R 形状对游骑兵的重要性

存在二进制分类问题： 如何获得Ranger模型变量的形状贡献

样本数据：

library(ranger)
library(tidyverse)

# Binary Dataset
df <- iris
df$Target <- if_else(df$Species == "setosa",1,0)
df$Species <- NULL

# Train Ranger Model
model <- ranger(
  x = df %>%  select(-Target),
  y = df %>%  pull(Target))

库（ranger）
图书馆（tidyverse）
#二进制数据集
早上好！，
根据我的发现，您可以将
ranger（）
与fastshap（）配合使用，如下所示：

library(fastshap)
library(ranger)
library(tidyverse)
data(iris)
# Binary Dataset
df <- iris
df$Target <- if_else(df$Species == "setosa",1,0)
df$Species <- NULL
x <- df %>%  select(-Target)
# Train Ranger Model
model <- ranger(
  x = df %>%  select(-Target),
  y = df %>%  pull(Target))
# Prediction wrapper
pfun <- function(object, newdata) {
  predict(object, data = newdata)$predictions
}

# Compute fast (approximate) Shapley values using 10 Monte Carlo repetitions
system.time({  # estimate run time
  set.seed(5038)
  shap <- fastshap::explain(model, X = x, pred_wrapper = pfun, nsim = 10)
})

# Load required packages
library(ggplot2)
theme_set(theme_bw())

# Aggregate Shapley values
shap_imp <- data.frame(
  Variable = names(shap),
  Importance = apply(shap, MARGIN = 2, FUN = function(x) sum(abs(x)))
)


此外，如果您需要单独的预测，可以执行以下操作：

# Plot individual explanations
expl <- fastshap::explain(model, X = x ,pred_wrapper = pfun, nsim = 10, newdata = x[1L, ])
autoplot(expl, type = "contribution")

#绘制单独的解释
早上好！，
根据我的发现，您可以将
ranger（）
与fastshap（）配合使用，如下所示：

library(fastshap)
library(ranger)
library(tidyverse)
data(iris)
# Binary Dataset
df <- iris
df$Target <- if_else(df$Species == "setosa",1,0)
df$Species <- NULL
x <- df %>%  select(-Target)
# Train Ranger Model
model <- ranger(
  x = df %>%  select(-Target),
  y = df %>%  pull(Target))
# Prediction wrapper
pfun <- function(object, newdata) {
  predict(object, data = newdata)$predictions
}

# Compute fast (approximate) Shapley values using 10 Monte Carlo repetitions
system.time({  # estimate run time
  set.seed(5038)
  shap <- fastshap::explain(model, X = x, pred_wrapper = pfun, nsim = 10)
})

# Load required packages
library(ggplot2)
theme_set(theme_bw())

# Aggregate Shapley values
shap_imp <- data.frame(
  Variable = names(shap),
  Importance = apply(shap, MARGIN = 2, FUN = function(x) sum(abs(x)))
)


此外，如果您需要单独的预测，可以执行以下操作：

# Plot individual explanations
expl <- fastshap::explain(model, X = x ,pred_wrapper = pfun, nsim = 10, newdata = x[1L, ])
autoplot(expl, type = "contribution")

#绘制单独的解释
爆炸