Leverage coverage.py’s dynamic contexts and find out! Why? You’re staring at a mysterious line of code in a huge codebase, wondering which test executes it. Running the entire test suite multiple times takes too long. What can you do? How? The answer is : coverage.py with dynamic contexts. This will enable us…

Don’t overfit it! Arrogant forecasters don’t exist The interesting thing about forecasting is that every week I get a new test set. Just because a model worked well on last week’s data doesn’t mean it’ll work well on next week’s. The challenge lies in properly validating models before putting them into production. How do…

Predict time series with non-integer seasonality — You may have used SARIMAX to model time series data with some recurring seasonality. For example, you may have hourly data with a pattern which repeats every 12 hours. But what you have, say, weekly data, and expect some kind of yearly seasonality. You can’t use n_periods=52, because the number…

Sometimes, the defaults don’t cover your use-case Why monitor a custom evaluation function? Sometimes, you’re working with a very custom evaluation metric which can’t be used as a loss function. So you might want to: train using some standard loss function, such as L2 loss choose your hyperparameters (such as n_estimators ) based on the best…

Learn how to evaluate it computationally and analytically, leveraging the power of JAX! — Intro Suppose you have a random variable X, and you put it through some transformation g. The distribution of the resulting random variable g(X) is known as the “pushforward distribution”. Today we’ll learn how to calculate its probability density. Example Rather than talking abstractly, let’s start with a practical example. …

Instead, plot its components, and check that they make sense Many data scientists approach modelling as a feature engineering task: they gather features, do cross-validation, and if the score isn’t good enough, they keep adding more features until it is. In forecasting, where there is typically little data, this is…

Make your return types more precise! What happens if you don’t use typing.overload Suppose we have a function which take a boolean argument inplace and that its return type depends on the value of inplace. If it’s True, it returns None, else it returns an integer: By inspecting the function, we can see that we expect…

Learn how, in some cases, you can calculate posterior distributions by hand! — Suppose you’ve tossed a coin 1,000 times and obtained 292. You’d like to know what the probability of obtaining heads is from a single coin toss — but you don’t just want a single estimate, you want an entire distribution. If you define y: the number of heads you obtain …

Quickly find out how many pull requests you’ve submitted and/or reviewed! — Say you want to show off how many pull requests you’ve submitted this year, or how many you’ve reviewed. Manually counting them on GitHub would be hard work…but there’s an easier, simpler, and more efficient way. Prerequisites In a Python3 virtual environment, install requests with pip : Generate an access token On your GitHub…