Publications by T. Moudiki

Simulation of dependent variables in ESGtoolkit

08.10.2020

Version 0.3.0 of ESGtoolkit has been released – on GitHub for now. As in v0.2.0, it contains functions for the simulation of dependent random variables. Here is how you can install the package from R console: library(devtools) devtools::install_github("Techtonique/esgtoolkit") When I first created ESGtoolkit back in 2014, its name stood for Ec...

3629 sym R (1216 sym/5 pcs) 6 img

Submitting R package to CRAN

15.10.2020

Disclaimer: I have no affiliation with Microsoft Corp. or Revolution Analytics. For the n-th time in x years, submitting an R package to CRAN ended up like comedy. This time for one anecdotal note (a kind of warning), whereas the previous accepted version of ESGtoolkit has had, for 5 years, 12 warnings and notes combined. No error, nothing’s...

3096 sym R (497 sym/1 pcs) 2 img

Explainable Statistical/Machine Learning explainability using Kernel Ridge Regression surrogates

05.11.2020

As announced last week, this week’s topic is Statistical/Machine Learning (ML) explainability using Kernel Ridge Regression (KRR) surrogates. The core idea underlying this type of ML explainability methods is to apply a second learning model to the predictions of the first so-called black-box model. How am I envisaging it? Not by utilizing KRR...

1066 sym 2 img

Boosting nonlinear penalized least squares

20.11.2020

For some reasons I couldn’t foresee, there’s been no blog post here on november 13 and november 20. So, here is the post about LSBoost announced here a few weeks ago. First things first, what is LSBoost? Gradient boosted nonlinear penalized least squares. More precisely in LSBoost, the ensembles’ base learners are penalized, randomized neu...

1487 sym 2 img

Bayesian forecasting for uni/multivariate time series

03.12.2020

This post is about Bayesian forecasting of univariate/multivariate time series in nnetsauce. For each statistical/machine learning (ML) presented below, its default hyperparameters are used. A further tuning of their respective hyperparameters could, of course, result in a much better performance than what’s showcased here. 1 – univariate ti...

1722 sym R (1848 sym/9 pcs) 8 img

Classify penguins with nnetsauce’s MultitaskClassifier

10.12.2020

I’ve recently heard and read about iris dataset’s retirement. iris had been, for years, a go-to dataset for testing classifiers. The new iris is a dataset of palmer penguins, available in R through the package palmerpenguins. In this blog post, after data preparation, I adjust a classifier – nnetsauce’s MultitaskClassifier – to the pal...

3013 sym R (2294 sym/10 pcs) 12 img

2020 recap, Gradient Boosting, Generalized Linear Models, AdaOpt with nnetsauce and mlsauce

28.12.2020

A few highlights from 2020 in this blog include: The introduction of mlsauce’s AdaOpt and LSBoost The introduction of Generalized Linear Models (GLMs) in nnetsauce What are AdaOpt, LSBoost and nnetsauce’s GLMs? mlsauce’s AdaOpt is a probabilistic classifier based on a mix of multivariable optimization and a nearest neighbors algorithm. T...

2683 sym

New activation functions in mlsauce’s LSBoost

11.02.2021

In previous posts, I introduced LSBoost; a gradient boosting machine that uses randomized and penalized least squares as a basis – instead of decision trees which are frequently used as base learners. mlsauce’s LSBoost takes into account a problem’s nonlinearity by including new, engineered explanatory variables \(g(XW+b)\) with: \(g...

1316 sym R (2321 sym/2 pcs) 2 img

An infinity of time series models in nnetsauce

05.03.2021

I was selected and invited to present this family of univariate/multivariate time series models at R/Finance 2020 (in Chicago, IL). However, the COVID-19 pandemics decided differently. It’s still a work in progress; comments, remarks, pull requests are welcome as usual (in nnetsauce). But the general philosophy of model construction in this fra...

2119 sym Python (6625 sym/3 pcs) 4 img

A forecasting tool (API) with examples in curl, R, Python

27.05.2021

This post is about a predictive analytics tool (in beta version) I started building during the first lockdown in March 2020. I used R and Python for this purpose, and more specifically Flask and rpy2. It’s been a pretty cool and instructive experience for me, of having both R and Python interacting into a web app, and deploying the tool on Hero...

3357 sym R (3421 sym/5 pcs) 4 img