Deux variables explicatives numériques

Régression intermédiaire en R

Richie Cotton

Data Evangelist at DataCamp

Visualiser 3 variables numériques

Nuage de points 3D
Nuage de points 2D avec la réponse en couleur

Une autre colonne pour le jeu de données sur les poissons

species	mass_g	length_cm	height_cm
Bream	1000	33.5	18.96
Bream	925	36.2	18.75
Roach	290	24.0	8.88
Roach	390	29.5	9.48
Perch	1100	39.0	12.80
Perch	1000	40.2	12.60
Pike	1250	52.0	10.69
Pike	1650	59.0	10.81

Nuage de points 3D

library(plot3D)

scatter3D(fish$length_cm, fish$height_cm, fish$mass_g)

library(plot3D)
library(magrittr)

fish %$%
  scatter3D(length_cm, height_cm, mass_g)

Nuage de points 3D

library(plot3D)
library(magrittr)

fish %$%
  scatter3D(length_cm, height_cm, mass_g)

Nuage 2D, réponse en couleur

ggplot(
  fish, 
  aes(length_cm, height_cm, color = mass_g)
) +
  geom_point()

Palettes de couleurs Viridis

ggplot(
  fish, 
  aes(length_cm, height_cm, color = mass_g)
) +
  geom_point() +
  scale_color_viridis_c(option = "inferno")

Modéliser avec 2 variables explicatives numériques

mdl_mass_vs_both <- lm(mass_g ~ length_cm + height_cm, data = fish)

Call:
lm(formula = mass_g ~ length_cm + height_cm, data = fish)

Coefficients:
(Intercept)    length_cm    height_cm  
    -622.16        28.97        26.34

Le flux de prédiction

explanatory_data <- expand_grid(
  length_cm = seq(5, 60, 5),
  height_cm = seq(2, 20, 2)
)

prediction_data <- explanatory_data %>% 
  mutate(
    mass_g = predict(mdl_mass_vs_both, explanatory_data)
  )

Tracer les prédictions

ggplot(
  fish, 
  aes(length_cm, height_cm, color = mass_g)
) +
  geom_point() +
  scale_color_viridis_c(option = "inferno") +
  geom_point(
    data = prediction_data, shape = 15, size = 3
  )

Inclure une interaction

mdl_mass_vs_both_inter <- lm(mass_g ~ length_cm * height_cm, data = fish)

Call:
lm(formula = mass_g ~ length_cm * height_cm, data = fish)

Coefficients:
        (Intercept)            length_cm            height_cm  length_cm:height_cm  
           159.1144               0.3001             -78.1234               3.5455

Le flux de prédiction, à nouveau

explanatory_data <- expand_grid(
  length_cm = seq(5, 60, 5),
  height_cm = seq(2, 20, 2)
)

prediction_data <- explanatory_data %>% 
  mutate(
    mass_g = predict(mdl_mass_vs_both_inter, explanatory_data)
  )

Tracer les prédictions

ggplot(
  fish, 
  aes(length_cm, height_cm, color = mass_g)
) +
  geom_point() +
  scale_color_viridis_c(option = "inferno") +
  geom_point(
    data = prediction_data, shape = 15, size = 3
  )

scatter-color-fish-length-height-mass-inferno-pred-inter.png

Passons à la pratique !

Régression intermédiaire en R