如何动态创建变量并将其组合到 r 中的数据框？

Question

我正在为多个number of clusters 运行kmeans，然后尝试将cluster results 组合 到original dataframe。

来自https://stats.stackexchange.com/questions/10838/produce-a-list-of-variable-name-in-a-for-loop-then-assign-values-to-the 的帖子我正在使用他们下面提到的代码来动态创建变量并根据我的需要进行修改。

上述帖子中的原始代码：

x <- as.list(rnorm(10000))
names(x) <- paste("a", 1:length(x), sep = "")
list2env(x , envir = .GlobalEnv)

现在将其应用于 iris 数据：

library(tidyverse)
library(ggthemes)
library(factoextra)

这在创建 3 个集群列表时效果很好：

# running for 1 to 3 clusters
lapply(1:3,

function(cluster_num){
  cluster_res_list <- as.list(kmeans(iris %>% select(-Species), cluster_num, nstart = 25)) 
  names(cluster_res_list) <- paste("iris_clus", 1:length(cluster_res_list), sep="_")
  list2env(cluster_res_list, envir = .GlobalEnv)
 
 # iris_df <- cbind(iris, cluster_res_list)
} )

问题：当我尝试将它们与原始数据集结合时出现错误：Error in as.data.frame.default(x[[i]], optional = TRUE, stringsAsFactors = stringsAsFactors) : cannot coerce class ‘"kmeans"’ to a data.frame

lapply(1:3,

function(cluster_num){
  cluster_res_list <- as.list(kmeans(iris %>% select(-Species), cluster_num, nstart = 25)) 
  names(cluster_res_list) <- paste("iris_clus", 1:length(cluster_res_list), sep="_")
  list2env(cluster_res_list, envir = .GlobalEnv)
 
  # to combine each cluster result to original df
  iris_df <- cbind(iris, cluster_res_list)
} )

Answer 1

kmeans 的输出可以使用fitted 函数查看为矩阵。矩阵的行名称标识集群。如果您想在原始日期框架中添加一列来标识集群分配，那么类似的方法会起作用。

以 3 个集群为例：

cluster_num <- 3

iris %>% 
    select(-Species) %>% 
    kmeans(centers = cluster_num, nstart = 25) %>% 
    fitted() %>% 
    row.names() %>%
    tibble(iris_clus = .) %>%
    cbind(iris) %>% 
    tail()

    iris_clus Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
145         2          6.7         3.3          5.7         2.5 virginica
146         2          6.7         3.0          5.2         2.3 virginica
147         1          6.3         2.5          5.0         1.9 virginica
148         2          6.5         3.0          5.2         2.0 virginica
149         2          6.2         3.4          5.4         2.3 virginica
150         1          5.9         3.0          5.1         1.8 virginica

将其插入您示例中的lapply

lapply(1:3, function(cluster_num) {
    iris %>% 
        select(-Species) %>% 
        kmeans(centers = cluster_num, nstart = 25) %>% 
        fitted() %>% 
        row.names() %>%
        tibble(iris_clus = .) %>%
        cbind(iris) 
})

这是将所有数据组合成一个数据集的一种方法。每个模型一列

clusters <- Reduce(cbind, lapply(1:3, function(cluster_num) {

   result <- iris %>% 
        select(-Species) %>% 
        kmeans(centers = cluster_num, nstart = 25) %>% 
        fitted() %>% 
        row.names() %>% 
        tibble(iris_clus = .)

   names(result) <- paste("iris_clus", cluster_num, sep = "_")
   return(result)

}))

cbind(iris, clusters)