11.7 Meeting Videos

11.7.1 Cohort 1

Meeting chat log
00:14:48    Tony ElHabr:    seed = 1101
00:14:52    Tony ElHabr:    what a hipster
00:15:11    pavitra:    I see a subliminal binary message
00:17:41    Tony ElHabr:    1101 -> D in hex
00:18:08    pavitra:    D for dark magicks
00:39:59    Jonathan Leslie:    I’m heading off. Thanks, Jon…really nice presentation!
00:45:54    Jim Gruman: thank you Jon!!!
00:47:45    Andy Farina:    Thank you Jon, great presentation and addition of workflow sets

11.7.2 Cohort 2

Meeting chat log
00:08:57    Janita Botha:   I have problems with physical knitting too... :)
00:10:18    Roberto Villegas-Diaz:  XSEDE
00:13:15    rahul bahadur:  Anyone works with Spark here? - SparkR/sparklyr?
00:22:38    Luke Shaw:  no sorry, have used pyspark before so have some spark understanding though
01:04:05    Amélie Gourdon-Kanhukamwe (she/they):   I have another call this week, gonna dash
01:04:18    Stephen Holsenbeck: ok, thanks for coming!
01:04:24    Janita Botha:   bye!
01:04:28    Luke Shaw:  Bye :)
01:13:19    Janita Botha:   cool! :)
01:14:37    Janita Botha:   I have to run! See you folks next week!
01:14:55    Stephen Holsenbeck: Bye Janita, have a good Monday!

11.7.3 Cohort 3

Meeting chat log
00:12:38    Daniel Chen:    it's essentially doing the multiple recipes and collecting the model metrics for you across all your preprocessing steps/models
00:12:40    Daniel Chen:    ?
00:14:29    Daniel Chen:    fn  

The function to run. Acceptable values are: tune::tune_grid(), tune::tune_bayes(), tune::fit_resamples(), finetune::tune_race_anova(), finetune::tune_race_win_loss(), or finetune::tune_sim_anneal().
00:15:00    Daniel Chen:    seems like there's only a few functions that are availiable to be used
00:16:36    Daniel Chen:    but they're using the string instead of quoted form because they're matching on string to see which functions are allowed: https://github.com/tidymodels/workflowsets/blob/main/R/workflow_map.R#L101
00:16:53    Ildiko Czeller: makes sense, thanks
00:16:55    Toryn Schafer (she/her):    Thanks, Daniel!
00:32:13    Daniel Chen:    i guess they're using tidyposterior, instead of tidymodels. so i guess that's what's adding to the confusion
00:35:06    Daniel Chen:    cross   

A logical: should all combinations of the preprocessors and models be used to create the workflows? If FALSE, the length of preproc and models should be equal.
00:49:17    jiwan:  tune_grid(
  object,
  preprocessor,
  resamples,
  ...,
  param_info = NULL,
  grid = 10,
  metrics = NULL,
  control = control_grid()
)
00:50:04    Daniel Chen:    https://tune.tidymodels.org/reference/tune_grid.html
00:50:52    jiwan:  A data frame of tuning combinations or a positive integer. The data frame should have columns for each parameter being tuned and rows for tuning parameter candidates. An integer denotes the number of candidate parameter sets to be created automatically

11.7.4 Cohort 4