Posts by Gary Hutson
Author: Gary Hutson
A function to speed up and simplify writing to SQL Server databases in R
Feed: R-bloggers. Author: Gary Hutson. I had a recent enquiry on our NHS-R community slack channel about which package is best to work with larger datasets, such as 5 million plus records, with high dimensionality. I got to thinking that the DBI and odbc packages would be best for this purpose, as this is still not considered big data, it is more medium data with manageable dimensionality. The functions can be fiddly to understand, so I thought I would combine all the functions into one lovely function wrapper in R. Overview of the function The function below allows you to ... Read More
Data.Table – everything you need to know to get you started in R
Feed: R-bloggers. Author: Gary Hutson. I will take you through step by step how to use the data.table package, and compare it with base R operations, to see the performance gains you get when using this optimised package. Load in data.table To load the package in you can follow the below instructions: #install.packages(data.table) library(data.table) You should now have everything you need to start the tutorial. Reading in a data.table csv To read files in data.table you use the fread syntax to bring files in. I will load the NHSRDatasets package and export this out and then I will use the ... Read More
ConfusionTableR – a package to tidy outputs of confusion matrix objects for storage in databases and row level structures
Feed: R-bloggers. Author: Gary Hutson. I am really excited to announce my beta package and it is now available to download on GitHub. This is my third package I have managed to create. I have many more projects, tutorials and code snippets available on my GitHub site. I hope you find it useful and read below to find out how to install it, work with it and get the most out of it. How to use the package? The package guidance, and installation, can be found on the GitHub site directly, but to install the package follow the below steps: ... Read More
R Package Tracking
Feed: R-bloggers. Author: Gary Hutson. I have recently uploaded my first R package to the CRAN repository, it needs an additional revision, but it is now there. I wanted to know how many downloads it has had since its release on CRAN last month. I thought shall I write a package, but alas there is one already available. The dlstats package saves the day I was searching on the old Google and I found this lovely package that does just what I need. I have created a small tutorial to show you how to build the small routine needed to ... Read More
Reticulate webinar – R and Python – a happy union
Feed: R-bloggers. Author: Gary Hutson. Wednesday (20th January 2021) myself and a colleagues Andreas kicked off the first webinar of 2021 for the NHS-R Community with our look at the benefits of using reticulate for joining up R and Python. What was the webinar about? The webinar was split into two sections: The first session involved me taking the functionality of the reticulate package and how you can easily pass R and Python commands to convert the data from the respective formats. This is actually really intuitive in R and the webinar recording in the next section will show the ... Read More
LondonR Talks – Computer Vision Classification – Turning a Kaggle example into a clinical decision making tool
Feed: R-bloggers. Author: Gary Hutson. I had the pleasure of speaking at the last LondonR event of 2020. What a strange year it has been? But this put the icing on the cake. The premise The premise of my talk was to take a novel Kaggle parasite cell dataset and advocate how this type of classification task could be transported to other areas such as clinical x-ray scanning, diagnostic image condition detection, etc. The live event To view the talk, have a look at the LondonR event below. I was on first and then two very interesting talks followed from ... Read More
NHS-R 2020 Week Long Conference
Feed: R-bloggers. Author: Gary Hutson. The NHS-R conference concluded, and I am emotional that it has ended. There were some fantastic speakers and the whole event, from start to finish was a blast. Openers I would like to include everyone on here, but the openers that had an impact for me are included below: Conference opening – the journey so far – Mohammed Amin Mohammed Mohammed Amin Mohammed on the NHS-R Journey so far What a great opener from Mohammed and it was really interesting to get a view of the direction of the NHS-R Community. OpenSAFELY.org: proving the power ... Read More
NHS-R Community – Computer Vision Classification – How it can aid clinicians – Malaria cell case study with R
Feed: R-bloggers. Author: Gary Hutson. The NHS-R conference is coming up and I have been invited to speak for the third year running, I know hat trick, as well as becoming an official fellow of the organisation, as I am now back with the NHS. This year I wanted to bring Deep Learning to the table, and my focus will be on how to apply Convolutional Neural Networks to a Kaggle Malaria cell problem. Understanding the data To understand the data I have first created two functions and prepared all my imports from the relevant R libraries: library(tensorflow) library(keras) library(plyr) ... Read More
Health Data Science Platform has landed – watch the webinar
Feed: R-bloggers. Author: Gary Hutson. The Health Data Science Platform has been an endeavour of love. But what is it? Watch our technical team discuss how and why you should be switching to the DSP in your healthcare organisation Introducing the DSP The webinar explains why use the DSP, how to use the DSP and what the DSP does. Under the hood The DSP uses curated machine learning (superivsed and unsupervised) machine learning algorithms alongside other algorithms, such as epidemiology curve estimations and forecasting tools. These have all be tested with customer and combined in to one easy to use ... Read More
Moving on as Head of Solutions and AI at Draper and Dash
Feed: R-bloggers. Author: Gary Hutson. Well, what can I say? It has been a blast over the past year and a half. In my time at the company I have managed to work on a number of fascinating projects, here is a list of just some of them:Data Science Platform – this has been the culmination of lots of machine learning projects, undertaken separately in R and Python, and has allowed for our Healthcare Data Science Platform to be developed. This, alongside skilled data scientists, data engineers and front end developers, we think we have developed something really specialClinical Outcome ... Read More
Recent Comments