两个数值型自变量

R 中级回归

Richie Cotton

Data Evangelist at DataCamp

可视化 3 个数值变量

3D 散点图
2D 散点图（颜色表示响应）

鱼类数据集的另一列

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

3D 散点图

library(plot3D)

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

library(plot3D)
library(magrittr)

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

3D 散点图

library(plot3D)
library(magrittr)

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

3D 散点图：长度、高度、质量

二维散点图，颜色表示响应变量

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

按颜色编码的散点图：鱼的长度、高度、质量

Viridis 色标

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

散点图：长度、高度、质量（Inferno 配色）

含两个数值型自变量的建模

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

预测流程

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)
  )

绘制预测结果

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
  )

散点图与预测点：长度、高度、质量（Inferno）

加入交互项

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

再次执行预测流程

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)
  )

绘制预测结果

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
  )

散点图与预测点：长度、高度、质量（含交互，Inferno）

Passons à la pratique !

R 中级回归