Prediction workflow with train:test split

pred_work.R

library(purrr)
library(broom)
library(modelr)

#data set up
my_iris <- iris %>% 
  mutate(train_test = ifelse(rbinom(n=n(), size = 1, prob = .85) == 1,
"train","test")) 

#set up model function
model_by_group <- function(df){
  lm(Sepal.Length ~ Sepal.Width,data = df %>% filter(train_test == "train"))
}

#store model, preds, coeffs, and model metrics in one dataframe
model_df <- my_iris %>% 
  group_by(Species) %>% 
  nest() %>% 
  mutate(model     = map(data, model_by_group),
         pred      = map2(data, model, modelr::add_predictions),
         coeffs    = map(model, broom::tidy),
         glance    = map(model, broom::glance)
         )

#want to view model coeffs
model_df %>% 
  unnest(coeffs)

#want to view model metrics such as r.squared
model_df %>% 
  unnest(glance)

#want to view predicted valus on test set
model_df %>% 
  unnest(pred) %>% 
  filter(train_test == "test")

#want avg absolute error
model_df %>% 
  unnest(pred) %>% 
  filter(train_test == "test") %>% 
  mutate(ae = abs(pred-Sepal.Length)) %>% 
  group_by(Species) %>% 
  summarise(mae = mean(ae))