Gapminder

Many models with purrr and broom

data(gapminder)
gapminder

## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan Asia       1952    28.8  8425333      779.
##  2 Afghanistan Asia       1957    30.3  9240934      821.
##  3 Afghanistan Asia       1962    32.0 10267083      853.
##  4 Afghanistan Asia       1967    34.0 11537966      836.
##  5 Afghanistan Asia       1972    36.1 13079460      740.
##  6 Afghanistan Asia       1977    38.4 14880372      786.
##  7 Afghanistan Asia       1982    39.9 12881816      978.
##  8 Afghanistan Asia       1987    40.8 13867957      852.
##  9 Afghanistan Asia       1992    41.7 16317921      649.
## 10 Afghanistan Asia       1997    41.8 22227415      635.
## # … with 1,694 more rows

gapminder %>%
  ggplot(aes(year, lifeExp, group = country)) + 
  geom_line(alpha = 1/3)

nz <- gapminder %>%
  filter(country == "New Zealand")

nz %>%
  ggplot(aes(year, lifeExp)) +
  geom_line() +
  ggtitle("Full data = ")

nz_mod <- lm(lifeExp ~ year, data = nz )

nz %>%
  add_predictions(nz_mod) %>%
  ggplot(aes(year, pred)) +
  geom_line() +
  ggtitle("Linear trend +")

nz %>%
  add_residuals(nz_mod) %>%
  ggplot(aes(year, resid)) +
  geom_hline(yintercept = 0, color = "white", size = 3) +
  geom_line() +
  ggtitle("Remaining pattern")

by_country <- gapminder %>%
  group_by(country, continent) %>%
  nest()

norway <- by_country$data[[96]]

country_model <- function(df) {
  lm(lifeExp ~ year, data = df)
}

#models <- map(by_country$data, country_model)

by_country <- by_country %>%
  mutate(model = map(data, country_model))
by_country

## # A tibble: 142 x 4
##    country     continent data              model   
##    <fct>       <fct>     <list>            <list>  
##  1 Afghanistan Asia      <tibble [12 × 4]> <S3: lm>
##  2 Albania     Europe    <tibble [12 × 4]> <S3: lm>
##  3 Algeria     Africa    <tibble [12 × 4]> <S3: lm>
##  4 Angola      Africa    <tibble [12 × 4]> <S3: lm>
##  5 Argentina   Americas  <tibble [12 × 4]> <S3: lm>
##  6 Australia   Oceania   <tibble [12 × 4]> <S3: lm>
##  7 Austria     Europe    <tibble [12 × 4]> <S3: lm>
##  8 Bahrain     Asia      <tibble [12 × 4]> <S3: lm>
##  9 Bangladesh  Asia      <tibble [12 × 4]> <S3: lm>
## 10 Belgium     Europe    <tibble [12 × 4]> <S3: lm>
## # … with 132 more rows

by_country %>%
  filter(continent == "Europe")

## # A tibble: 30 x 4
##    country                continent data              model   
##    <fct>                  <fct>     <list>            <list>  
##  1 Albania                Europe    <tibble [12 × 4]> <S3: lm>
##  2 Austria                Europe    <tibble [12 × 4]> <S3: lm>
##  3 Belgium                Europe    <tibble [12 × 4]> <S3: lm>
##  4 Bosnia and Herzegovina Europe    <tibble [12 × 4]> <S3: lm>
##  5 Bulgaria               Europe    <tibble [12 × 4]> <S3: lm>
##  6 Croatia                Europe    <tibble [12 × 4]> <S3: lm>
##  7 Czech Republic         Europe    <tibble [12 × 4]> <S3: lm>
##  8 Denmark                Europe    <tibble [12 × 4]> <S3: lm>
##  9 Finland                Europe    <tibble [12 × 4]> <S3: lm>
## 10 France                 Europe    <tibble [12 × 4]> <S3: lm>
## # … with 20 more rows

by_country <- by_country %>%
  mutate(
    resids = map2(data, model, add_residuals)
  )

resids <- unnest(by_country, resids)