Publications by T. Moudiki
`crossvalidation` on R-universe, plus a classification example
I had to rename my R package crossval – generic functions for cross-validation – to crossvalidation, because its name was clashing with an existing CRAN R package’s named crossval. Here is how to install crossvalidation: options(repos = c( techtonique = 'https://techtonique.r-universe.dev', CRAN = 'https://cloud.r-project.org')) ins...
1840 sym R (2255 sym/2 pcs)
parallel grid search cross-validation using `crossvalidation`
Install package ‘crossvalidation’ options(repos = c( techtonique = 'https://techtonique.r-universe.dev', CRAN = 'https://cloud.r-project.org')) install.packages("crossvalidation") Import packages library(crossvalidation) library(randomForest) library(microbenchmark) Input data set.seed(123) n <- 1000 ; p <- 10 X <- matrix(rnorm(n * p),...
723 sym R (4540 sym/12 pcs) 2 img
`crossvalidation` and random search for calibrating support vector machines
Install and load packages options( repos = c(techtonique = 'https://techtonique.r-universe.dev', CRAN = 'https://cloud.r-project.org') ) install.packages("crossvalidation") library(crossvalidation) library(e1071) Input data transforming model response into a factor y <- as.factor(as.numeric(iris$Species)) explanatory variables X...
830 sym R (1487 sym/7 pcs)
Forecasting with `ahead`
A few weeks ago, I introduced a Forecasting API that I deployed on Heroku. Under the hood, this API is built on top of ahead (and through Python packages rpy2 and Flask); an R package for univariate and multivariate time series forecasting. As of October 13th, 2021, 5 forecasting methods are implemented in ahead: armagarchf: univariate time seri...
1082 sym R (161 sym/1 pcs)
Automatic Forecasting with `ahead::dynrmf` and Ridge regression
Last week I presented ahead, an R package for univariate and multivariate time series forecasting. In particular, the function dynrmf was introduced for univariate time series, with examples of Random Forest and Support Vector Machines fitting functions (fitting and predicting through fit_func and predict_func arguments of dynrmf). First things...
443 sym R (161 sym/1 pcs)
Fast and scalable forecasting with ahead::ridge2f
Two weeks ago I presented ahead, an R package for univariate and multivariate time series forecasting. And last week, I’ve shown how ahead::dynrmf could be used for automatic univariate forecasting. This week, I compare the speeds of execution of ahead::ridge2f (quasi-randomized autoregressive network) and ahead::varf (Vector AutoRegressive m...
709 sym R (161 sym/1 pcs)
Time series cross-validation using `crossvalidation` (Part 2)
In a previous blog post, I presented time series cross-validation with crossvalidation::crossval_ts. The most recent version of package crossvalidation, v0.4.1, contains a new function called eval_ts. How does crossvalidation::eval_ts work? As described in the graph below: crossvalidation::crossval_ts and crossvalidation::eval_ts have the sam...
1551 sym R (2331 sym/8 pcs) 2 img
Hundreds of Statistical/Machine Learning models for univariate time series, using ahead, ranger, xgboost, and caret
Today, we examine some nontrivial use cases for ahead::dynrmfforecasting. Indeed, the examples presented in the package’s README work quite smoothly – for randomForest::randomForest and e1071::svm – because: the fitting function can handle matricial inputs (can be called as fitting_func(x, y), also said to have a x/y interface), and not o...
2098 sym R (3188 sym/7 pcs) 10 img
A dashboard illustrating bivariate time series forecasting with `ahead`
Here is a link to a dashboard illustrating bivariate time series forecasting with the package ahead: https://thierry.shinyapps.io/ridge2shiny/ This dashboard is more specifically about ahead::ridge2f (in R) and ahead.Ridge2Regressor (in Python) hyperparameters’ meaning and impact. In the first two rows of the figure, everything related to ahead...
1742 sym 2 img
New version of nnetsauce — various quasi-randomized networks
A new version of nnetsauce, v0.10.0, is available on Pypi (for Python) and GitHub (for R). To those who’ve never heard about nnetsauce: it’s a package for supervised learning (as of February 2022, you can solve regression, classification, and time series forecasting problems with nnetsauce) based on various combinations of components \(g(XW+...
1635 sym R (1849 sym/2 pcs) 2 img