Reading through documentation for a programming function to find what arguments it likes can be tedious, especially since many of the possible options either don’t work together or aren’t documented. Something I have been including on most of my newer classes is a static method called get_new_params(method=’random’) which does pretty much exactly as it says, […]
The simple elegance of `.get_new_params()` Read More »
For a model, metrics like MAE and RMSE and so on quantify how accurate a prediction is. However, the vast majority of metrics are symmetric, meaning they care equally about overestimates and underestimates. So far, I have found really one relatively common way for caring about direction: Mean Logarithmic Error (MLE). I also created the
Over and Underestimate Loss Metrics Read More »
Sister breaks newish phone (Pixel 5A), but it’s still connect, just the screen is dead. Seems a shame to throw all that away, but usually repair shops are more expensive than just buying a new phone. Timely fact was this Verge article in the news feed announcing the availability of official Google parts on iFixit.
Pixel 5a Phone Screen Replacement Read More »
Let’s be clear right up front: Canada is essentially part of the US. There are really only two differences: the big flags flying over some businesses are maple leaves rather than stars and stripes, and lots of the packaging is double-labeled in French. There are more differences between my home, Minneapolis and Los Angeles than
Canada: Toronto and Hamilton Digital Nomad Review Read More »
It has been impossible in the past to get all three of the largest neural network architectures running in the same Python environment in such a way that they don’t conflict and so that they will also train on GPU. The reason I want all the libraries running in the same environment is that AutoTS
PyTorch, Tensorflow, and MXNet on GPU in the same environment and GPU vs CPU performance Read More »
Power, glorious power!That’s what I think when I see the stream raging through the ravine in early spring. I’ve wanted to put a hydroelectric generator in there for ages. There is one problem, there isn’t really enough water flow for enough of the year to do anything. Actually, it’s either dry or frozen solid for
Hydroelectric Power for IOT devices (more fun than practical) Read More »
This winter was particularly harsh, with lots of young trees dying back or dying completely, even though they are supposedly hardy to much further north. This spring also saw a particularly powerful spring melt. And that, of course, is an erosion problem. The valley here is in a fragile balance. It has never quite adjusted
I was so excited to see the announcement of the M6 forecasting competition. For those who don’t know the M series of competitions (not to be confused with BMW cars) is a long running series of competitions for forecasting time series. It comes from the 1980’s, well predating the modern data science explosion. And this
All the Problems with the M6 Competition (and a few good things) Read More »
Note that a variation on this article may also be posted on the Nousot blog. Time series are a string of numbers varying across time. It could be the weather, sales of tissue paper, electricity demand of a region, or countless other things. There are plenty of useful things to do with this type of
Preprocessing for Time Series Read More »
I can see why Columbia, particularly Medellin, is a popular travel destination. Firstly, the weather is perfect all year round. It has a tag of the City of Eternal Spring, or perhaps more likely, eternal summer given that it is mostly 70 rarely leaving the 60-80 degree range. It is lush and fertile, with ample
Columbia: Cycling and Remote Work in Medellin Read More »
