Questions about the history of the output of machine learning models.

You can output the result of lm function or randomforest function, or run it with summary() to see the result in report format on the console.

It is hard to extract the numerical data from this report output.
The advent of {broom} has made it easier.

Question 1

Why did we historically get report-like output on the console instead of a tabular format to make it easier to retrieve the numbers?

Question 2

Does this report-like format have anything to do with something called dgTMatrix?

thank you

  1. Nicely formatted results that could be included in publishing and reporting were very helpful before the wide spread adoption of markdown. SAS and SPSS were often used instead of R/S because of their publication friendly tables and formatted output, not because they were better for statistics.

  2. Not sure what that is...


This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.