Among all probability distributions, the normal distribution is probably the most well-established and well-characterized. The importance of things like the central limit theorem and the normality assumptions in linear regression highlight it well. One of the more interesting ones is the fact that you can approximate a binomial distribution with ...

Introduction Bayesian optimization Acquisition functions Data preparation Random forest model The true distribution of the hyperparameters random search bayesian optimization UCB bayesian optimization PI bayesian optimization EI Contrast the results deep learning model Random search Bayesian optimization UCB Bayesian optimization PI Bayesian optimization EI Contrast the results Conclusion Session info ...

Lately I’ve been publishing screencasts demonstrating how to use the tidymodels framework, from first steps in modeling to how to evaluate complex models. Today’s screencast demonstrates how to implement multiclass or multinomial classification using with this week’s #TidyTuesday dataset on volcanoes. ???? Here is the code I used ...

Introduction In R Data One-proportion test Assumption of prop.test() and binom.test() Chi-square goodness of fit test Does my distribution follow a given distribution? Observed frequencies Expected frequencies Observed vs. expected frequencies By hand One-proportion test Verification in R Goodness of fit test Verification in R Introduction In a ...

This post outlines the steps needed to build R 4+ for Windows with OpenBLAS. The release of R 4.0 includes significant changes to the Windows build system from prior versions—for the better! Before anything, we all owe Jeroen Ooms significant gratitude for the many hours he spent working on the build ...

PreambleCatalan Castellers are collaborating (Wikipedia)Availability of distributed code tracking tools and associated collaborative tools make life much easier in building collaborative scientific tools and products. This is now especially much more i...

Preamble Catalan Castellers are collaborating (Wikipedia) Availability of distributed code tracking tools and associated collaborative tools make life much easier in building collaborative scientific tools and products. This is now especially much more important in data science as it is applied in many different industries as a de-facto standard. Essentially ...

I’m a long-term fan of Weezer. Such was the brilliance of their first two albums that I have stuck with them through thick and thin. And dear me, there has been some very thin music. Nonetheless I own every album – thirteen of them. Among them are six albums entitled “...

In the previous post, we showed how we can assign values in Pandas Data Frames based on multiple conditions of ... Read moreR: How To Assign Values Based On Multiple Conditions Of Different Columns

Running R with taskscheduleR and cronR In a previous post, we talked about how to run R from the Windows Task Scheduler. This article will talk about two additional approaches to schedule R scripts, including using the taskscheduleR package on Windows and the cronR package for Linux. For scheduling Python ...

Photo by Djurdjica Boskovic on Unsplash If your data science team experienced an abrupt transition to working at home, it may be a good time to rethink their development tools. In this post, I’ll talk about why laptop-centric data science gets in...

The CoViD-19 situation in Italy is little by little improving and I feel a bit more optimistic. It’s time for a new post! I will go back to a subject that is rather important for most agronomists, i.e. the selection of crop varieties. All farmers ar...

TLDR: BayestestR currently uses a 89% threshold by default for Credible Intervals (CI). Should we change that? If so, by what? Join the discussion here. Magical numbers, or conventional thresholds, have bad press in statistics, and there are many of them. For instance, .05 (for the p-value), or the 95% range for the ...