Introduction Corpus & model Evaluation & analogy Experimental set-up Results: model parameters Results: analogy categories Visualizing vector offsets Summary & caveats References Introduction This post walks through corpus-based methods for evaluating the efficacy of vector space models in capturing semantic relations. Here we consider the standard evaluation tool for VSMs: the offset method ...

I’ve released pqR-2020-07-23, a new version of my variant implementation of R.  You can install it on Linux, Windows, or Mac as described at pqR-project.org. Installation must currently be from source, similarly to source installs of R Core versions of R. This version has preliminary implementations ...

Introduction Apache Spark is an open-source distributed cluster-computing framework implemented in Scala that first came out in 2014 and has since then become popular for many computing applications including machine learning thanks to among other aspects its user-friendly APIs. The popularity also gave rise to many online courses of varied quality. ...

Hello readers, today’s blog I will be looking at predicting the formula 1 grid using the Tidymodels collection of R packages. The idea is to use data from the practice sessions on a Friday, to give an idea of what the grid is expected to be for the race on ...

The Marshall Project has a solid story and set of visualizations on the impact of COVID-19 in U.S. prisons. They keep the data (and vis) regularly updated. They do great work and this is an important topic, but this visualization breaks my “ordered grid” OCD: To be fair, it’...

Occupations classification is an important step in tasks such as labour market analysis, epidemiological studies and official statistics. To assist research on the labour market, ESCO has defined a taxonomy for occupations. Occupations are specified and organized in a hierarchical structure based on the International Standard Classification of Occupations (ISCO). ...

Our last few posts on portfolio construction have simulated various weighting schemes to create a range of possible portfolios. We’ve then chosen portfolios whose average weights yield the type of risk and return we’d like to achieve. However, we’ve noted there is more to portfolio construction than ...

Our last few posts on portfolio construction have simulated various weighting schemes to create a range of possible portfolios. We’ve then chosen portfolios whose average weights yield the type of risk and return we’d like to achieve. However, we’ve noted there is more to portfolio construction than ...

I recently created a visualization of the distribution of river flow directions and also of coastal orientations. Following its publication in social networks (here), I was asked to make a post about how I did it. Well, here we go to start with an example of rivers, coastal orientation is ...

Explainable 'AI' with Gradient Boosted randomized networks.

Explainable 'AI' with Gradient Boosted randomized networks.

Explainable 'AI' with Gradient Boosted randomized networks.

I recently created a visualization of the distribution of river flow directions and also of coastal orientations. Following its publication in social networks (here), I was asked to make a post about how I did it. Well, here we go to start with an example of rivers, coastal orientation is ...

Today, Emil Hvitfeldt and I led a useR! 2020 online tutorial on predictive modeling with text using tidy data principles. This tutorial was hosted by R-Ladies en Argentina; huge thanks to the organizers for their leadership and effort in making this tutorial possible. Materials for this tutorial are available on GitHub, ...

Our last few posts on portfolio construction have simulated various weighting schemes to create a range of possible portfolios. We’ve then chosen portfolios whose average weights yield the type of risk and return we’d like to achieve. However, we’ve noted there is more to portfolio construction than ...

Akshaj is a budding deep learning researcher who loves to work with R. He has worked as a Research Associate at the Indian Institute of Science and as a Data Scientist at KPMG India. In the previous post, we went through the dataset, the pre-processing involved, train-test split, and talked ...