gower | Python package for Gower distance | Machine Learning library

I am using the R programming language. I want to learn how to measure and plot the run time of difference procedures as the size of the data increases.

I found a previous stackoverflow post that answers a similar question: Plot the run time of three functions

It seems that the "microbenchmark" library in R should be able to accomplish this task.

Suppose I simulate the following data:

I am using the R programming language. I incorporated my own code along with a lengthy tutorial over here : https://michael.hahsler.net/SMU/EMIS7332/R/viz_classifier.html . In the end, I produced a visual "plot" (see the end of this code, "final_plot")

I am using the R programming language. I am trying to figure out how to "recreate" plots in ggplot2/plotly, once they have been created in base R.

For example, I created some data and made a plot :

I am using the R programming language and following this tutorial over here: https://michael.hahsler.net/SMU/EMIS7332/R/viz_classifier.html .

I simulated some data and plotted the results as per the tutorial:

This may be a usage misunderstanding, but I expect the following toy example to work. I want to have a lagged predictor in my recipe, but once I include it in the recipe, and try to predict on the same data using a workflow with the recipe, it doesn't recognize the column foo and cannot compute its lag.

Now, I can get this to work if I:

1. Pull the fit out of the workflow that has been fit.
2. Independently prep and bake the data I want to fit.

Which I code after the failed workflow fit, and it succeeds. According to the documentation, I should be able to put a workflow fit in the predict slot: https://www.tidymodels.org/start/recipes/#predict-workflow

I am probably fundamentally misunderstanding how workflow is supposed to operate. I have what I consider a workaround, but I do not understand why the failed statement isn't working in the way the workaround is. I expected the failed workflow construct to work under the covers like the workaround I have.

In short, if work_df is a dataframe, the_rec is a recipe based off work_df, rf_mod is a model, and you create the workflow rf_workflow, then should I expect the predict() function to work identically in the two predict() calls below?

I have this dataset:

I am attempting to run a clustering algorithm over a list of dissimilarity matrices for different numbers of clusters k and extract some information for each run.

This first block of code produces the list of dissimilarity matrices

I am attempting to apply the gower_matrix function from the gower package to the values of a dictionary using this chunk of code:

I've put together a data preprocessing recipe for the recent coffee dataset featured on TidyTuesday. My intention is to generate a workflow, and then from there tune a hyperparameter. I'm specifically interesting in manually declaring predictors and outcomes through the various update_role() functions, rather than using a formula, since I have some great plans for this style of variable selection (it's a really great idea!).

The example below produces a recipe that works just fine with prep and bake(coffee_test). It even works if I deselect the outcome column, eg. coffee_recipe %>% bake(select(coffee_test, -cupper_points)). However, when I run the workflow through tune_grid I get the errors as shown. It looks like tune_grid can't find the variables that don't have the "predictor" role, even though bake does just fine.

Now, if I instead do things the normal way with a formula and step_rm the variables I don't care about, then things mostly work --- I get a few warnings for rows with missing country_of_origin values, which I find strange since I should be imputing those. It's entirely possible I've misunderstood the purpose of roles and how to use them.