Modèles par catégorie

Régression intermédiaire en R

Richie Cotton

Data Evangelist at DataCamp

4 catégories

unique(fish$species)

"Bream" "Roach" "Perch" "Pike"

Scinder l'ensemble de données

La façon futée

base-R : split() + lapply()
dplyr : nest_by() + mutate()

La façon simple

bream <- fish %>% 
  filter(species == "Bream")
perch <- fish %>% 
  filter(species == "Perch")
pike <- fish %>% 
  filter(species == "Pike")
roach <- fish %>% 
  filter(species == "Roach")

4 modèles

mdl_bream <- lm(mass_g ~ length_cm, data = bream)

Call:
lm(formula = mass_g ~ length_cm, data = bream)

Coefficients:
(Intercept)    length_cm  
   -1035.35        54.55

mdl_pike <- lm(mass_g ~ length_cm, data = pike)

Call:
lm(formula = mass_g ~ length_cm, data = pike)

Coefficients:
(Intercept)    length_cm  
   -1540.82        53.19

mdl_perch <- lm(mass_g ~ length_cm, data = perch)

Call:
lm(formula = mass_g ~ length_cm, data = perch)

Coefficients:
(Intercept)    length_cm  
    -619.18        38.91

mdl_roach <- lm(mass_g ~ length_cm, data = roach)

Call:
lm(formula = mass_g ~ length_cm, data = roach)

Coefficients:
(Intercept)    length_cm  
    -329.38        23.32

Données explicatives

explanatory_data <- tibble(
  length_cm = seq(5, 60, 5)
)

Générer des prédictions

prediction_data_bream <- explanatory_data %>%
  mutate(
    mass_g = predict(mdl_bream, explanatory_data),
    species = "Bream"
  )

prediction_data_pike <- explanatory_data %>%
  mutate(
    mass_g = predict(mdl_perch, explanatory_data),
    species = "Perch"
  )

prediction_data_perch <- explanatory_data %>%
  mutate(
    mass_g = predict(mdl_pike, explanatory_data),
    species = "Pike"
  )

prediction_data_roach <- explanatory_data %>%
  mutate(
    mass_g = predict(mdl_roach, explanatory_data),
    species = "Roach"
  )

Visualiser les prédictions

ggplot(fish, aes(length_cm, mass_g, color = species)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE)

nuage : masse vs longueur par espèce

Ajouter vos prédictions

ggplot(fish,aes(length_cm, mass_g, color = species)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  geom_point(data = prediction_data_bream, size = 3, shape = 15) +
  geom_point(data = prediction_data_perch, size = 3, shape = 15) +
  geom_point(data = prediction_data_pike, size = 3, shape = 15) +
  geom_point(data = prediction_data_roach, size = 3, shape = 15)

nuage avec vos prédictions

Coefficient de détermination

mdl_fish <- lm(mass_g ~ length_cm + species, data = fish)

mdl_fish %>% 
  glance() %>% 
  pull(adj.r.squared)

0.917

mdl_bream %>% glance() %>% pull(adj.r.squared)

0.874

mdl_perch %>% glance() %>% pull(adj.r.squared)

0.917

mdl_pike %>% glance() %>% pull(adj.r.squared)

0.941

mdl_roach %>% glance() %>% pull(adj.r.squared)

0.815

Erreur-type résiduelle

mdl_fish %>% 
  glance() %>% 
  pull(sigma)

mdl_bream %>% glance() %>% pull(sigma)

74.2

mdl_perch %>% glance() %>% pull(sigma)

mdl_pike %>% glance() %>% pull(sigma)

mdl_roach %>% glance() %>% pull(sigma)

38.2

Passons à la pratique !

Régression intermédiaire en R