{"id":2991,"date":"2023-04-10T00:30:23","date_gmt":"2023-04-10T00:30:23","guid":{"rendered":"http:\/\/optimumsportsperformance.com\/blog\/?p=2991"},"modified":"2023-04-10T12:29:21","modified_gmt":"2023-04-10T12:29:21","slug":"tidymodels-workflow-sets-tutorial","status":"publish","type":"post","link":"https:\/\/optimumsportsperformance.com\/blog\/tidymodels-workflow-sets-tutorial\/","title":{"rendered":"Tidymodels Workflow Sets Tutorial"},"content":{"rendered":"

Intro<\/strong><\/span><\/p>\n

The purpose of workflow sets are to allow you to seamlessly fit multiply different models (and even tune them) simultaneously. This provide an efficient approach to the model building process as the models can then be compared to each other to determine which model is the optimal model for deployment. Therefore, the aim of this tutorial is to provide a simple walk through of how to set up a workflow_set()<\/strong> and build multiple models simultaneously using the tidymodels<\/strong> framework.<\/p>\n

The full code (which will include code not directly embedded in this tutorial) is available on my GITHUB page<\/a><\/span><\/strong>.<\/p>\n

Load Packages & Data<\/strong><\/span><\/p>\n

Data comes from the nwslR package<\/a><\/strong><\/span>, which provides a lot of really nice National Women’s Soccer League data.<\/p>\n

We will be using stats for field players to determine those who received the the Best XI<\/strong> award (there will only be 10 players per season since we are dealing with field player stats, no goalies).<\/p>\n

\r\n## packages\r\nlibrary(tidyverse)\r\nlibrary(tidymodels)\r\nlibrary(nwslR)\r\nlibrary(tictoc)\r\n\r\ntheme_set(theme_light() +\r\n            theme(strip.background = element_rect(fill = "black"),\r\n                  strip.text = element_text(face = "bold")))\r\n\r\n\r\n## data sets required\r\ndata(player)\r\ndata(fieldplayer_overall_season_stats)\r\ndata(award)\r\n\r\n## join all data sets to make a primary data set\r\nd <- fieldplayer_overall_season_stats %>%\r\n  left_join(player) %>% \r\n  left_join(award) %>% \r\n  select(-name_other) %>% \r\n  mutate(best_11 = case_when(award == "Best XI" ~ 1,\r\n                             TRUE ~ 0)) %>% \r\n  select(-award)\r\n\r\nd %>% \r\n  head()\r\n<\/pre>\n
\"\"<\/a>
\nOur features will be all of the play stats: mp<\/strong>, starts<\/strong>, min<\/strong>, gls<\/strong>, ast<\/strong>, pk<\/strong>, p_katt<\/strong> and the position (pos<\/strong>) that the player played.<\/p>\n
Exploratory Data Analysis<\/strong><\/span><\/p>\n
Let’s explore some of the variables that we will be modeling.<\/p>\n
How many NAs are there in the data set?<\/p>\n
\"\"<\/a><\/p>\n