Fit many models and get predictions based off of the training data

many_models_and_predictions.R

library(modelr)
library(tidyverse)
library(gapminder)

# nest data by continent and label test/train data
nested_gap <- gapminder %>% 
  mutate(test_train = ifelse(year < 1992, "train", "test")) %>% 
  group_by(continent) %>% 
  nest()

# make a linear model function than only trains on training set
cont_model <- function(df) {
  lm(lifeExp ~ year, data = df %>% filter(test_train == "train"))
}

# fit a model and add predictions to all data
fitted_gap <- nested_gap %>% 
  mutate(model = map(data, cont_model)) %>% 
  mutate(pred  = map2(data, model, add_predictions))

# unnest predictions and filter only the test rows
fitted_gap %>% 
  unnest(pred) %>% 
  filter(test_train == "test")