc. Let’s create an Object Detector model using Darknet and YOLOv4 to see if we can emulate the "eyes of the car".

    Speaker Bio:
    Ridwan Alam is a self-taught software developer, and recently completed the Metis Data Science bootcamp. He enjoys working with Computer Vision, NLP, Machine Learning, along with working on projects in React to help create stimulating visuals. He takes a key interest in emerging technologies such as Hyperloop and Bitcoin as he sees these tools as pathways into our future. Please reach out to him if you would like to talk more about Data Science, Web Development, or anything tech! If you are aware of any Data Science opportunities please contact him as he is actively searching since his Data Science bootcamp!

    Speaker Event - 2: Understanding SHAP values for better model interpretation
    Although there have been sweeping improvements in the predictive power of machine-learning models, the interpretation of these models and their results have become more complex. While a single decision tree or basic regression model can easily be interpreted and the importance of features determined, more complicated ensembles or deep-learning models are not as readily understood. SHapley Additive exPlanation (SHAP) values provide an agnostic way of exploring how different features impact model results. Although this concept was originally devised for game theory, it has also enjoyed great success with machine learning. In this talk I will explore SHAP values, how one calculates them and how to apply them to feature importance in machine learning.

    Speaker Bio:
    Dan has a PhD in Physics & Astronomy from Johns Hopkins University and has worked to apply machine learning techniques to Cosmology. After exploring the mysteries of the Universe, he transitioned to data science full-time. Dan now analyzes insurance claims from the healthcare industry to find undiagnosed patients with rare diseases and explores patient journeys through different disease states.

    You must download and install Zoom if you have not done it already. Once you have installed Zoom, click on the event link provided in your email to join the meeting.

  • Civic Hacking with Python with Code for Philly

    Online event

    Join us as we hear from the Code for Philly (CFP) Team and their project leaders about opportunities to use your Python skills to improve the city. CFP brings together coders, graphic artists, project managers, UX/UI designers, and other professionals to complete projects that benefit the City of Philadelphia and nonprofits in our community.

    The group will do a brief review of their current Python projects, who they support, and how to get involved. It's a great event for those who want to get involved, whether you are looking for real-world experience in order to learn more about Python, or are already a Python expert and want to give back.

  • Visualizing Deep Learning with Tensorboard & PyTorch and Self Programming AI

    This event is co-sponsored by DataPhilly and PhillyPUG (Python Users Group). Please RSVP to only one of the meetup groups.

    Event Schedule:

    1. Meeting opens at 5:45pm
    2. Introductions (Starts at 6pm)
    3. Speaker Event -1
    Topic: Visualizing Deep Learning with Tensorboard & PyTorch
    Speaker: Joe Papa
    4. Speaker Event -2
    Topic: Self Programming Artificial Intelligence
    Speaker: Kory Becker
    5. Networking Event (30 minutes)
    Hang around for an online networking event after the speaker event.

    Speaker Event - 1

    Visualizing Deep Learning with Tensorboard & PyTorch
    Tensorboard is a powerful visualization toolkit for deep learning research and development. Its visualization capabilities, once reserved for Tensorflow, are now natively supported by PyTorch. In this presentation, you'll learn how to use Tensorboard with PyTorch to develop and visualize deep learning models.

    Speaker Bio:
    Joe Papa has over 25 years experience in research & development and is the founder of INSPIRD.ai. He holds an MSEE and has led AI Research teams with PyTorch at Booz Allen and Perspecta Labs. Joe has mentored hundreds of Data Scientists and has taught 6,000+ students across the world on Udemy.

    Speaker Event - 2

    Self-Programming Artificial Intelligence
    https://arxiv.org/abs/1709.05703

    Is it possible for a computer program to write its own programs? While this kind of idea could seem far-fetched, it may actually be closer than we think. This presentation introduces "AI Programmer", a machine learning system, which can automatically generate full software programs requiring only minimal human guidance. The system uses genetic algorithms coupled with a tightly constrained programming language. We’ll cover an overview of the system design and see examples of its software-generation capabilities.

    Speaker Bio:
    Kory Becker is a Senior Software Engineer for Bloomberg LP. With a background in artificial intelligence and machine learning, she is the author of “Building Voice-Enabled Apps with Alexa” (2017 Bleeding Edge Press), and creator of AI Programmer, a system that can generate software programs with minimal human guidance. She has developed award-winning software products that have been featured prominently in publications like PC Magazine, PC World, USA Today, Consumer Reports, and Apple iTunes. Her research has been referenced by leading sources, including Google Brain. You can find her articles at http://www.primaryobjects.com. She is active on social media (https://twitter.com/primaryobjects) and on GitHub (https://github.com/primaryobjects).

    You must download and install Zoom if you have not done it already. Once you have installed Zoom, click on the event link provided in your email to join the meeting.

    3
  • Good to the Last Drop: Writing Robust Flask Apps

    Online event

    We will be meeting virtually! Join us on BlueJeans: https://bluejeans.com/404863639

    We'll open the video conference at 5pm, and start the presentation at 5:30pm. Follow along as Isaac Evans walks us through creating a Flask app.

    Building it right the first time doesn’t have to be hard! During this hands-on tutorial, you’ll learn about developing robust Flask apps, common Flask “gotchas”, and concrete best-practices with detailed instructions to avoid them. A guided tour of tools that always keep an eye on your code and ensure you follow these practices will set you on the path to Flask success!

    Join us: https://bluejeans.com/404863639

    Isaac Evans is the leader of a small startup working on giving security tools directly to developers. Previously, he conducted research into binary exploitation bypasses for techniques like control-flow integrity and novel hardware defenses on new architectures like RISC-V as a researcher at the US Defense Department under a SFS program and at MIT Lincoln Laboratory. Isaac received his BS/MS degrees in EECS from MIT. Other interests include next-generation programming languages, secure-by-design frameworks, software-defined radio, and the intersection of cryptography and public policy.

    7
  • Project Night

    Location visible to members

    Work on your own Python projects, get programming help, work through tutorials, help others, and hang out with Pythonistas. We'll share some resources to help new coders get started under the guidance of experienced programmers. Dinner will be served, thanks to our host.

    We'd like to feature a few lightning talks. If you have a cool Python project you're working on and would like to share, get in touch with the PhillyPUG organizers. Works-in-progress are strongly encouraged, it is a great way to get feedback and hear new ideas!

    If you're hiring or looking, feel free to drop by to mingle. Be sure to bring business cards and job descriptions.

    Audience: Open to everyone! We welcome new coders, experienced professionals, and everything in between.

    Things to bring: a laptop, power cord, and a smile!

    All attendees are expected to follow the Python Software Foundation's Code of Conduct:
    https://www.python.org/psf/codeofconduct/

    Please see any of the organizers if you have any questions, or are looking to host your own Python project night.

    2
  • "How I Solved my NYC Parking Problem with Python" with Jessica Garson of Twitter

    Doors open at 5:30pm; pizza at 6. The presentation will start soon afterward!

    We are lucky this month to have a speaker from New York City, Jessica Garson. Jessica is a Developer Advocate at Twitter, and will be showing us how she used Python to solve her NYC parking problem:

    "Since I have a car in New York City, my car is subject to the city’s alternate side of the street parking regulations. This means most nights I need to move my car before the early morning street cleaning that happens in my neighborhood. I had developed a nightly routine around moving my car before I go to bed. I am sometimes a bit too good at this and I often move my car on days I don’t need to. Since alternate side of the street parking is often canceled on days where there are holidays, or bad weather, there is a Twitter handle @NYCASP, which posts daily and whenever there is an emergency situation. I used Python, Twilio and the Twitter API to solve this problem for myself so I get a text message whenever I don’t need to move my car."

    Jessica Garson is a Python programmer, educator, and artist. She currently works at Twitter as a Developer Advocate. Previously, she was an adjunct professor teaching Python at NYU and worked at ISL, Burson-Marstellar, The National Education Association, ISSI Data, and Salsa Labs. Before working in technology, Jessica worked on numerous political campaigns throughout the country. She has run many meetups and conferences including DC’s Tech Lady Hackathon in 2016 and 2017, and DC’s Hack&&Tell. In her spare time, she is on a never-ending quest for the perfect vegan snack.

    You can follow Jessica on Facebook, Instagram, Pinterest, and SnapChat... just kidding! Follow her on Twitter here: https://twitter.com/jessicagarson

  • Simpl Developer Bootcamp: How to Make Serious Games and Simulations with Django!

    **NOTE**: You MUST register at this link, NOT through Meetup:

    https://forms.gle/EHa1T6NftporwSVT9

    Built by experts in game design and education, Simpl is free, open source, and is a “simple” yet sophisticated toolset designed to transform learning experiences with serious game play. We’re passionate about sharing Simpl with the world.

    To that end, the Alfred West Jr. Learning Lab and Wharton Interactive is pleased to announce our first-ever Simpl Developer Bootcamp! It will take place online (we will stream every session) and on the campus of The Wharton School in Philadelphia, PA on Friday, October 25, 2019. This 1-day bootcamp is aimed at developers to show what Simpl can do, and get you on the path of building your own Simpl simulations. During this bootcamp you’ll hear from the core authors of the platform as we start with the design principles that govern the data model to writing your first lines of code to bring that idea to life. Below is a tentative agenda for our 1-day bootcamp:

    * The Simpl Data Model
    * Build a Simple Game with Simpl
    * Hands-On Coding: Single and Multiplayer Games
    * Resources and Take-Aways

    When we first built Simpl we had two distinct audiences in mind. One was the developers who will use the platform to bring Simpl games to life. The other were the practitioners who are professors, instructional designers, or more broadly, anyone involved in teaching that believes that a game or simulation can improve the learning experience for their students. Though this bootcamp is aimed at developers, both sets of users are critical to the success of your game or simulation in the classroom. It is our hope that the developers attending this bootcamp will go back to their respective organizations and find passionate practitioners to partner with to bring a Simpl game into the classroom!

    PhillyPUG is helping promote this event for our primary hosting sponsor, The Wharton School. If you are interested in attending either online or in-person please fill out this form:

    https://forms.gle/EHa1T6NftporwSVT9

  • Wagtail Space US: A Two-Day Conference for Django's Favorite CMS

    Jon M. Huntsman Hall

    REGISTER HERE: https://us.wagtail.space/

    Wagtail is a very popular content management system for the Django web framework. It is used by NASA, Amnesty International, Google, Mozilla, and powered HillaryClinton.com during the 2016 presidential election (so it scales!). More information is available here: https://wagtail.io/

    Wagtail Space US will comprise talks, training and an optional sprint. The event is free, and we encourage anyone with interest to come, from beginner to expert.

    *** If you wish to attend, you must register at this link! Click the "Sign Up" button. ***

    REGISTER HERE: https://us.wagtail.space/

  • Adventures in Dunderland: Introduction to the Python Data Model

    Jon M. Huntsman Hall

    Presented by Walt Mankowski.

    Hosted by PhillyPUG at the Wharton School, Huntsman Hall, room G-55.
    Doors at 5:30pm, pizza around 6pm, presentation shortly after.

    Description

    Python is designed to be easy to learn for beginners, and easy to pick up for experience programmers. But Python’s simplicity means you might not be using all the features the language has to offer. This is particularly true if the features don’t exist in the languages you’re used to.

    Last year I left academia and got a job at a startup as a Python programmer. I thought I knew the language pretty well, but a few months in I was surprised to discover a language feature I hadn't known about. Python classes have can special methods that can be used to have the classes pretend to be built-in types. These methods provide an interface to the Python data model, and they’re a key feature in writing idiomatic Python code. They can also make code look like complete magic if you don’t know they exist.

    In this talk I’ll try to demystify things. I’ll review Python’s double-underscore (“dunder”) methods, which combine ideas from operator overloading, mix-ins, and inheritance, but which are implemented in a unique way by Python. We’ll discuss how they can be used to have your classes emulate the behavior of Python’s internal types like lists and dictionaries.

    Bio

    Walt is a recovering ivory tower computer scientist. He’s a long-time Perl programmer and short-time Python programmer who enjoys pointing out things that Perl does better than Python to his friends and coworkers. He enjoys Perl, Python, regular expressions, high-performance computing, and Futurama.