Machine Learning with Python

**Latest Dojo Location!** **Knotty Pine Brewing** 1765 W 3rd Ave, Columbus, OH 43212 We're going to try a new dojo location for a few weeks and see how it works Dojos are informal Python group study sessions where everyone interested in Python gathers to learn about Python, help others with Python, or just hang out. Everyone is welcome from Python beginners to experts. Bringing a laptop is encouraged (we'll have extension cords and power strips). If there's something you want to learn leave a comment on this invite so we can plan ahead. We're looking for speakers for our Monthly Meetups! Fill out the form if you are interested in presenting to the Python Community. https://forms.gle/ehSfUAC2WgR34Crq9

AI is changing how art is made. But when does it stop being your work and start being the machine’s? This month we're going to be doing a panel with with digital image, music, and written word artists, talking about at what point, while using AI in the creation process, does the work become not the artist creation? We encourage audience participation during this event that will be moderated by Chris Slee. Whether you’re deep in the field or just getting curious, come connect with others building and exploring AI in Columbus. Sponsored by [Transform Labs](https://www.transformlabs.com/services)

**Improving Office in Franklinton** Physical location: Improving Office 330 Rush Alley Suite #150 Columbus, OH 43215 Schedule: 6:00 p.m.: Socialize, eat, and drink. Improving will be providing pizza and beverages. 6:30 to 8:00 pm. Main meeting and presentation(s). Topic: Exploration of Large Language Models and Programming with Chris Pazsint We meet on the last Monday of each Month. Presentations are given by members and friends of this group. If you would like to do a presentation (small or large) on a python topic, please contact Central OH Python at centralohpython@gmail.com

**Important time note:** Please plan on arriving between 5:30 and 6:00 as the elevators lock after 6 and you'll need to message us and we'll need to come get you. The building address is 4450 Bridge Park The entrance is 6620 Mooney St, Suite 400 You will need to scan your ID at the door to get a visitor badge. **Abstract** GitHub Copilot is powerful, but what if you could scale from a solo AI assistant to an entire team of specialized agents working in parallel? This session introduces Squad: an open-source framework for multi-agent orchestration that lets you define teams of AI agents with specific roles, responsibilities, and expertise. We'll progress from Copilot basics to the Copilot CLI, explore how Agents add autonomy, and see how Instructions and Skills let you customize agent behavior. Then, the climax: a live demo where a Squad team of 3 agents (Lead, Developer, Tester) stands up and builds a working application in real-time, showcasing true multi-agent collaboration. Whether you're new to AI or exploring how to scale your use of Copilot, this session will show you what's possible when agents work as a team. **YouTube Link** TBD

**Details:** If you haven’t yet built an Agent yourself, this is for you! A hands-on workshop where you build a production-ready AI chatbot from scratch using Python, Streamlit, Claude AI, and RAG (Retrieval-Augmented Generation). **Speaker Bio:** Gus Cavanaugh is a former strategy consultant turned GTM leader in data and analytics. He teaches Python, data, and AI through local meetups and enjoys helping others get hands-on with modern tools. He lives in Winston-Salem with his family and starts most days at 6am in the gym. **Audience Takeaway:** By the end of this workshop, you'll have created: * ✅ AI-powered chatbot that answers questions about uploaded documents * ✅ RAG implementation with vector search and semantic retrieval * ✅ Web search integration for current information * ✅ Professional web interface using Streamlit * ✅ Cloud-deployed application that runs immediately * ✅ Portfolio-ready code you can customize and share No AI experience required. No local installation needed. Everything runs in the cloud. **Zoom: This is a *hybrid* event. To attend online, join us on Zoom here at 6pm:** https://iit-edu.zoom.us/j/89379230295?pwd=NdETyE5sdYuSrvsrBZXSBFkUESBVkg.1 Meeting ID: 893 7923 0295 Passcode: 5t5WYn **Sponsor:** **[AlphaSense](https://www.tegus.com) will provide the meeting site, as well as pizza and soft drinks for the onsite participants.** * **Address:** 200 N. LaSalle Street. Suite 1100. Chicago, IL 60601 * **AlphaSense's Overview:** The world’s most sophisticated companies rely on AlphaSense to remove uncertainty from decision-making. With market intelligence and search built on proven AI, AlphaSense delivers insights that matter from content you can trust. Our universe of public and private content includes equity research, company filings, event transcripts, expert calls, news, trade journals, and clients’ own research content. * The acquisition of Tegus by AlphaSense in 2024 advances our shared mission to empower professionals to make smarter decisions through AI-driven market intelligence. Together, AlphaSense and Tegus will accelerate growth, innovation, and content expansion, with complementary product and content capabilities that enable users to unearth even more comprehensive insights from thousands of content sets. Our platform is trusted by over 6,000 enterprise customers, including a majority of the S&P 500. Founded in 2011, AlphaSense is headquartered in New York City with more than 2,000 employees across the globe and offices in the U.S., U.K., Finland, India, Singapore, Canada, and Ireland. * **Logistics**: To access the Tegus by AlphaSense building, we require **first and last names** of those who RSVP'd by Apr 15. Attendees will then present their **IDs** when they arrive at the front desk (right when they enter the building). They will be sent up in the elevator to the 11th floor where we will be.

**The Data-Driven Brand: Using Analytics to Shape Perception** Can you use analytics to improve tacos? This being CBUSDAW, we think the answer is probably “yes”, but we’re not sure how to implement or test this theory. For our April meetup we’ve got Sara Kear, CMO of Condado Tacos, to investigate this delicious question. Sara will explore how she blends quantitative data and qualitative customer feedback to shape brand positioning and drive business decisions. We all know that marketing and analytics go way beyond attribution. Sara will show how Condado uses customer insights to inform product and pricing strategy. She’ll also highlight how Condado leverages customer feedback at scale to influence operational priorities, positioning marketing as the voice of the customer across the organization. In the last 12 years Condado has gone from one location in Columbus to 52 locations across 10 states, so we’re guessing there’s more to that growth than really good guac (though the guac probably helps). Ultimately, this talk focuses on the intersection of art and science—using data to inform creativity and build a brand that resonates with customers in a measurable way. **About Our Speaker** Sara Kear is Chief Marketing Officer at Condado Tacos, where she oversees brand, restaurant design, menu and pricing strategy, off-premise including catering, and customer data strategy. Since joining in 2021, she has helped grow the brand from 19 to 52 locations while building a data-driven marketing organization focused on loyalty and customer insights. Condado has since been named to the Inc. 5000, recognized as Breakout Retailer by Chain Store Age, and consistently ranked among FastCasual’s Top 100 Movers & Shakers. Thanks to our 2026 sponsors: [Clarivoy](https://www.clarivoy.com), [What Box Consulting Group](https://www.whatboxconsultinggroup.com), [Conductrics](https://www.conductrics.com), and [Piwik PRO](https://piwik.pro) More info at [cbusdaw.com](https://cbusdaw.com)

The Fellowship of the Star Schema: Transforming OLTP Data for Power BI One does not simply build reports on OLTP data. Join us on an epic journey from the depths of raw, normalized tables to the shining halls of a well-modeled star schema fit for Power BI greatness. We will demystify the differences between OLTP and OLAP, walk through star schema vs snowflake (and why Power BI has a clear favorite), and show you the compression differences between normalized and columnar storage that will make you never look at an OLTP model the same way again. We will cover the different types of dimensions, when to use them, and how to handle Slowly Changing Dimensions without losing your mind. You will leave knowing exactly how to identify a bad model, how to convert OLTP data into a clean star schema, and how to forge relationships that rule them all. Whether you are a data wizard, a curious hobbit, or somewhere in between, your models will never be the same.