talk-data.com talk-data.com

Event

January Members Talk evening

2025-01-14 – 2025-01-14 Meetup Visit website β†—

Activities tracked

3

Hi PyLadies Berlin! In this members' talks evening held in-person and online, we will have an introduction from our sponsor Bettermile and 2 very insightful talks about Scikit Learn for you and a showcase of data at Bettermile πŸ₯³

πŸ¦ΈπŸ»β€β™€οΈ 🦹 Non Coding Super Powers is our beloved quick series about everything else, but code, that we need to be nurtured and grown.

🎀 Contributing to OpenSource - how to get started in 5 minutes!

πŸ’‘ Stefanie Senger (she/her) - Scikit-learns metadata routing API This talk will introduce scikit-learn users to the new API for metadata routing, a feature introduced in the recent releases and almost fully available since version 1.5 (released in May 2024).

Level: Beginner to the domain (already familiar with Python)

πŸ‘©β€πŸ’» Stefanie is an open source developer at :probabl., contributing mainly to scikit-learn. With a PhD in History centered on Solidarity Movements, she made a career shift into tech, bringing a unique interdisciplinary perspective to her work.

✨ Tamara Atanasoska (she/her) - Writing a custom scikit-learn estimator Scikit-learn is a popular machine learning library. It currently has over 200 estimators ready to use for a vast array of use cases. What if you are working on something special that still hasn't found its way into the library? Scikit-learn offers a way to write new compatible estimators, which can be seamlessly integrated with the rest of the library. We will look into what an estimator is, what API that scikit-learn estimators have, reasons why you would like to implement your own and an example of how to. We will end with real-world examples of how other OSS projects use this for their needs.

Level: Intemediate Python developer

πŸ‘©β€πŸ’» Tamara is working on ML explainability, interpretability and fairness. She is a maintainer of fairlearn and a scikit-learn and skops contributor. Tamara works as an open source engineer at :probably..

πŸ“¦ Helen FitzGerald and Claudia Stangarone - Predicting Delivery Risks with Machine Learning: A TrustCourier Innovation

Claims in logistics, especially for lost parcels or delivery issues, can be a significant cost for companies. In this talk, we’ll present the framework and share some early results of a new feature within TrustCourier. This feature uses machine learning to predict and flag high-risk deliveries before they escalate into costly claims.

πŸ‘©β€πŸ’» Claudia is a data analyst at GLS Studio, with a strong interest in machine learning and data engineering. With a PhD in mineral physics, she switched from a career in geo and planetary science a few years ago. Her goal is to strike the perfect balance between technology and science.

πŸ‘©β€πŸ’» Helen is a junior data analyst who transitioned into the field after achieving a B.A and M.Phil in linguistics, where she was first introduced to language models and Python. Her prior experience spans business development, social media & community management, and marketing, equipping her with a diverse and well-rounded perspective.

✨ Our host Bettermile provides a geo-based and AI-powered SaaS product suite for dynamic, multi-constraint, many-stop address processing, routing and navigation.


πŸ“† Agenda 18h30 Doors open 19h00 Community Announcements 19h15 Welcome from our sponsor Bettermile 19h20 Non-Coding Super Power talk: contributing to open source 19h25 Scikit-learns metadata routing API 19:55 short break 20h00 Writing a custom scikit-learn estimator 20h35 Predicting Delivery Risks with Machine Learning: A TrustCourier Innovation 20h50 Networking 21h30 See You Next Time! :D


❓ Can men attend ❓ Everyone is welcome. :) If you identify as someone well-represented in open source and in tech, please be mindful of the space and privileges you have, and use it to support others.

πŸŽ₯ This hybrid event will be streamed on YouTube https://www.youtube.com/@PyLadiesBerlin

πŸ• There will be food and drinks (with vegetarian and vegan options thanks to our sponsor)

🀝 By attending our online event, you agree to the PyLadies Code of Conduct: https://www.pyladies.com/CodeOfConduct/

πŸ“§ Contact Interested in speaking at one of our events? Have a good idea for a Meetup? Get in touch with us at [email protected]

πŸ’¬ Find us on the PyLadies Global workspace:

  1. https://slackin.pyladies.com enter your email address. Accept the email invitation
  2. Go to workspace https://pyladies.slack.com
  3. Join channel #city-berlin, #germany, #jobs-europe

Sessions & talks

Showing 1–3 of 3 Β· Newest first

Search within this event →

Predicting Delivery Risks with Machine Learning: A TrustCourier Innovation

2025-01-14
talk

Claims in logistics, especially for lost parcels or delivery issues, can be a significant cost for companies. In this talk, we’ll present the framework and share some early results of a new feature within TrustCourier. This feature uses machine learning to predict and flag high-risk deliveries before they escalate into costly claims.

Writing a custom scikit-learn estimator

2025-01-14
talk
Tamara Atanasoska (:probably..)

Scikit-learn is a popular machine learning library. It currently has over 200 estimators ready to use for a vast array of use cases. What if you are working on something special that still hasn't found its way into the library? Scikit-learn offers a way to write new compatible estimators, which can be seamlessly integrated with the rest of the library. We will look into what an estimator is, what API that scikit-learn estimators have, reasons why you would like to implement your own and an example of how to. We will end with real-world examples of how other OSS projects use this for their needs.

Contributing to OpenSource - how to get started in 5 minutes!

2025-01-14
talk
Stefanie Senger (:probabl.)

This talk will introduce scikit-learn users to the new API for metadata routing, a feature introduced in the recent releases and almost fully available since version 1.5 (released in May 2024).