修改R中的对象，使其兼容绘图 每个评论已更新：

如何解决修改R中的对象，使其兼容绘图 每个评论已更新：

我在R中找到了一个程序，该程序可以绘制数据集中的观测图。

PropertyWithAppliesTo<T>

对于上面生成的图，我想对其进行修改，以便在这些图上仅显示第一个观测值。我试图修改下面的代码

#source: https://cran.r-project.org/web/packages/xgboost/xgboost.pdf

library(xgboost)

data(agaricus.train,package='xgboost')
data(agaricus.test,package='xgboost')

bst <- xgboost(agaricus.train$data,agaricus.train$label,nrounds = 50,eta = 0.1,max_depth = 3,subsample = .5,method = "hist",objective = "binary:logistic",nthread = 2,verbose = 0)

xgb.plot.shap(agaricus.test$data,model = bst,features = "odor=none")

contr <- predict(bst,agaricus.test$data,predcontrib = TRUE)

xgb.plot.shap(agaricus.test$data,contr,top_n = 12,n_col = 3)

有人可以告诉我我做错了什么吗？还是这根本不可能？ 谢谢

解决方法

据我所知，它并不是真的可以工作。这是一个示例-二进制变量的得分为0或1：得分为0 = SHAP值介于0.2和0.5之间，而得分为1 = SHAP值介于1.2和1.5之间-这是该图所说明的-该变量的SHAP值在0和1之间的差异。选择“第一个观察值”可能是得分为0或得分为1的观察值，因此显示的SHAP值并不能真正告诉您有关变量的太多信息。这就是为什么SHAP图需要矩阵包含多个观察值的原因（以及为什么您的方法行不通）。

尽管如此，如果您愿意，您可以拉取前n个观测值的SHAP值，然后在ggplot或基数R中将第一个观测值自己绘制出来，例如

library(tidyverse)
library(xgboost)

data(agaricus.train,package='xgboost')
data(agaricus.test,package='xgboost')

bst <- xgboost(agaricus.train$data,agaricus.train$label,nrounds = 50,eta = 0.1,max_depth = 3,subsample = .5,method = "hist",objective = "binary:logistic",nthread = 2,verbose = 0)

xgb.plot.shap(agaricus.test$data,model = bst,features = "odor=none")

contr <- predict(bst,agaricus.test$data,predcontrib = TRUE)

## Use "plot = FALSE" to return the data to "mat",instead of the rendered plot
mat <- xgb.plot.shap(agaricus.test$data[1:2,],contr[1:2,top_n = 12,n_col = 3,plot = FALSE)

## Format the data
mat$shap_contrib %>% 
  t() %>%
  as.data.frame() %>% 
  rownames_to_column() %>%
  set_names(c("Variable","SHAP","second_observation")) %>% 
## Then plot however you want
  ggplot(aes(y = SHAP,x = "")) +
  geom_point(pch = 3) +
  theme_bw() +
  theme(axis.ticks.x = element_blank(),axis.title.x = element_blank()) +
  facet_wrap(facets = vars(Variable))

每个评论已更新：

library(tidyverse)
library(xgboost)

data(agaricus.train,predcontrib = TRUE,approxcontrib = FALSE)
pred <- predict(bst,agaricus.test$data)

## Use "plot = FALSE" to return the data to "mat",plot = FALSE)

## Format the data
SHAP <- as.matrix(mat$shap_contrib[1,]) %>%
  as.data.frame() %>% 
  rownames_to_column() %>%
  set_names(c("Variable","SHAP"))

Score <- as.matrix(mat$data[1,]) %>%
  as.data.frame() %>% 
  rownames_to_column() %>% 
  set_names(c("Variable","Score"))

Pred <- ifelse(pred[1] <= 0.5,1)

SHAP_Score <- left_join(SHAP,Score,by = "Variable")

SHAP_Score_Pred <- cbind(SHAP_Score,Pred)

ggplot(SHAP_Score_Pred,aes(y = SHAP,x = Score)) +
  geom_hline(yintercept = 0,lty = 2,col = "grey75") +
  geom_point(pch = 3,cex = 3,col = "red") +
  ggtitle(label = paste("Prediction for this observation =",Pred,sep = " ")) +
  theme_bw(base_size = 12) +
  theme(axis.text = element_text(size = 14),axis.title = element_text(size = 16)) +
  scale_x_continuous(breaks = c(0,1)) +
  facet_wrap(facets = vars(Variable))