Locke Data Talks

Locke Data helps organisations get started with data science. Increase your skills and stay up to date by catching up on our presentations.

Search
categories

Ethical Data Science: Tools and Practices

  • September 21, 2018
Let’s talk ethics Abstract We want to do no harm but sometimes our models have unintended consequences. Come learn about some of the ethical challenges we as data scientists may face, how we can put checklists and frameworks around ourselves to help ensure we don’t do unethical things accidentally, and what tools we can use to check our models for issues. Slides View the presentation full screen or view it below. Read More

Hands-on intro to SQL and R

  • September 3, 2018
SQL is an important skill for everyone! Abstract Learn SQL from the comfort of RStudio in this 2.5 hour hands-on workshop. Using SQLite as our database of choice, we’ll learn the fundamentals of good data structures, querying single datasets, and combining multiple datasets for getting answers from across your database. Bring your laptop with RStudio and we’ll send more info closer to the date on packages to install. Slides View the presentation full screen or view it below. Read More

Data Science Fundamentals

  • September 1, 2018
Get an overview about data science. Abstract Data scientists know the “magic” of making accurate predictions over time. Magic is just sufficiently advanced technology, and most of a data scientist’s magic is a good process, a robust understanding of data, and the ability to sensibly apply some recipes. Let’s go behind the curtains and see the process and the fundamentals employed in making any prediction. Learn enough to start adding magic to your own work. Read More

Shipping Data Science Products with R and Docker

  • August 13, 2018
How do we get our R code into production more quickly? Abstract There’s no point being a data scientist if your work never makes it to production. This session explores a solution for getting your code live, scalable, and easily managed. Covering models, dashboards, and other products built in R, you’ll look at how Docker containers can make managing dependencies a breeze, allow your code to be hosted anywhere, and have it work in high-scale systems. Read More

Anchor Modelling - agile databases

  • August 10, 2018
Yes, there’s normal forms beyond third, and yes they can be really useful! Abstract Anchor Modelling is a fantastic database modelling paradigm that uses sixth normal form (6NF) to store data and provides third normal form (3NF) views for ease of use. This session deep dives into all the concepts behind Anchor Modelling (and indeed databases generally!) and then takes you through how Anchor Modelling uses these concepts to move away from the traditional data warehouse paradigm to deliver a purely additive, agile database. Read More

Statistics 101

  • August 9, 2018
Take a visual, intuitive tour through some important concepts of statistics. Abstract We can be better at our jobs if we have a good grasp of basic statistics. It doesn’t matter if you’re a DBA looking to understand query plan performance, a data warehouse person needing to come up with ETL load time estimates, or an analyst needing to report figures to managers. Statistics can help you all. If only maths classes hadn’t been so darn boring! Read More

R for Developers

  • July 19, 2018
Learn about R from a developer perspective. Abstract Whether you’re interested in picking up another language, or you need to understand what those new data scientists have written and how you go about implementing their crazy new algorithms in your front-end, this session will take you through the R fundamentals, drawing comparisons against other languages, and give you a load of tips to make getting started easier. Slides View the presentation full screen or view it below. Read More

Git in 5 minutes

  • June 23, 2018
Learn about source control – it’ll save your bacon! Abstract Git can seem scary but once you know a few key terms it’s pretty easy day to day. This lightning talk helps fasttrack you through the basics. Slides View the presentation full screen or view it below. Hit the Space bar to navigate through the slides. Presentation history July 27th, 2016 - SQL Guerilla talks June 23rd, 2018 - satRdays Cardiff Read More

Tidy Data Science

  • June 23, 2018
Cut the lines of code you need to build awesome stuff. Going from getting data to deploying a model in three hours, you’ll get hands-on with the cutting-edge tidyverse packages that can at least halve the code you need to write! Notebooks Clone these notebooks to tackle the exercises or just browse them to learn! Presentation history June 23rd, 2018 - satRdays Cardiff Read More

From Excel to R

  • June 21, 2018
Welcome to this training space for journalists looking to see if R can be of use in the day job. Learn about the fundamentals of working with key formats in R. manipulating the data, and visualising it. Notebooks Clone these notebooks to tackle the exercises or just browse them to learn! Presentation history June 21st, 2018 - European Data and Computational Journalism Conference Read More

R for Reporting

  • June 9, 2018
What does it take to use R for reporting? Abstract Urgh! There’s data science, machine learning, artificial intelligence, and tons of buzz words flying around that make R & Python sound like you need a big fat budget to hire a bevvy of boffins and racks of servers. This isn’t the case. R is actually a really nice, practical language that you can use to do ETL and reporting. You can do it for free and you don’t even need a Coursera course in stats to be able to use it. Read More

Coping with x2,000 data volumes growth

  • June 5, 2018
Experience my pain as I try to build an Azure Data Platform that scales. Abstract I worked in a startup and our volumes started small, really small. I was the data scientist but I needed to actually build a data platform first. By the end of 6 months, daily volumes were 2,000 times the size. This talk takes you through my 6 months of learning how to build a high-scale data platform whilst requirements, scale, and technology were all changing. Read More

Intro to R

  • May 24, 2018
Learn the fundamentals of R. Abstract R, the statistical programming language, is another open-source program making inroads into the Microsoft world. R was originally for doing stats, but it now does database CRUD, reporting, documentation, and even websites. It can be awkward to know where to start, so this session fast tracks you to the sections you need to know about to save yourself pains you didn’t even know you had. Read More

Modern R for data science

  • May 24, 2018
What are the cutting edge R packages that’ll make doing data science a breeze? Abstract R’s pace of change has been increasing and even the caret package is being supplanted by newer, easier to use packages. In this session, I’ll walk you through what the latest workflows for data science can look like from getting data to deploying models. Slides View the presentation full screen or view it below. Read More

Solving Power BI painpoints with R

  • May 22, 2018
Power BI is pretty nifty but it has some areas that R can help make easier. Abstract This session will look at how PowerBI dashboard developers can use R to solve data import and data visualisation challenges. By the end of this session, you’ll know how you can use R to connect to more data sources, do sophisticated data transformation easily, avoid spatial data point limitations, and build custom graphics. Read More

Using Microsoft ML Server for data science

  • May 18, 2018
Explore one of Microsoft’s data science products to see if it’s useful for you. Abstract Microsoft’s ML Server can help you overcome in-memory restrictions of R and allows you to build and deploy models that can be used natively in SQL or accessible via a web service. This demo-packed session will take you through the end to end data science process using Microsoft ML Server so that you can see if it’s right for you. Read More

Picking the right Microsoft tool for the data science job

  • May 18, 2018
Microsoft have a lot of great tools for doing data science. The trouble is they have a lot of great tools for doing data science! This session gives you a framework to help you decide on the right tool to fit your needs so that you can get started sooner. View the decision tree full screen Presentation history January 24th, 2018 - Tech Summit Birmingham May 18th, 2018 - Data Science Ecomomy Read More

Preparing your business for data science

  • February 23, 2018
What do you need to be ready for data science? Abstract So you’re thinking about doing implementing data science project in your business? You might be considering one or all of these options: Hiring a data scientist Using existing staff Engaging a consultant Like with most things in business, if you fail to plan, you plan to fail. Starting out on a project without adequate planning, risks wasted time and money when you hit unexpected roadblocks. Read More

R for ETL

  • February 10, 2018
Learn about R for moving data about. Abstract Slides View the presentation full screen or view it below. Hit the Space bar to navigate through the slides. Presentation history February 10th, 2018 - Tech Outbound Read More

R & SQL Server for real-time predictions

  • December 9, 2017
Putting data science models with SQL Server can be a great and simple way to operationalise your data science models. Learn how to do it. Abstract Embedding your R (and soon Python!) models in SQL Server enables you to add predictive capabilities to your applications and analytics in place of buying expensive components or making substantial changes to your systems. In this demo-packed talk, you’ll see how you can go from a model built in R to making predictions on the fly in SQL Server 2016. Read More

DataOps - DevOps for analytics

  • October 17, 2017
What’s DevOps? How can we implement it’s lessons as data professionals? How we can we spend time doing cool things? Abstract DevOps is a movement focused on improving quality and time to deliver value by tackling the thorny issues of infrastructure, testing, integration, and deployment. These are big issues that have faced the data & analytics world for years, and tools have been slow to be delivered. This is changing though, so now we can start using the concepts from DevOps and applying them to analytics. Read More

Build your first bot - no code required!

  • October 13, 2017
Learn how to build a bot without having to learn to code. Abstract Learn how to build a bot that will answer questions asked by users. Learn how to customise it and embed it on your website. Learn how to do all of this without having to write a single line of code. I’ll be using Microsoft’s qnamaker.io site to build an FAQ bot and the putting it live with an Azure Bot Service and the Skype Web Control. Read More

Cut the R Learning Curve

  • September 6, 2017
Avoid the pain of learning R by finding out about the best bits. Abstract R is a powerful language to add to the BI, analytics and data science technologies you may already be using. This session circumvents the painful experience of on-boarding a new technology and will give you the foundation needed to use R effectively.Topics covered will include effective R coding, development best-practices, using R as a reporting tool, and how to build and administer a solid platform for analysis. Read More

Is the cloud cost effective?

  • July 5, 2017
Is it worth putting your stuff on the cloud? Let’s talk numbers! Abstract Yes, the cloud is cool. Yes, it can be easy. But… will it save or even make the company money? That is the all important question! Learning to build a financial business case for a technology decision is a smart move. Transform the techy topic that C-suite people don’t feel like they can discuss into something they can discuss by making it a financial topic. Read More

Data Science Executive Briefing

  • June 27, 2017
Understand what data science is and isn’t, how you go from business goals to data science problems, and how you acquire talented data scientists. Abstract Data science aims to use data to build processes that help automate away low-value work, help people take the most effective action, and help people adapt more quickly to changing circumstances. Data science is identifying when to send out engineers, which customers to talk to, and which patients to send to a consultant. Read More

Data + Docker = Discombobulating?

  • June 26, 2017
Learn about Docker and how you can store data in Docker containers safely. Abstract If you’re like me, you like your data to stick around for a long time and most importantly you want to know it’s safe. In the Docker world, there’s the maxim of “never patch”, always make a new container with the latest version of the application. If we’re sticking in our database in a container like Microsoft are doing with SQL Server now, what happens when we need to apply the latest patches? Read More

Failing my way to success with Azure

  • June 2, 2017
Experience my pain as I try to build an Azure Data Platform that scales. Abstract Azure is a constantly evolving area, with more new features per day than I could shake a stick at. It’s awesome, you can use PowerShell, it’s cheaper than tin. It’s the future, so they tell me. It’s also a real PITA when you’re trying to achieve a task and you don’t know which bit is best! Read More

Logistic Regressions in R

  • April 19, 2017
Learn what logistic regressions are. See how we can use R to prepare data, build models, and evaluate them. Abstract Learn about a fundamental type of model used to make classification prredictions and probabilities of an outcome’s likelihood. Logistic regressions are a core model in machine learning, inherited from statistics, and it’s vital to understand them if you’re interested in data science. The neat thing is they’re pretty simple! Read More

data.table power hour

  • April 7, 2017
Learn how to use this fantastic package in R for high-speed, low-code table wrangling. Abstract The package data.table is super-fast and super-powerful and can turn your long-winded and slow R code into a lean, mean, data-crunching machine. This hour takes you through the key aspects of the package and how it can make your life better. We’ll be looking at: Basic syntax Data I/O Joins Within group activities Pivoting data Cool hacks Slides View the presentation full screen or view it below. Read More

data.table in 5 minutes

  • March 15, 2017
Get a quick overview about the R package data.table Abstract The package data.table is super-fast and super-powerful and can turn your long-winded and slow R code into a lean, mean, data-crunching machine. This quick talk takes you through the most important features and benefits. Slides View the presentation full screen or view it below. Hit the Space bar to navigate through the slides. Presentation history March 15th, 2017 - Data Science Exeter Read More

The You in Community

  • February 18, 2017
Keynote about why and how peoeple can get involved in the R community. Slides View the presentation full screen or view it below. Hit the Space bar to navigate through the slides. Videos Presentation history February 18th, 2017 - SatRdays Cape Town Read More

Reproducible R docs in github

  • February 13, 2017
Learn how to build awesome docs in R and github. Abstract We can combine R and Github to make fantastic data driven documents, blogs, books and more. This talk takes you through the building blocks and how you can use them for different types of documents. Slides View the presentation full screen or view it below. Hit the Space bar to navigate through the slides. Presentation history February 13th, 2017 - R-Ladies London Read More

Personal Branding for Data Scientists

  • January 24, 2017
Slides View the presentation full screen or view it below. Hit the Space bar to navigate through the slides. Presentation history January 24th, 2017 - Bristol Data Scientists Read More

Get going with modern R in SQL Server in 30 minutes

  • October 24, 2016
Learn about provisioning data science machines for production, programmatically. Abstract Description Starting with provisioning a SQL Server on Azure, this end to end demo shows you how get everything set up to start using the best R packages available in realtime. Slides View the presentation full screen or view it below. Hit the Space bar to navigate through the slides. Get more info in the repository Videos Presentation history October 24th, 2016 - UK TechDays Online at Future Decoded October 24th, 2016 - SQL Bristol Read More

Infrastructure for R peeps

  • September 3, 2016
It’s important to know how to work your operating systems – if only so you know how to avoid working with your operating systems! Abstract Continuous integration, Docker, openCPU, shiny server, RStudio server, Microsoft R Server, R in Hadoop, your laptop, your grid computer … There’s a lot of infrastructure out there and someone has to configure it. This session whistle-stops through networking, Linux basics, and other key concepts to help get you up to speed because one day, the person configuring the server could be you. Read More

Board Packs: Combining Shiny, LaTeX And Databases For Full Effect

  • September 3, 2016
Making complex report compilation easy is something we can do in R. Learn how! Abstract The monthly report pack for the Board – with lots of information from different sources and all requiring commentary from lots of people – these things can take weeks to produce, send for commentary, and then compile into one pack. This full hour takes you through a framework for a single core source document, a shiny interface, hooks into the database for commentary, and the LaTeX (or markdown) document structure needed for developing a single interface through which lots of people can contribute to a single document. Read More

Getting better with data

  • June 8, 2016
Aimed at security folks, this talk is about how people involved with protecting our data can use some of it to improve protection. Abstract So many alerts and dashboards, so little time. It’s incredibly tough to know what to focus on when monitoring your network. This talk takes you through some ways of using the data available to you to reduce unimportant alerts, and liberating your time. Slides View the presentation full screen or view it below. Read More

My ways of being lazy with infrastructure

  • May 17, 2016
Learn how we can take some of the effort out of infrastructure work Abstract Oops, I never made one apparently! Slides View the presentation full screen or view it below. Hit the Space bar to navigate through the slides. Presentation history May 17th, 2016 - IT Pro Portugal Read More

Skilling up to code with data

  • April 13, 2016
Coding helps you scale as an analyst - learn some important concepts to help you get started. Abstract It’s starting to feel like every data project is a software project. It’s becoming essential to have some coding skills to really analyse your data. This session will cover how you can get to grips with programming. Why code with data What coding languages can be used Coding best practices Source control Testing Continuous testing (& deployment) Coding your infrastructure Slides View the presentation full screen or view it below. Read More

Analytical web services

  • March 10, 2016
“Works on my machine” isn’t useful - learn how we can get our models into production. Abstract In your day job you build some awesome bit of analysis in R but now people want this information available real time and against every thing that comes into the business - you need an R web service but not being a developer you have no clue how to go about it. Read More

Knowing your Rs from your elbow

  • October 4, 2015
Learn the fundamentals of R. Abstract R, a fantastic open-source language, will rock your world. Instead of showing you how to do dry old statistics and worrying about your random trees and bagging methods, this session is going to take you through the super-cool stuff. No TLAs allowed in this session, only cool terms like shiny & LaTeX! We’re gonna get your data out of SQL Server in just a few lines, then we’re going to chart it for awesomeness, and then the fun begins. Read More

Agile BI

  • May 16, 2015
Work smart not hard. BI needs to scale and this talk helps you do that. Abstract Agile methodologies are widely used in the dev world and are becoming increasingly adopted in the database world. But what about BI? Covering the technology and process sides of enabling agile BI, this session is designed to give you practical tips to get things moving more quickly for you. Slides View the presentation full screen or view it below. Read More