This turned out to be a bit of a downer, but it was a good learning exercise, and the general approach will be useful for generating test data on a different project. See notebook here.
Category Archives: Uncategorized
This was about 2 hours of fuss that I wish I had avoided. With my updated Jupyter Notebooks, I need to be explicit about what conda environment for python I am using.
It is all laid out clearly, if only I had been looking in this bit of the IPython docs:
For example, using conda environments, install a
Python (myenv) Kernel in a first environment:
source activate myenv python -m ipykernel install --user --name myenv --display-name "Python (myenv)"
And in a second environment, after making sure ipykernel is installed in it:
source activate other-env python -m ipykernel install --user --name other-env --display-name "Python (other-env)"
Just because I missed posting for the last year, doesn’t mean I have not been writing. Perhaps I have been writing more. Here is something that I just wrote for a perspective on opportunities for machine learning in population health.
Machine learning (ML) is emerging as a technology, climbing the “peak of inflated expectations” or perhaps even starting to slip into the “trough of disillusionment”, in the terms of the technology hype cycle,[ref] and offers both opportunities and threats to population health. ML is a technique for constructing computer algorithms, and what distinguishes ML methods from other computer solutions is that, while the structure of the computer program may be fixed, the details are learned from data. This data-driven approach is now dominant in Artificial Intelligence (AI), especially through deep neural networks, and stands in contrast to the old way, an expert-algorithms approach in which rules summarizing expert knowledge were painstakingly constructed by engineers and domain specialists. ML has succeeded by trading experts and programmers for data and nonparametric statistical models. However, the applications where ML has been successfully deployed remain limited. AI luminary Andrew Ng provides this concise heuristic: “[i]f a typical person can do a mental task with less than one second of thought, we can probably automate it using AI either now or in the near future.”[ref]
The editor only wants 1,000 words, so this is getting cut.
There is a new sort of publication model in Global Health, and I just gave it a try (editor’s note: just = in the last year). Gates Open Research offers “author-led publication and open peer review”, and is available now to Gates Foundation-funded researchers.
I used it to publish a Data Note, which is a dataset together with a short description of what is in the dataset.
Have a look here: https://gatesopenresearch.org/articles/2-18/v1
Just before that year of not writing anything here, I mentioned that I have a new microsimulation platform, and it is called Vivarium. That is still true, and now it even has some documentation: https://vivarium.readthedocs.io/en/latest/
It has been the thing that kept me too busy to blog for the last year. But it did generate some aesthetically pleasing figures for test purposes, as well as some population health results of interest. More details to come.
I got busy a year ago, and didn’t write anything until now. Well, I wrote some notes, but I never polished anything up enough to hit publish. What was I up to a year ago?
Lots of the same things I am up to now, but I’m going to start writing again, anyway.
For the last six months I’ve made brief mentions of the happenings of IHME “Diversity Club” on Healthy Algorithms. What is it?
I’m not sure if I mentioned, but I’m a co-chair of the Department of Global Health Diversity Committee, and we had a strategic retreat in December, where we identified “Training (Stand-alone and in curriculum)” as one of our top three priorities. We had a good brainstorm on ways to advance this priority, and an idea that stuck with me from it was “Different types of workshops, trainings, dialogues (format and topic – individual, structural, policy)”
Diversity Club is a different type of workshop. It has low-overhead. It is regularly recurring. And it has drawn a range of interest, depending on the time of year, the topic, and the competing priorities around IHME.
You can see some of the things we’ve discussed tagged diversity club on HA https://healthyalgorithms.com/tag/diversity-club/
Looking back on them, discussing The Invisible Knapsack was the one I was most nervous about https://healthyalgorithms.com/2017/04/10/diversity-club-the-invisible-knapsack/ it went fine.
Counter-measures for implicit bias left me the most optimistic about the possibility of positive change https://healthyalgorithms.com/2017/02/24/journal-club-counter-measures-for-implicit-bias/
I’ll report back again at a year.
Did you know you can change the signature of functions dynamically in Python 3? It is a bit nasty, and maybe will make things look nicer for vivarium users.
SO question that got me started: https://stackoverflow.com/a/33112180/1935494
I’ve had a new line of research developing for the last 18 months or so—*microsimulation*. It started when I stepped in to help with the “Cost Effectiveness Analysis with Microsimulation” (or CEAM) project at IHME. Now it is growing and growing to take over all of my research and recreation time. Is that bad or good?
Some of this work has now seen daylight from our presentations at SummerSim and iHEA in July, and today I am please to introduce a python package that you can use, too.
The programmers I’ve been working with on this convinced me that it is not just for cost effectiveness analysis and we need a more expansive name for it. So I present to you: vivarium. https://github.com/ihmeuw/vivarium