自定义重要性图 - R

Question

我正在撰写结果分析，并希望在执行随机森林后从变量重要性图中更改我的 MeanDecreaseAccuracy 图。我只想获取 MeanDecreaseAccuracy 图表并将其转换为条形图，以提供比当前显示的更好的可视化效果。

最好的方法是什么？

我当前的代码（在此之前有很多事情要做，但是对于这个例子来说这应该足够了）：

wine=read.csv("wine_dataset.csv")
wine$quality01[wine$quality >= 7] <- 1
wine$quality01[wine$quality < 7] <- 0
wine$quality01=as.factor(wine$quality01)
summary(wine)
num_data <- wine[,sapply(wine,is.numeric)]
hist.data.frame(num_data)

set.seed(8, sample.kind = "Rounding") #Set Seed to make sure results are repeatable
wine.bag=randomForest(quality01 ~ alcohol + volatile_acidity + sulphates + residual_sugar + 
    chlorides + free_sulfur_dioxide + fixed_acidity + pH + density + 
    citric_acid,data=wine,mtry=3,importance=T)    #Use Random Forest with a mtry value of 3 to fit the model

wine.bag #Review the Random Forest Results
plot(wine.bag) #Plot the Random Forest Results
imp=as.data.frame(importance(wine.bag)) #Analyze the importance of each variable in the model
imp=cbind(vars=rownames(imp),imp)
barplot(imp$MeanDecreaseAccuracy, names.arg=imp$vars)

我目前的输出是：

我正在使用的当前代码可以在here找到：

Answer 1

这里有几个选项：

library(randomForest)
library(tidyverse)

# Random forest model
iris.rf <- randomForest(Species ~ ., data=iris, importance=TRUE)

# Get importance values as a data frame
imp = as.data.frame(importance(iris.rf))
imp = cbind(vars=rownames(imp), imp)
imp = imp[order(imp$MeanDecreaseAccuracy),]
imp$vars = factor(imp$vars, levels=unique(imp$vars))

barplot(imp$MeanDecreaseAccuracy, names.arg=imp$vars)

imp %>% 
  pivot_longer(cols=matches("Mean")) %>% 
  ggplot(aes(value, vars)) +
  geom_col() +
  geom_text(aes(label=round(value), x=0.5*value), size=3, colour="white") +
  facet_grid(. ~ name, scales="free_x") +
  scale_x_continuous(expand=expansion(c(0,0.04))) +
  theme_bw() +
  theme(panel.grid.minor=element_blank(),
        panel.grid.major=element_blank(),
        axis.title=element_blank())

我也不会放弃点图，它（恕我直言）是更清晰的可视化。以下选项比您问题中的内置输出更具自定义性：

dotchart(imp$MeanDecreaseAccuracy, imp$vars, 
         xlim=c(0,max(imp$MeanDecreaseAccuracy)), pch=16)

imp %>% 
  pivot_longer(cols=matches("Mean")) %>% 
  ggplot(aes(value, vars)) +
  geom_point() +
  facet_grid(. ~ name) +
  scale_x_continuous(limits=c(0,NA), expand=expansion(c(0,0.04))) +
  theme_bw() +
  theme(panel.grid.minor=element_blank(),
        panel.grid.major.x=element_blank(),
        panel.grid.major.y=element_line(),
        axis.title=element_blank())

您也可以绘制值本身而不是点标记。例如：

imp %>% 
  pivot_longer(cols=matches("Mean")) %>% 
  ggplot(aes(value, vars)) +
  geom_text(aes(label=round(value,1)), size=3) +
  facet_grid(. ~ name, scales="free_x") +
  scale_x_continuous(limits=c(0,NA), expand=expansion(c(0,0.06))) +
  theme_bw() +
  theme(panel.grid.minor=element_blank(),
        panel.grid.major.x=element_blank(),
        panel.grid.major.y=element_line(),
        axis.title=element_blank())

Answer 2

你也可以考虑棒棒糖图表（例如来自ggalt），或者像这里一样：https://uc-r.github.io/lollipop 示例：

suppressPackageStartupMessages({
    library(ggalt)
    library(randomForest)
    library(data.table)
})

# Random forest model (from @eipi10)
iris.rf <- randomForest(Species ~ ., data=iris, importance=TRUE)
imp <- data.table(importance(iris.rf), keep.rownames = TRUE, 
                  key = "MeanDecreaseAccuracy")
imp[, rn := factor(rn, unique(rn))]
ggplot(melt(imp, id.vars="rn")[grep("Mean", variable)], 
       aes(x=rn, y=value, label = round(value, 1))) + 
    geom_lollipop(point.size = 3, point.colour = "cadetblue") +
    geom_text(nudge_y = 5) +
    coord_flip() +
    facet_wrap(~variable) +
    theme_minimal() +
    labs(y="Percent", x=NULL)

^{由reprex package (v0.3.0) 于 2020 年 4 月 28 日创建}