Welcome to the next virtual event from PyData Edinburgh!
As always, this will last an hour, and we'll have a main talk plus a Q&A session at the end. The session starts at 18:30, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!). We've got some more volunteers for lightning talk, so if we get a couple more we'll be able to run an evening with just lightning talks, which would be great.
MAIN TALK: Automated Exploratory Data Analysis of Databases
=====================================================================
Diego will present some of the challenges of exploratory data analysis in data science and data engineering projects and how to approach them. He will show how to use the AEDA Python library (https://github.com/darenasc/aeda) developed by himself that helps with the exploration of new data sets from databases. The takeaways from the talk are: ideas and techniques to use for data exploration, how to use an automated solution to explore the content of databases and how to create a data catalogue, and also some recommendations of Python libraries for data exploration.
My links are:
- Personal webpage with a list of projects and talks: https://darenasc.github.io
- LinkedIn: https://www.linkedin.com/in/darenasc/
- Twitter: https://twitter.com/darenasc
- Calendly: https://calendly.com/darenasc/
About
Diego Arenas is a computer scientist with an MSc in Data Science from the University of Edinburgh. He is currently finishing his Engineering Doctorate in Computer Science at the University of St Andrews. He has more than 15 years of experience working on data science and data engineering projects for multiple industries.
LOGISTICS
===========
1825: Zoom Waiting room will open
1830: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 1930
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
The PyData Global Online Conference is where users, contributors, and newcomers can share experiences to learn from one another and grow together. PyData provides a virtual forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization.
This three-day online event consists of talks, tutorials, and discussions to bring attendees the latest project features along with cutting-edge use cases.
The time span of the conference stretches beyond any single time zone, reflecting the global nature of our community. To accommodate our attendees, each session will be recorded and made available to attendees the following day. Following the Conference, all recordings will be posted to the PyData YouTube channel.
Smart solutions recommendations in an IT ticketing system
Description changed:
Welcome to the next virtual event from PyData Edinburgh!
As always, this will last an hour, and we'll have a main talk plus a Q&A session at the end. The session starts at 18:30, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!). We've got some more volunteers for lightning talk, so if we get a couple more we'll be able to run an evening with just lightning talks, which would be great.
Tonight we're delighted to welcome a speaker from one of our sponsors, thugh there's been a name change there!
MAIN TALK: Smart solutions recommendations in an IT ticketing system
=====================================================================
First line support in large organisations requires significant human resources to deliver fast, on-demand response to customer incidents. In order to reduce ticket inflow, companies rely on knowledge bases, either browsable by the customer or used as a backend for chatbots. We will discuss some of our attempts at providing smart knowledge base solution identification at N-able, as well as the opposite problem: generating knowledge base articles from solved helpdesk tickets.
About
Catalina Hallett is a data science technical lead at N-able, where she works in developing machine learning solutions that enhance N-able products and help us better understand and support our customer base. Her main area of expertise is NLP and she has previously worked in AI for credit risk applications and predictive text modelling.
LOGISTICS
===========
1825: Zoom Waiting room will open
1830: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 1930
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Realtime NLP in Google cloud with Kafka, Apache Beam, TFX and Vertix AI.
Description changed:
Welcome to the next virtual event from PyData Edinburgh!
As always, this will last an hour, and we'll have a main talk plus a Q&A session at the end. The session starts at 6pm, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!). We've got some more volunteers for lightning talk, so if we get a couple more we'll be able to run an evening with just lightning talks, which would be great.
Tonight we welcome two speakers who are giving the talk together. Angus is a well known face at PyData, and has helped support us since the very start and we're delighted his colleague Alex will also be joining us.
MAIN TALK: Realtime NLP in Google cloud with Kafka, Apache Beam, TFX and Vertix AI.
=====================================================================
Bios:
Angus Neilson, Senior Data Engineer at Trustpilot (Data Platform)
Angus has worked with data in some shape or form for the last 15 years across many sectors including Finance, Telco, Aeronautics, Healthcare and Energy. Most recently he's been working with Kafka and a variety of cloud based data technologies in AWS, Azure and Google. His focus is making data fast and correct. He has a long running interest in how we develop and encourage new generations of Engineers.
Alex Chan, Machine Learning Engineer at Trustpilot (Data Platform)
Alex is an ML Engineer at Trustpilot currently working on operationalising NLP models across a variety of languages. His favourite machine learning algorithm is the Gaussian process.
----------------------------------------------------------------------------------------------------
Abstract:
In this talk we will explore the implementation of a new improved real time analysis of reviews within TrustPilot with natural language processing enabled by Kafka, Apache Beam, TFX (Tensor flow extended) and Vertix AI. All of course written in Python :-)
LOGISTICS
===========
1755: Zoom Waiting room will open
1800: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 1900
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Machine Learning and its Potential to Improve Epilepsy Diagnosis
Description changed:
Welcome to PyData Edinburgh's August event, when when we'll be hearing about ML's potential to help tackle epilepsy.
As always, we're keeping this to a one hour session, and we will have a main talk plus a Q&A session at the end. We will meet at 18.30, use the Zoom link which will be provided in the registration email once you RSVP.
We want to very much keep this group alive, so let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!).
MAIN TALK & SPEAKER BIO:
=====================================================================
Machine Learning and its Potential to Improve Epilepsy Diagnosis
Static rule-based algorithms to assist medical diagnosis and treatment monitoring have been used in practice for decades (e.g. heart rate monitoring). Research into detecting epileptic seizures from the electrical activity of the brain , with machine learning, has been an active area of research for over 20 years. Given recent advancements in "big data", portable bio-sensing technologies, and other computer hardware/software, the feasibility of successfully implementing such algorithms into practice is improving.
This talk is an overview of how new applications of ML could soon provide physiologists with better quantitative tools to improve workflow and diagnostic accuracy. Prior knowledge of epilepsy, neuroscience, and ML is not assumed: talk aims to be accessible to a broad range of backgrounds.
Bio
Dr. David Elliott is a Teacher in Mathematical Sciences Computing at the University of Edinburgh, with a PhD in Applied Statistics from Lancaster University. He has a background in Psychology and Developmental Disorders, with his recent research focusing on developing hardware, software, and quantitative methods for portable neurological monitoring of childhood patients with epilepsy. He now focuses on teaching the statistical foundations and practical applications of data science and machine learning.
LOGISTICS
===========
18:25: Zoom Waiting room will open
18:30: Meetup will start — welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 19:30
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Adopting Amazon SageMaker for machine learning at FreeAgent
Description changed:
Welcome to PyData Edinburgh 2021, July edition! Tonight, we have a great talk about model deployment in the cloud.
As always, we're keeping this to a one hour session, and we will have a main talk plus a Q&A session at the end. We will meet at 6.00pm, use the Zoom link which will be provided in the registration email once you RSVP.
We want to very much keep this group alive, so let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!).
MAIN TALK & SPEAKER BIO:
=====================================================================
SageMaker is Amazon Web Services’ (AWS) platform for machine learning. It offers a range of different features that cover the end-to-end lifecycle of a machine learning project, vastly simplifying the process. Or at least that is the promise, but is it the reality? At FreeAgent, the Data Science team has been using SageMaker extensively for two years. In this talk I want to share our experiences and introduce the key SageMaker features that work well for us in solving specific problems. I will also highlight some problems we encountered along the way and share the lessons we learned in adopting an AWS-based approach to machine learning.
Bio
David Edwards is a Senior Software Engineer at FreeAgent. He joined FreeAgent as a Data Scientist and worked to bring FreeAgent’s first machine learning driven feature to customers. Recently, he has moved to FreeAgent’s Data Platform team to help enable teams across the company to deliver data-driven capabilities to customers.
LOGISTICS
===========
1755: Zoom Waiting room will open
1800: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 1900
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
What can data scientists learn from data-driven responses to Covid-19?
Description changed:
[Photo from Prachatai, Flickr https://www.flickr.com/photos/prachatai/49616970132]
Welcome to PyData Edinburgh 2021, April edition! We've been quiet for a bit but we tonight have Matthew Higgs (who was one of the original founders of PyData Edinburgh!) with an interesting talk, so as always, get comfy and grab a beer. We hope to see you all in person at some point - not too far away?
As always, we're keeping this to a one hour session, and we will have a main talk plus a Q&A session at the end. We will meet at 6.30pm, use the Zoom link which will be provided in the registration email once you RSVP.
We want to very much keep this group alive, so let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!).
MAIN TALK & SPEAKER BIO:
=====================================================================
What can data scientists learn from data-driven responses to Covid-19?
Data-driven responses to Covid-19 have been developed at speed across the public sector, academia, and commercial sector - leading to a range of successes, failures, and opportunities for lessons to be learned. At the ‘Observatory for Monitoring Data-Driven Approaches to Covid-19’ (omddac.org.uk) we are analysing key data-driven responses to Covid-19 and collating lessons learned by way of stakeholder interviews, case study analysis, and representative public surveys. In this talk, I will highlight some key findings from our stakeholder interviews and reflect on the role of data science during the Covid-19 pandemic. I will discuss successful applications of data science, ethical issues to be aware of, and what stakeholders *really* think about working with data scientists.
Matthew Higgs MMath, PhD is a Lecturer in the Department of Computing and Information Sciences at Northumbria University and a Co-Investigator on the UKRI-funded project ‘Observatory for Monitoring Data-Driven Approaches to Covid-19’ (omddac.org.uk). Since completing his PhD in Computational Statistics and Machine Learning at University College London in 2011, Matthew has worked in technical and non-technical roles in academia, the commercial sector, and the public sector - with a focus on managing diverse stakeholders and developing data-driven products and solutions.
LOGISTICS
===========
1825: Zoom Waiting room will open
1830: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 1930
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Welcome to the final virtual PyData Edinburgh of 2020! What a year!
Though a very different set of events from usual, we have thoroughly enjoyed all the speakers we have heard from. We're delighted that it's someone from our sponsor Lloyds that will be speaking for us this time.
As always, we're keeping this to a one hour session, and we will have a main talk plus a Q&A session at the end. We will meet at 6pm, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!).
MAIN TALK:
=====================================================================
Valcon is a Python library for supercharging all ML and data-related projects with easy to use Controls (Metrics and Validations), Logging, Configuration and more.
This talk will cover the development of Valcon in Lloyds Banking Group as an innersource, use-case driven library, which aims to accelerate and standardise the development and reporting of data and machine learning metrics across the data science portfolio.
The talk will be hosted by Christopher Hedderick and Radu Ghitescu, Machine Learning Engineers at LBG, and will include an overview of Valcon, lessons learned during development and a live demo.
LOGISTICS
===========
1755: Zoom Waiting room will open
1800: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 1900
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Welcome to the next of our virtual PyData Edinburgh!
As always, we're keeping this at just one hour, and we will have a main talk plus a Q&A session at the end. We will meet at 7pm, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!). We've got some more volunteers for lightning talk, so if we get a couple more we'll be able to run an evening with just lightning talks, which would be great.
MAIN TALK: Cheuk Ting Ho
=====================================================================
Bio:
After having a career in data science, Cheuk now brings her knowledge in data and passion for the tech community into TerminusDB as the developer relations lead. Cheuk constantly contributes to the open-source community by giving free tutorials on Twitch and organise sprints to encourage diversity contributions.
Abstract:
Do you have multiple versions of Python installed? Have you installed via Homebrew and Anaconda? Chances are, you have spaghetti Python paths, which could be a pain in the long run. It’s time to clear up and manage different python environments properly.
LOGISTICS
===========
1855: Zoom Waiting room will open
1900: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 2000
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Untangle Spaghetti Python Paths: How to manage your Python environments
Description changed:
Welcome to the next of our virtual PyData Edinburgh!
As always, we're keeping this at just one hour, and we will have a main talk plus a Q&A session at the end. We will meet at 7pm, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk in the future, whether a main or a lightning one, we're always looking out for speakers (as you know!). We've got some more volunteers for lightning talk, so if we get a couple more we'll be able to run an evening with just lightning talks, which would be great.
MAIN TALK: Cheuk Ting Ho)
=====================================================================
Bio:
After having a career in data science, Cheuk now brings her knowledge in data and passion for the tech community into TerminusDB as the developer relations lead. Cheuk constantly contributes to the open-source community by giving free tutorials on Twitch and organise sprints to encourage diversity contributions.
Abstract:
Do you have multiple versions of Python installed? Have you installed via Homebrew and Anaconda? Chances are, you have spaghetti Python paths, which could be a pain in the long run. It’s time to clear up and manage different python environments properly.
LOGISTICS
===========
1855: Zoom Waiting room will open
1900: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 2000
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Welcome to our latest virtual PyData Edinburgh! As in the case of the last one, we're keeping this into the 1-hour format, and we will have a main talk plus a Q&A session at the end. We will meet at 6pm, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk, whether a main or a lightning one, we're always looking out for speakers (as you know!).
Ben Batorsky
Ben is a freelance Data Scientist working across industries (government, infrastructure, health) to build data science capacity and create tools and models for business impact. He has extensive experience in the field of Natural Language Processing and the use of multi-modal datasets.
A common task in processing text data is to identify named subjects such as companies and products. This is referred to as Named Entity Recognition (NER). In this talk, I will provide an overview of model-based NER and focus on an application using the spaCy NLP library on a non-English text corpus. I will discuss how to structure data for this task and considerations when evaluating results.
LOGISTICS
===========
1755: Zoom Waiting room will open
1800: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 1900
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Welcome to our latest virtual PyData Edinburgh! As in the case of the last one, we're keeping this into the 1-hour format, and we will have a main talk plus a Q&A session at the end. We will meet at 7pm, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk, whether a main or a lightning one, we're always looking out for speakers (as you know!).
TALK: A beginner’s guide to web scraping in Python
==================================================
Caterina Constantinescu
In this talk I’ll be sharing my recent experiences with Scrapy, a tool for webscraping in Python. This introductory talk will briefly discuss some alternative tools within the webscraping landscape, then cover a few examples of increasing complexity (i.e., pages to scrape) - all accompanied by a discussion of the relevant Scrapy code generating the results, as well as some minimal examples of data wrangling used on the information extracted. In the interest of full disclosure, I will be discussing this topic from the perspective of a regular R user, but a Python neophyte - so feedback and advice will be welcome.
Bio: Dr Caterina Constantinescu is a data scientist working at Tesco Bank, whose past work ranges across areas such as research methods, national health data, occupational therapy, transport and data for good. Her academic background prior to this involved researching if various emotion-generating stimuli used in lab settings could approximate emotional states occurring in daily life. For several years she have also organised meetings for the R user group in Edinburgh (EdinbR), focusing on statistical programming.
LOGISTICS
===========
1855: Zoom Waiting room will open
1900: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 2000
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
The Companies We Keep: Building a network graph of UK corporate ownership data
Description changed:
Welcome to our third event in the series of virtual PyData Edinburgh! As per usual, we're keeping this into the 1-hour format, and we will have a main talk plus a Q&A session at the end. We will meet at 6pm, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk, whether a main or a lightning one, we're always looking out for speakers (as you know!). Specifically, we'd like for the next event to be a lightning talks-only one, and we're looking for 5 speakers to give a lightning (5 mins!).
MAIN TALK:
=====================================================================
Bio: Adam is a recovering astrophysicist who made the transition to commercial data science 5 years ago. He is currently Lead Data Scientist at HAL24K, a smart-city startup. Adam is also a Royal Society Entrepreneur in Residence at the University of Southampton and a core volunteer with DataKind UK.
Abstract: In June 2016 the UK government launched the world’s first open “beneficial ownership” register; a requirement for all UK companies to register who were the “persons of significant control”, PSCs, who actually controlled the company. In a partnership between DataKind UK and Global Witness we have built the worlds first network graph mapping all of the UK public data on those who control corporate interests in the UK; it comprises in excess of 4.5 million companies and 4 million individual people. It has been enriched with company officer data and metrics of financial secrecy based upon geographic regions.
The goal of the project was to enable Global Witness to search for “shady patterns” within corporate ownership networks to act as leads for investigative journalism to expose corrupt practices. Further more, we were able to analyse the completeness of the register and identify ways of improving such data structures to inform other world governments how to best build similar public registers of corporate ownership.
We present here how we built this amazing data structure using Python tools for cleaning and data processing and a Neo4j graph database storing the network graph itself. In addition, we share some of the insights derived from this process.
LOGISTICS
===========
1745: Zoom Waiting room will open
1800: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 1900
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Welcome to our second event in the series of virtual PyData Edinburgh! As in the case of the last one, we're keeping this into the 1-hour format, and we will have a main talk plus a Q&A session at the end. We will meet at 7pm, use the Zoom link which will be provided in the registration email once you RSVP.
As always, let us know if you would like to give a talk, whether a main or a lightning one, we're always looking out for speakers (as you know!).
MAIN TALK:
=====================================================================
Bio: Following a career as a highly qualified IT manager working in the oil and gas sector, Alex McCall joined the National Records of Scotland, before pursuing his passion for data and studying for a masters degree. Alex is now a data scientist working with the rapidly growing data science company Effini, helping businesses of all kinds gain a competitive edge through data.
Abstract: Commercially successful data science delivery demands that applications are economical to run, secure and relevant to the customer. Costs can run out of control and basic security requirements can be breached, leaving the company exposed. Too often, meet-ups, academic lectures and books focus on the technical aspects, but do not always demonstrate how to commercialise and deliver the application.
This talk charts the personal development of the speaker during development of a dashboard application for a holiday company. It includes key decisions (and mistakes) and obstacles that led to the final design. This journey started from zero knowledge of Data Science, zero knowledge of R and zero knowledge of Cloud Computing. It highlights key areas of data security and cloud architecture needed as the application moved from concept, through to prototype and then final commercial delivery.
The R Shiny application was delivered on a Docker container running on AWS Elastic Container Services, secured with AWS Cognito authentication and a secure Virtual Private Cloud.
LOGISTICS
===========
1845: Zoom Waiting room will open
1900: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 2000
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking, Canon Medical and Effini.
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
The results in Table 1 don’t seem to correspond to those in Figure 2...
Description changed:
We're excited to bring you the first of a regular virtual meetup. We might not be able to give you pizza & drinks, but bring your own, settle down for a listen and we will bring you some excellent speakers.
We'll be using Zoom, and the details will be emailed to all attendees prior to the event, so make sure you've RSVP'd so we send them out to you.
We're delighted to say that Mine Çetinkaya-Rundel from the University of Edinburgh, who was due to speak for us in March, is going to help kick off these virtual events. She'll be speaking about workflows for reproducibility that touch on everything from data storage, cleaning, analysis, to communication of final results.
We're keeping the event a little shorter than usual, so no lightning talks - however... we would love to hear from you if you have a lightning talk you would like to give at a virtual event in a few weeks time, so get in touch with us.
MAIN TALK:
=====================
Bio: Mine is a Senior Lecturer in the School of Mathematics at University of Edinburgh and Data Scientist and Professional Educator at RStudio. Mine’s work focuses on innovation in statistics and data science pedagogy, with an emphasis on computing, reproducible research, student-centered learning, and open-source education as well as pedagogical approaches for enhancing retention of women and under-represented minorities in STEM. Mine works on integrating computation into the undergraduate statistics curriculum, using reproducible research methodologies and analysis of real and complex datasets. She is one of the organisers of R-Ladies Edinburgh
Description:
For data analysis to be reproducible, the data and code should be assembled in a way such that results (e.g. tables and figures) can be re-created. While the scientific community is by and large in agreement that reproducibility is a minimal standard by which data analyses should be evaluated, and a myriad of software tools for reproducible computing exist, it is still not trivial to reproduce someone’s (sometimes your own!) results without fiddling with unavailable analysis data, external dependencies, missing packages, out of date software, etc.
In this talk, we present good, better, and best workflows for reproducibility that touch on everything from data storage, cleaning, analysis, to communication of final results.
LOGISTICS
===========
1855: Zoom Waiting room will open
1900: Meetup will start - welcome & community announcements followed by our main speaker, and then Q&A
We'll aim to be finished by 2000
REMOTE MEETINGS
===================
Please remember the Code of Conduct applies to a remote meeting as well.
When you join the meeting, your microphone will be muted, and your camera switched on, we miss you all, it's nice to see you! Once the talk starts, feel free to switch your camera off.
We'll use the chat channel in Zoom to deal with any issues, and we'll advise on how we will run the Q&A at the start of the session.
SPONSORS
=============================
While we might not be making such full use of our sponsors as we normally do, we still appreciate all they do for us to allow us to run this group - so thanks to Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking and Canon Medical
CODE OF CONDUCT
====================
Though virtual, our Code of Conduct still applies to all attendees, organisers and speakers. Please take the time to read through if you haven't before, we really appreciate your help to maintain a welcoming and friendly PyData community.
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
The results in Table 1 don’t seem to correspond to those in Figure 2...
Description changed:
Welcome to the March PyData Edinburgh!
We're really looking forward to welcoming Mine Çetinkaya-Rundel from the University of Edinburgh to speak about workflows for reproducibility that touch on everything from data storage, cleaning, analysis, to communication of final results.
As always, we'll have a few lightning talks - though this month we have something a little different (you'll have to come along to find out what!) - plus pizza and refreshments and plenty of chat!
MAIN TALK:
=====================
Bio: Mine is a Senior Lecturer in the School of Mathematics at University of Edinburgh and Data Scientist and Professional Educator at RStudio. Mine’s work focuses on innovation in statistics and data science pedagogy, with an emphasis on computing, reproducible research, student-centered learning, and open-source education as well as pedagogical approaches for enhancing retention of women and under-represented minorities in STEM. Mine works on integrating computation into the undergraduate statistics curriculum, using reproducible research methodologies and analysis of real and complex datasets. She is one of the organisers of R-Ladies Edinburgh
Description:
For data analysis to be reproducible, the data and code should be assembled in a way such that results (e.g. tables and figures) can be re-created. While the scientific community is by and large in agreement that reproducibility is a minimal standard by which data analyses should be evaluated, and a myriad of software tools for reproducible computing exist, it is still not trivial to reproduce someone’s (sometimes your own!) results without fiddling with unavailable analysis data, external dependencies, missing packages, out of date software, etc.
In this talk, we present good, better, and best workflows for reproducibility that touch on everything from data storage, cleaning, analysis, to communication of final results.
LIGHTNING TALKS
========
We have an exciting set of Lightning Talks signed up, which this month
will include a few *slightly* longer ones for reasons that will be
revealed on the night!
LOGISTICS
===========
Please remember to RSVP to come to this event :)
1815: Doors open, drinks & networking
1845: Talks start - welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS
=============================
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas and for this event — Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking and Canon Medical
CODE OF CONDUCT
====================
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
Welcome to a new decade and and a new year of PyData Edinburgh!
We're delighted to kick off 2020 with graduate student, Hunter Gabbard, from Glasgow University, who is going to tell us about the data science of detecting and analysing gravity waves. We will also have lightning talks and community announcements, all accompanied by refreshments and followed by pizza.
Please RVSP if you can join us at Solar Winds Edinburgh office.
****************************************************************************
This may be your last chance to see Thomas Kober, who's sadly departing for Berlin, so you surely wouldn't want to miss giving him a proper PyData Edinburgh send-off!
****************************************************************************
MAIN TALK
After the groundbreaking discovery of gravitational waves in 2015, the Laser Interferometer Gravitational wave Observatory (LIGO) detectors have continued to see a steady stream of upgrades to their performance. As our gravitational wave detectors become more sensitive, rather than seeing a handful of signals per observation run we will see many hundreds of signals. Although the algorithms we use to extract the physical properties of detected signals are optimal, they are not fast enough to deal with the sheer deluge of gravitational wave data we expect to gather in the near future. Using a novel application of machine learning (conditional variational autoencoders) we show for the first time that we are able to achieve a level of 6–7 orders of magnitude speed-up in performance over existing techniques.
BIO
Hunter Gabbard is an astrophysicist and PhD Candidate at the University of Glasgow. After having completed his B.S. in Physics at the University of Mississippi, he was awarded a Fulbright Scholarship from the U.S. Department of State for research at the Max Planck Institute for Gravitational Physics in Hannover, Germany. In 2015, he was fortunate enough to have been on the Nobel Prize winning team (LIGO) which discovered gravitational waves. Over the course of his PhD Hunter has continued research in the now burgeoning field of gravitational-wave astronomy.
LIGHTNING TALKS
We still have a few spaces for some lightning talks this month — share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
Please RSVP to come to this event :)
1815: Doors open, drinks & networking
1845: Talks start — welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas and for this event — Cathcart Associates, Wood Mackenzie, Solar Winds, Lloyds Banking Group and Canon Medical
CODE OF CONDUCT
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
Picture credit: Dr Dennis Bogdan (original) and Yinweichen (SVG rendering)
License: Creative Commons CC BY-SA 3.0
https://creativecommons.org/licenses/by-sa/3.0/deed.en
Welcome to the final PyData Edinburgh event of the year - and the decade!
Please note we're having this event on the first TUESDAY night of December as there is another great event on the Thursday, so we wanted to go to both :)
But the rest is the same as always, we will have a main talk, our lightning talks, pizza &refreshments and great chat! We're back at Wood Mackenzie this time, and all christmas jumpers are very welcome if you need an excuse to give them their first outing of this year.
MAIN TALK:
=====================
Bio: Tim Squires is a Technical Architect, scout leader, pilot and sailor currently working with The Registers of Scotland. Tim has also been an aerial cameraman (drones) with the BBC and ITV. Tim first published code in 1979 in BEEBUG, the BBC Micro magazine and has not stopped programming since except to fly microlights and sail. Even then, he’s been writing software for drones and boat navigation.
Description:
The Space Plane project started as a scout project to encourage kids, especially girls, into engineering careers. It has now grown into an attempt to break a world record - The Highest Horizontal Flight by an Autonomous Fixed Wing Aircraft. Under the hood is a Python script which is responsible for launching and landing the aircraft. The Space Plane Project is sponsored by Equal Experts, a software consultancy network.
There will be drones - not sure if they'll be in their christmas woollies!
LIGHTNING TALKS
========
We still have a few spaces for some lightning talks this month - share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
===========
Please RSVP to come to this event :)
1815: Doors open, drinks & networking
1845: Talks start - welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS
=============================
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas and for this event — Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking and Canon Medical
CODE OF CONDUCT
====================
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
Welcome to our November PyData Edinburgh meetup! We're looking forward to hearing from someone who's a familiar face at our meetups, and as always we'll have our lightning talks, all followed by pizza and chat. This month we're delighted to be heading along to Lloyds - so remember we need your full name & and matching Photo ID for security.
MAIN TALK: Make any company an AI company!
PRESENTER: Greg Fousas
Greg is a data scientist with work experience that spans more than 20 projects, 15 brands, 5 industries and 5 countries and still counting! He studied Production Engineering and Management, he has a MSc in Operational Research from the University of Edinburgh and studied a bit of Cognitive Science. Recently he completed a self-driving car nanodegree. Greg also runs an amateur online Python course entitled “your 10 minutes of Python per day” and is happy to be able to call Scotland home.
DESCRIPTION
AI and Machine Learning have become must-haves for almost all industries and companies. H2O.ai's goal is to help companies all over the world to use Machine Learning.
H2O.ai's opensource toolset, which includes packages R, Python and Spark, starts from offering products which can accelerate the data preparation, then help with ML model building and finally make the deployment easier and platform agnostic!
LIGHTNING TALKS
Share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
Please note all attendees MUST sign up to the Meetup to be admitted.
1815: Doors open, drinks & networking
1845: Talks start - welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS & REFRESHMENTS
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas — Cathcart Associates (https://www.cathcartassociates.com), Solarwinds (https://www.solarwinds.com), Wood Mackenzie (https://www.woodmac.com), Lloyds Banking (https://www.lloydsbank.com) and Canon Medical (https://research.eu.medical.canon)
CODE OF CONDUCT
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
PHOTO CREDIT
Carlo "Granchius" Bonini (https://www.flickr.com/photos/granchius/)
Licence: CC BY-SA 2.0 (https://creativecommons.org/licenses/by-sa/2.0/).
On Flickr: https://flic.kr/p/5qvtA1
As the summer nights give way to the autumn we have another PyData Edinburgh to cheer you up.
Our main speaker in October is Edinburgh University's Benjamin Bach, a lecturer in Informatics who specializes in interactive information visualization interfaces. We will also have lightning talks and community announcements, all accompanied by refreshments and followed by pizza.
Please RVSP if you can join us at Solar Winds Edinburgh office.
MAIN TALK
This talk gives an overview of a few tools for data visualization, including visualization design and creation, exploratory data analysis, and creating communicative visualizations. The talk will discuss tools that require some programming (Python(!), D3) and others that are usable out of the box (rawgraphs, vistorian, tableau), and will cover both tools for general purpose charts amd tools for specific kinds of data such as networks.
BIO
Benjamin is a Lecturer (Assistant Prof.) in Design Informatics and Visualization at the University of Edinburgh. His research designs and investigates interactive information visualization interfaces to help people explore, communicate, and understand data across media such as screens, mixed reality, paper, and physicalizations.
http://benjbach.me
LIGHTNING TALKS
We still have a few spaces for some lightning talks this month - share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
Please RSVP to come to this event :)
1815: Doors open, drinks & networking
1845: Talks start — welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas and for this event — Cathcart Associates, Wood Mackenzie, Solar Winds, Lloyds Banking Group and Canon Medical
CODE OF CONDUCT
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
Welcome to the September PyData Edinburgh event, we are back after our wee summer break!
As always, we will have a main talk, our lightning talks, pizza &refreshments and great chat! This time we are at Wood Mackenzie so come along for a great night.
MAIN TALK
=====================
Bio: Roman Popat is a former biologist turned data scientist. He works freelance helping customers from all industries to grab new opportunities with data driven products. His latest adventure is with a product on the interface of consumer retail and finance. Roman is a former Data Lab employee and has a PhD in microbiology. His weapons of choice are R and Python.
Description:
The traditional workflow for providing ML outputs to a mobile application would be to send data to the cloud, execute the inferences and then send back the predictions. With growing concerns over data governance there are good reasons for this to change. I will outline my experience with current tools designed to allow execution of the model inferences on the device without the need to share any data over the network. This is not a full overview of the technologies, just a postcard from my corner of the industry with some insights and learning from my experience, oh and the models are with SciKit Learn of course. 🙂
LIGHTNING TALKS
========
We still have a few spaces for some lightning talks this month - share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
===========
Please RSVP to come to this event :)
1815: Doors open, drinks & networking
1845: Talks start - welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS
=============================
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas and for this event — Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking and Canon Medical
CODE OF CONDUCT
====================
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
Machine learning-based upper-limb prosthesis control
Description changed:
Welcome to the July PyData Edinburgh event!
As usual, we will have a main talk, our lightning talks, pizza & refreshments and great chat! This month we're delighted to welcome Agamemnon Krasoulis, from Newcastle University's Intelligent Sensing Lab, as our main speaker.
Please RVSP if you can join us at Solar Winds Edinburgh office.
MAIN TALK
In the Intelligent Sensing Lab, our research is motivated by the potential of prosthetics to restore function to individuals with sensorimotor deficit, by transforming thought into action and sensation into perception. In this talk, I will talk about our work in translating biological signals, for example, recordings of muscular activity, into control actions for the motors of hand prostheses. I will present current challenges in translating research advances into clinical products and how we aim to leverage machine learning (and Python of course!) to overcome them. Finally, I will give a real-time demonstration of our research using a state-of-the-art prosthetic hand and muscle control.
BIO
Agamemnon Krasoulis is as a Research Associate in the Intelligent Sensing Lab of the School of Engineering, Newcastle University. Prior to that, he obtained a PhD and MRes in Informatics at the University of Edinburgh. His research interests lie in the intersection of machine learning and biomedical engineering. His current focus is on the development and deployment of control algorithms for upper-limb prostheses. He has carried out research in the fields of prosthetics, brain-machine interfaces for motor rehabilitation and cochlear implants.
LIGHTNING TALKS
We still have a few spaces for some lightning talks this month - share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
Please RSVP to come to this event :)
1815: Doors open, drinks & networking
1845: Talks start — welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas and for this event — Cathcart Associates, Wood Mackenzie, Solar Winds, Lloyds Banking Group and Canon Medical
CODE OF CONDUCT
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
Welcome to the June PyData Edinburgh event!
As always, we will have a main talk, our lightning talks, pizza &refreshments and great chat! We're really pleased that this month we have a speaker from one of our sponsors, Maciej Pajak from Canon.
Please RVSP if you can join us - and our lovely hosts this time are Wood Mackenzie.
MAIN TALK
=====================
Bio:
Maciej works as an AI Scientist at Canon Medical Research Europe, developing machine learning solutions in healthcare. He has a PhD in Informatics from Edinburgh University and his previous experience spans Computer Science, Psychology, and Bioinformatics.
Description:
"At Canon we work with a wide variety of medical data and a whole range of machine learning tasks (and we use Python for that!). In this talk I will give you an insight into our exciting work, and how we approach challenges specific to data science & machine learning in the medical domain.
But we need to deal with universal challenges of data science too, here I will focus on measuring model's performance, which I believe many of you can relate to. We all use quantitative metrics to keep track of where we are in our algorithm development, summarise our progress, and provide evidence to the clients that our models are worth spending money on. Of course, you want the metric to be informative, relevant to the use case, understandable by the stakeholders, and well, you don't want it to make your model look weak... Then, another question is - how much can you steer development of a model towards optimising a particular metric? And should you? I aim to run through a selection of practical examples and share a few personal reflections."
LIGHTNING TALKS
========
We still have a few spaces for some lightning talks this month - share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
===========
Please RSVP to come to this event :)
1815: Doors open, drinks & networking
1845: Talks start - welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS
=============================
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas and for this event — Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking and Canon Medical
CODE OF CONDUCT
====================
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
We will be at Lloyds this time, so remember to bring an ID.
TALK DETAILS
=============
Object Detection using TensorFlow
---------------------------------------------------------------
Presenter: Martina Pugliese
Martina works as Data Science Lead at Mallzee. Both in her work and outside she loves to investigate phenomena from data, producing results in terms of models and visualisations. She studied Physics and has done some research in Evolutionary Linguistics so if you start chatting about language to her you'll find she'll never stop.
Description:
Object detection is the area of Machine Learning that deals with teaching a machine to recognise both what is in an image and where in the image a given object is. It is a fascinating task that can be tackled via Deep Learning and is getting more and more ubiquitous in our everyday life due to several major developments in research and applications.
This talk will go through a brief chronology of the field and will walk you through the milestones that made this task very popular these days. There will be a few tools shown that tackle the problem, from Haar Cascades with OpenCV, the YOLO network, and eventually various neural network models you can implement with TensorFlow. Specifically, the latter will be given a bit of depth to demonstrate how an object detection job can be configured and launched using its API. Along the way, there'll be brief overviews of deep learning and some of its main concepts as well as an introduction to TensorFlow as a general Machine Learning framework.
LIGHTNING TALKS
==================
Share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
===========
Please note all attendees MUST sign up to the Meetup to be admitted.
1815: Doors open, drinks & networking
1845: Talks start - welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS & REFRESHMENTS
=============================
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas — Cathcart Associates (https://www.cathcartassociates.com), Solarwinds (https://www.solarwinds.com), Wood Mackenzie (https://www.woodmac.com), Lloyds Banking (https://www.lloydsbank.com) and Canon Medical (https://research.eu.medical.canon)
CODE OF CONDUCT
====================
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
We're delighted to be back at SolarWinds again (remember, to avoid ending up in the parking lot, don't use sat nav, follow the instructions on our address 😆).
We'll have our regular update on the PyData community, lightning talks and we're delighted to have Sabine Weber from the Institute for Language, Cognition and Computation at University of Edinburgh as our main speaker.
We look forward to seeing you there — doors open at 1815, make sure you've clicked attend to reserve your place!
TALK DETAILS
=============
Show not tell: Teaching machines entailment
---------------------------------------------------------------
Presenter: Sabine Weber
Sabine Weber is a second year PhD student at the Institute for Language, Cognition and Computation at the University of Edinburgh. She works on semantics and specifically on detecting and aligning entailment in English and German. She has a background in both Linguistics and Computer Science.
Description:
Detecting entailment and reasoning with it is one of the tasks that humans solve with ease, but that computers struggle with. If we hear that our Aunt Mary arrived in London, we know that she is in London at this very moment. But how can we teach knowledge like this to a machine without writing down thousands of rules by hand? In this talk I will present a method to mine entailment relations between verbs from a large collection of news text in German and English and show some possible applications for the resulting multilingual entailment graphs.
LIGHTNING TALKS
==================
Share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
If you want to give a lightning talk at this event, send us a message either here on Meetup, through Twitter @PyDataEdinburgh or any other way you know how to find us!
Just 5 minutes, still informal, no need for slides unless you want them — go on, give it a go!
LOGISTICS
===========
Please note all attendees MUST sign up to the Meetup to be admitted.
1815: Doors open, drinks & networking
1845: Talks start - welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS & REFRESHMENTS
=============================
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas — Cathcart Associates (https://www.cathcartassociates.com), Solarwinds (https://www.solarwinds.com), Wood Mackenzie (https://www.woodmac.com), Lloyds Banking (https://www.lloydsbank.com) and Canon Medical (https://research.eu.medical.canon)
CODE OF CONDUCT
====================
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
Big data, machine learning and maps: lessons learned on aerial imagery.
Description changed:
Welcome to the March PyData Edinburgh event! As always, we will have a main talk, a few lightnings, pizza and beer and good chats! Please RVSP and join along. This month our lovely hosts are Wood Mackenzie.
MAIN TALK
=====================
Bio: Olivia Wilson is a Research Scientist at Ordnance Survey. She specialises in scale within machine learning applied to the investigation of aerial imagery. Her daytime job is managing the python code repository used to train neural networks on aerial images. She holds an MSc in Computer Science with distinction.
Description: Meet Ordnance Survey (OS), the national mapping agency of Great Britain with a wealth of data going back centuries, and now looking forward into the geospatial age. Most people know us for our paper map products of popular walking and hiking destinations, but the main resource we have is from digital data such as MasterMap – the most detailed topographic map of Great Britain.
But where does Python come into all this, you ask? In many areas across the business Python is a key language, particularly within our data science and research teams. We use python in our deep learning research using python libraries such as keras, tensorflow and quiver. So come and find out more about our investigation of models trained on aerial imagery.
LIGHTNING TALKS
========
We have an exciting set of Lightning Talks signed up, which this month
will include a few *slightly* longer ones for reasons that will be
revealed on the night! It’s gonna be amazing!
LOGISTICS
===========
Please sign up to come to the event :)
1815: Doors open, drinks & networking
1845: Talks start - welcome & community announcements followed by our main speaker, then lightning talks.
We'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS
=============================
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas and for this event — Cathcart Associates, Wood Mackenzie, Solarwinds, Lloyds Banking and Canon Medical
CODE OF CONDUCT
====================
The PyData Code of Conduct (https://pydata.org/code-of-conduct/) governs this meetup. To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact the local group organizers (message us on the meetup page). Please also submit a report of any potential Code of Conduct violation directly to NumFOCUS using the link found at https://numfocus.org/code-of-conduct.
Thank you for helping us to maintain a welcoming and friendly PyData community!
Expired changed:Not ExpiredEdited at by Sarah Lister