Toronto Data Workshop

A weekly hour-long discussion where industry and academic participants collectively consider, collate, share, and disseminate best practices in the critical initial data-centric steps in any data science project. Thursdays at 4-5pm (Toronto time) via Zoom. All welcome! Sign up here.

17 November 2020: If you would like to participate in the Toronto Data Workshop on Reproducibility (25/26 February 2021) then please see here.

Thanks to Hidaya Ismail for the brilliant maple leaf and dinosaur hex stickers.

Overview

Since Fall 2019, the Toronto Data Workshop (TDW) has brought together researchers from various academic disciplines as well as industry to collectively consider, collate, share, and disseminate best practices in the critical initial data-centric steps of any data science project: collection; cleaning; storage; retrieval; dissemination; and protection. We meet weekly for an hour and aim to have a roughly even split of participants from academia and industry over the course of each term.

We meet on Thursdays at 4-5pm (Toronto time) via Zoom. For an invitation please sign up here. Anyone is welcome to attend - you don’t need to be affiliated with the university. We start at 4:01 with a brief welcome and then three minutes of break-out rooms to meet some of the other participants. At 4:05 we return to the main room and the speaker is introduced. Speakers typically speak for 20-45 minutes, during which participants are encouraged to add comments and questions to the chat, rather than verbally interrupting. We then have a chaired question period, in which those with questions are asked to signal this in the chat, at which point they’ll be called on to introduce themselves and ask their question.

The current organising committee is: Faria Khandaker, Kelly Lyons, and Rohan Alexander. The TDW is a joint initiative between the Faculty of Information and the Department of Statistical Sciences at the University of Toronto and we especially thank Dean Wendy Duff and Chair Radu Craiu for their support.

Fall 2020 speakers

Date (Toronto time)	Speaker	Topic
Thu, 3 Sep, 4-5pm	Erik Drysdale (The Hospital for Sick Children)	Using hospital data
Tue, 8 Sep, 3:30-4:30pm	Sophie Bennett (Industry data scientist)	UK A levels algorithm issues (jointly hosted with SRI)
Thu, 10 Sep, 4-5pm	A Mahfouz, Diego Mamanche Castellanos, Hidaya Ismail, Ke-Li Chiu & Paul Hodgetts (University of Toronto)	Various R packages and research developed by students
Thu, 17 Sep, 4-5pm	Amber Simpson (Queen’s University)	Cancer and AI
Thu, 24 Sep, 4-5pm	Chelsea Parlett-Pelleriti (Chapman University)	Talking to non-statisticians about statistics
Thu, 1 Oct, 4-5pm	Florence Vallée-Dubois (Université de Montréal)	Canadian demographics by riding (1991-2015)
Thu, 8 Oct, 4-5pm	Yim Register (University of Washington Data Lab)	Self-advocacy within machine learning systems
Thu, 22 Oct, 4-5pm	Jeff Waldman, Leanne Trimble, Leslie Barnes, & Lisa Strug (University of Toronto)	Panel on data-focused resources at U of T
Thu, 29 Oct, 4-5pm	Fei Chiang (McMaster University)	Data currency and applications
Thu, 5 Nov, 4-5pm	Andrew Whitby (Industry data scientist)	Censuses
Mon, 9 Nov, 4-5pm	Tom Cardoso (Globe and Mail)	Bias Behind Bars
Thu, 12 Nov, 4-5pm	Kevin Armstrong (University of Toronto)	Measuring poverty for NGOs
Thu, 19 Nov, 4-5pm	Michael Chong (University of Toronto)	High-throughput Bayesian modelling workflow
Thu, 26 Nov, 4-5pm	Postponed
Thu, 3 Dec, 10-11am	Jenny Cresswell (World Health Organization)	Underreporting and misclassification in maternal mortality data
Thu, 10 Dec, 4-5pm	Shabrina Mardevi (United Nations Population Fund & University of Toronto) & Romesh Silva (United Nations Population Fund)	Population data estimation
Thu, 17 Dec, 4-5pm	Liza Bolton (University of Toronto), Maria Tackett (Duke University), Nathalie Moon (University of Toronto), Teon Brooks (Mozilla Firefox)	Panel on teaching data-focused topics

• Thursday, 3 September 2020, 4-5pm
  Special guests Dean Wendy Duff (Faculty of Information) and Department Chair Radu Craiu (Department of Statistical Sciences).
  Erik Drysdale (The Hospital for Sick Children)
  Erik works as a Machine Learning Specialist at the Hospital for Sick Children (SickKids) for the Goldenberg Lab and AI in Medicine (AIM) initiative. His professional responsibilities include the development and training of the machine learning models for various pediatric data science projects. His research interests are focused on the intersection of statistics and machine learning methods such as high-dimensional inference, survival analysis, and optimization methods. Erik will talk about the challenges of applying ML in hospital data and why statistics still matters in ML.
• Tuesday, 8 September 2020, 3:30-4:30pm
  Jointly hosted with Gillian Hadfield and the Schwartz Reisman Institute for Technology and Society.
  Sophie Bennett (Industry data scientist)
  Sophie Bennett holds an undergraduate degree in Experimental Psychology from the University of Oxford and a PhD in Neuroscience from King’s College. She is the lead data scientist at Up Learn, a London-based online learning platform specialising in A levels. In this role, she conducts evaluations of course effectiveness and uses data to improve instruction and curriculum design. She is passionate about increasing the use of responsible evidence and statistics to guide social policy, and, in her spare time, enjoys working with publicly available datasets to explore London demographics, social issues and infrastructure. Sophie will discuss A Levels, Ofqual and algorithms.
  
• Thursday, 10 September 2020, 4-5pm
  Toronto Data Lab launch event.
  A Mahfouz (University of Toronto)
  Diego Mamanche Castellanos (University of Toronto)
  Hidaya Ismail (University of Toronto)
  Ke-Li Chiu (University of Toronto)
  Paul Hodgetts (University of Toronto)
  Various Toronto Data Lab projects will be presented including arxivdl, aRianna, cesR, and more!
• Thursday, 17 September 2020, 4-5pm
  Amber Simpson (Queen’s University)
  Dr. Simpson is the Canada Research Chair in Biomedical Computing and Informatics and Associate Professor in the School of Computing (Faculty of Arts and Science) and Department of Biomedical and Molecular Sciences (Faculty of Health Sciences). She specializes in biomedical data science and computer-aided surgery. Her research group is focused on developing novel computational strategies for improving human health. Dr Simpson will discuss cancer and AI.
  
• Thursday, 24 September 2020, 4-5pm
  Chelsea Parlett-Pelleriti (Chapman University)
  Chelsea is a PhD candidate and full-time instructional faculty at Chapman University where her research focuses on using novel statistical and Machine Learning methods (mostly Bayesian statistics, IRT models, and clustering) to behavioral data. As an instructor she teaches Python, R and Data Science, and loves using novel technology (like TikTok, Twitch, and flipped classes) to better engage and inspire students. Chelsea will discuss talking to non-DS team members about DS topics.
• Thursday, 1 October 2020, 4-5pm
  Florence Vallée-Dubois (Université de Montréal)
  Florence Vallée-Dubois is a Ph.D. candidate at the department of political science of the University of Montreal. She is also a member of the Centre for the Study of Democratic Citizenship and Canada Research Chair in Electoral Democracy. Her research interests focus on Quebec and Canadian politics, political behaviour and quantitative methods. Her doctoral project focuses on the political behaviour and democratic representation of seniors in Canada. Florence will discuss Canadian Demographics by Electoral Riding (1991-2015).
• Thursday, 8 October 2020, 4-5pm
  Yim Register (University of Washington Data Lab)
  Yim Register (they/them) is a radical optimist, child advocate, and PhD student at the University of Washington Data Lab exploring what self-advocacy looks like within machine learning systems. They study how empowering novices with Data Science knowledge can impact their participation and joy in an AI-driven world! Their passion project right now is writing a book called Life Lessons from Algorithms, a book that teaches how machine learning algorithms work through trauma recovery skills. Yim will discuss self-advocacy within machine learning systems.
• Thursday, 22 October 2020, 4-5pm
  Panel discussion on data-focused resources at the University of Toronto.
  Jeff Waldman (University of Toronto)
  Leanne Trimble (University of Toronto)
  Leslie Barnes (University of Toronto)
  Lisa Strug (University of Toronto)
  Jeff Waldman is the Manager, Institutional Data Governance; Leslie Barnes is the Digital Scholarship Librarian at UTL; Leanne Trimble is the Data and Statistics Librarian at UTL; Lisa Strug is a Senior Scientist in the Program of Genetics and Genome Biology, Associate Director of The Centre for Applied Genomics, Professor of Statistical Sciences and Biostatistics at the University of Toronto, and Director of CANSSI Ontario.
• Thursday, 29 October 2020, 4-5pm
  Fei Chiang (McMaster University)
  Fei Chiang is an Associate Professor in the Department of Computing and Software (Faculty of Engineering), the Director of the Data Science Research Group, and a Faculty Fellow at the IBM Centre for Advanced Studies. She served as an inaugural Associate Director of the MacData Institute. Her research interests and industrial experience is in data management, spanning data cleaning, data quality, data privacy, data fusion, and database systems. Professor Chiang will discuss data currency and its applications.
• Thursday, 5 November 2020, 4-5pm
  Andrew Whitby (Industry data scientist)
  Andrew is a data scientist and economist currently looking for his next challenge. He is particularly interested in the economics of technology, creativity, innovation and growth. He wrote The Sum of the People: How the Census Has Shaped Nations from the Ancient World to the Modern Age which was published in March 2020. Previously, he worked as a Data Scientist at the World Bank, and at Nesta, the UK’s innovation think tank. His academic background combines economics, statistics and computer science. He completed his doctoral research in the Department of Economics at the University of Oxford. Andrew will discuss censuses.
  
• Monday, 9 November 2020, 4-5pm
  Tom Cardoso (Globe and Mail)
  Tom Cardoso is a crime and justice reporter and data journalist for The Globe and Mail. Tom will discuss his Bias Behind Bars series of articles which show Black and Indigenous inmates in Canada are more likely to get worse scores than white inmates, based solely on their race.
  
• Thursday, 12 November 2020, 4-5pm
  Kevin Armstrong (University of Toronto)
  Kevin Armstrong is a Masters of Information student at the University of Toronto, and a data consultant for ‘Women’s Integrated Sexual Health’ (WISH) - a three-year program delivering integrated health care in 16 countries in Africa and South Asia. Kevin will discuss methods for measuring poverty and use cases for NGOs.
• Thursday, 19 November 2020, 4-5pm
  Michael Chong (University of Toronto)
  Michael is a PhD student in the Department of Statistical Sciences at the University of Toronto building models for demographic estimation. Previously, he completed his BSc in Integrated Science at McMaster University. Michael will discuss lessons from a high-throughput Bayesian modelling workflow
• Thursday, 26 November 2020, 4-5pm
  Postponed
• Thursday, 3 December 2020, 10-11am
  Jenny Cresswell (World Health Organization)
  Jenny Cresswell is in the measurement & monitoring team in the Department of Sexual and Reproductive Health & Research at the World Health Organization. She leads a portfolio of work on maternal mortality and morbidity, and the development of indicators for global and national reproductive health monitoring. Part of this portfolio involves providing technical support to Member States in strengthening their maternal mortality data collection and reporting. Previously, Jenny training in epidemiology and demography, and was an Assistant Professor at the London School of Hygiene & Tropical Medicine, UK. Jenny will discuss underreporting and misclassification in maternal mortality data.
• Thursday, 10 December 2020, 4-5pm
  Shabrina Mardevi (United Nations Population Fund and University of Toronto)
  Romesh Silva (United Nations Population Fund)
  Shabrina is a Masters of Information student at the University of Toronto and a Population Data Estimation and Analysis Intern at the United Nations Population Fund. Romesh holds a PhD in Demography from the University of California, Berkeley, and is a Technical Specialist, Health & Social Inequalities, at the United Nations Population Fund.
  
• Thursday, 17 December 2020, 4-5pm
  Panel discussion on teaching data-focused topics.
  Liza Bolton (University of Toronto)
  Maria Tackett (Duke University)
  Nathalie Moon (University of Toronto)
  Teon Brooks (Mozilla Firefox)
  Liza Bolton is an Assistant Professor, Teaching Stream, at the University of Toronto. Maria Tackett is an Assistant Professor of the Practice in the Department of Statistical Science at Duke University. Nathalie Moon is an Assistant Professor, Teaching Stream, University of Toronto. Teon L. Brooks, holds a PhD in experimental psychology from NYU, and now works as a data scientist for Mozilla Firefox. He also serves as the technical advisor and President of BrainWaves, an NIH-funded project to teach experimentation and cognitive neuroscience to high school students in NYC, and has co-founded Computation in Education Labs (CIEL), a nonprofit that aims to further the mission of the BrainWaves project while focusing on data science and computational thinking.

Summer 2020 speakers

• Thursday, 21 May 2020, 4-5pm
  Rohan Alexander (University of Toronto, Information)
  Rohan is a post-doctoral fellow at the Faculty of Information, University of Toronto. He holds a PhD in Economics from the Australian National University. He will talk about getting data from PDFs into R, with an application to the Kenyan census.
• Thursday, 28 May 2020, 4-5pm
  Shiro Kuriwaki (Harvard University, Government)
  Shiro is a Ph.D. Candidate at the Department of Government, Harvard University. His research focuses on democratic representation in American Politics, for instance cast vote records, public opinion, survey methods, and applied statistics more generally. Shiro will bring together best practices for organizing data and code in the social sciences that experts have proposed with some of his own experience. He will propose a project-oriented workflow that adopts a minimal and consistent file organization structure within a single project, using RStudio Projects and GitHub. He will then discuss how to organize multiple projects that share common components, and propose the use of custom R packages to share code and Dataverse to share large datasets. He will use some of his own projects involving the Cooperative Congressional Election Study (CCES), one of the largest political surveys of American Politics, as a demonstration.
  Recording available here.
• Thursday, 4 June 2020, 4-5pm
  Marija Pejcinovska (University of Toronto, Statistical Sciences)
  Marija is a second-year Ph.D. student in Statistics at the University of Toronto. Her research interests are in applied statistics, specifically the application of Bayesian methods to data and modeling challenges that arise in demography, public health, and certain areas of the social sciences. Marija will talk about a current project with the World Health Organization (WHO) focused on estimating global maternal mortality to share her R workflow and the different tools and packages she’s found helpful in the data processing stage. More specifically, she’ll be sharing a few ways of dealing with text and date data in R.
• Thursday, 11 June 2020, 4-5pm
  Harrison Jones (Deloitte)
  Harrison is a Manager at Deloitte in Toronto, where he focuses on data analytics and machine learning in the property & casualty insurance, life insurance, health insurance, pensions, and the public sector. Harrison will talk about using R with actuarial data.
• Thursday, 18 June 2020
  Cancelled in support of the Black Lives Matter movement and to provide an opportunity for reflection and learning. We also announced stipends in support of University of Toronto students or recent graduates who identify as a member of a visible minority group, racialized group, or as a person of colour.
• Thursday, 25 June 2020, 4-5pm
  A Mahfouz (University of Toronto, Information)
  A is a Master of Information student at the University of Toronto with a background in geography. Their prior work has been largely concerned with data pipelines. A will talk about geographic data cleaning, extracting mappable data from Google Directions API results in Python.
  Slides available here.
• Thursday, 2 July 2020, 4-5pm
  Heather McBrien (University of Toronto, Statistical Sciences)
  Heather just graduated from the Statistics BSc program at the University of Toronto, and is interested in modelling in population health research, particularly using novel data sources to answer questions where traditional data is lacking. Heather will talk about how the data that we collect can bias the results that we obtain and our knowledge of the problem.
  Slides available here.
• Thursday, 9 July 2020, 4-5pm
  Roxanne Chui (University of Toronto, Information)
  Roxanne is an emerging anthropological data science professional. She did her BSc program in Forensic anthropology and worked in the pharmaceutical industry before doing her Masters in data science. She is passionate about excavating context from data for predicting future patterns of human behaviour. Roxanne will talk about an EDA approach to Tokyo AirBnB datasets and pattern discovery in listing prices using R - ‘What do we have here among millions of observations?’
  Slides available here.
• Thursday, 16 July 2020, 4-5pm
  Casey Breen (University of California, Berkeley, Demography)
  Casey is a PhD student in the Demography Department at Berkeley. He previously worked at the Institute for Social Research and Data Innovation, home of IPUMS. Casey will talk about CenSoc, which is a project to link 1940 Census data with Social Security Administration mortality records in the US.
• Thursday, 23 July 2020, 11am-noon
  Marta Kołczyńska (Institute of Political Studies of the Polish Academy of Sciences)
  Marta is an Assistant Professor at the Institute of Political Studies of the Polish Academy of Sciences and a visiting researcher in the Probabilistic Machine Learning Group, Department of Computer Science, Aalto University. Her research interests include comparative analyses of political attitudes and behavior across nations and over time, as well as the methodology of comparative research, in particular cross-national surveys. Marta will talk about cleaning survey data, in particular a project in which she gathers political trust items from different cross-national survey datasets to model time trends, and the tools she has developed to facilitate this work.
• Thursday, 30 July 2020, 4-5pm
  Alex Luscombe (University of Toronto, Criminology and Sociolegal Studies)
  Alexander McClelland (Carleton University, Criminology and Criminal Justice)
  Alex Luscombe is a PhD student in the Centre for Criminology & Sociolegal Studies at the University of Toronto and a Junior Fellow at Massey College. Alexander McClelland is an Assistant Professor at the Institute of Criminology and Criminal Justice, Carleton University. They will talk about Policing the Pandemic, which is a project that was launched on 4 April, 2020, to track and visualize the massive and extraordinary expansions of police power in response to the COVID-19 Pandemic and the unequal patterns of enforcement that may arise as a result.
  Slides available here.
• Thursday, 6 August 2020, 4-5pm
  Sharla Gelfand (Freelance R Developer)
  Sharla is a freelance R developer specializing in enabling easy access to data and replacing manual, redundant processes with ones that are automated, reproducible, and repeatable. They will talk about creativity in R. Slides available here.
• Thursday, 13 August 2020, 4-5pm
  Richard Iannone (R Studio)
  Rich is a Software Engineer at R Studio. Rich will talk about pointblank, which is an R package that allows workflows involving nice and easy data validation in reproducible documents.
• Thursday, 20 August 2020, 4-5pm
  Aije Egwaikhide (IBM)
  Aije Egwaikhide holds an undergraduate degree in Economics and Statistics from the University of Manitoba, and a post-graduate degree in Business Analytics from St. Lawrence College, Kingston. She works at IBM where she is a Lead Data Scientist on the System Enablement group. Aije will talk about preparing data for optical character recognition (OCR).

Winter 2020 speakers

• Noon, Friday, 24 January 2020
  Steven Pimentel (U of T, business intelligence)
• Noon, Friday, 31 January 2020
  Arik Senderovich (U of T, Information)
  
• Noon, Friday, 7 February 2020
  Kathy Chung (U of T, Records of Early English Drama)
• Noon, Friday, 14 February 2020
  Josh Harris (KOHO)
• Noon, Friday, 28 February 2020
  Eugene Joh (St. Michael’s Hospital)
• Noon, Friday, 6 March 2020
  Fatemeh Nargesian (University of Rochester, Computer Science)

Fall 2019 speakers

• Noon, Thursday, 26 September 2019
  Periklis Andritsos (ODAIA & U of T, Information)
  
• Noon, Thursday, 10 October 2019
  Hassan Teimoori (Deloitte, Omnia AI)
  Ludovic Rheault (U of T, Political Science)
• Noon, Wednesday, 16 October 2019
  Lauren Kennedy (Columbia University)
  
• Noon, Thursday, 24 October 2019
  Sharla Gelfand (Freelance R and Shiny developer)
  
• Noon, Thursday, 7 November 2019
  Maria D’Angelo (Delphia)
  Hareem Naveed (Munich Re)
  
• Noon, Thursday, 21 November 2019
  Michelle Alexopoulos (U of T, Economics)
  Paraskevi Massara (U of T, Medicine)

If you would like to receive invitations to the series, then you can subscribe here.