我想在R包h2o中的h2o.glrm()函数的帮助下降低混合数据集的维数。我的数据集包括二元变量（具有两个可能水平的名义变量），名义变量（具有三个或更多可能水平）和有序变量（具有三个或更多可能水平）。我对二元变量使用逻辑损失，对有序变量和名义变量分别使用有序损失和分类损失。
下面是我的问题的一个最小的、可重复的例子。

# Load packages
library(tibble)
library(h2o)
# Example data for MRE
my_data <- tibble::tibble(
  var.1 = as.factor(rep(1, 10)),
  var.2 = as.factor(c(NA, 1, 1, -1, -1, -1, 1, 1, 1, 1)),
  var.3 = as.factor(rep(-1, 10)),
  var.4 = as.factor(c(-1, 1, 1, 1, 1, 1, -1, 1, 1, 1)),
  var.5 = as.factor(rep(-1, 10)),
  var.6 = as.factor(c(1, 2, 3, 1, 2, 2, 2, 2, 2, 3)),
  var.7 = as.factor(c(NA, 2, 3, 2, 2, 2, 2, 3, 1, 2)),
  var.8 = as.factor(c(2, 3, 2, 2, 2, 2, 3, 2, 2, 2)),
  var.9 = as.factor(c(1, 2, 3, 4, 1, 2, 3, 4, 1, 3)),
  var.10 = as.factor(c(1, 1, 1, 1, NA, 1, 1, -1, -1, 1))
)
my_data_types <- tibble::tibble(
  var_name = paste("var", 1:10, sep = "."),
  var_type = c(rep("binary", 5),
               rep("ordinal", 3),
               "nominal", "binary")
)
# Initialize h2o cluster
h2o::h2o.init()
h2o::h2o.no_progress()
# Convert data to h2o object
my_data_h2o <- h2o::as.h2o(my_data)
# Define loss function for ordinal and nominal variables
losses <- tibble::tibble(
  index = which(my_data_types$var_type %in% c("ordinal", "nominal")) - 1,
  loss = NA_character_
)
for (i in seq_along(losses$index)) {
  losses$loss[i] <-
    ifelse(my_data_types$var_type[losses$index[i] + 1] == "ordinal", "Ordinal",
           ifelse(my_data_types$var_type[losses$index[i] + 1] == "nominal", "Categorical", NA))
}
# Run GLRM
my_glrm <- h2o::h2o.glrm(
  training_frame = my_data_h2o,
  k = 2,
  loss = "Logistic",
  loss_by_col_idx = losses$index,
  loss_by_col = losses$loss,
  regularization_x = "None",
  regularization_y = "None",
  transform = "NONE",
  max_iterations = 2000,
  seed = 12345
)

当我运行上述模型时，我收到以下错误消息：

Error in .h2o.doSafeREST(h2oRestApiVersion = h2oRestApiVersion, urlSuffix = page,  : 
  
ERROR MESSAGE:
Illegal argument(s) for GLRM model: GLRM_model_R_1683532209346_20.  Details: ERRR on field: _loss: Logistic is not a numeric loss function

虽然我不认为这是错误消息告诉我的，但我也在数据集的另一个版本上运行了模型，其中二进制变量没有被定义为因子。

# Alternative example data for MRE
my_data_2 <- tibble::tibble(
  var.1 = rep(1, 10),
  var.2 = c(NA, 1, 1, -1, -1, -1, 1, 1, 1, 1),
  var.3 = rep(-1, 10),
  var.4 = c(-1, 1, 1, 1, 1, 1, -1, 1, 1, 1),
  var.5 = rep(-1, 10),
  var.6 = as.factor(c(1, 2, 3, 1, 2, 2, 2, 2, 2, 3)),
  var.7 = as.factor(c(NA, 2, 3, 2, 2, 2, 2, 3, 1, 2)),
  var.8 = as.factor(c(2, 3, 2, 2, 2, 2, 3, 2, 2, 2)),
  var.9 = as.factor(c(1, 2, 3, 4, 1, 2, 3, 4, 1, 3)),
  var.10 = c(1, 1, 1, 1, NA, 1, 1, -1, -1, 1)
)
# Convert data to h2o object
my_data_2_h2o <- h2o::as.h2o(my_data_2)
# Run GLRM
my_glrm_2 <- h2o::h2o.glrm(
  training_frame = my_data_2_h2o,
  k = 2,
  loss = "Logistic",
  loss_by_col_idx = losses$index,
  loss_by_col = losses$loss,
  regularization_x = "None",
  regularization_y = "None",
  transform = "NONE",
  max_iterations = 2000,
  seed = 12345
)

当我在数据集的替代版本上运行模型时，我收到以下错误：

Error in .h2o.doSafeREST(h2oRestApiVersion = h2oRestApiVersion, urlSuffix = page,  : 
  
ERROR MESSAGE:
Illegal argument(s) for GLRM model: GLRM_model_R_1683532209346_21.  Details: ERRR on field: _loss: Logistic is not a numeric loss function
ERRR on field: _loss_by_col: Loss function Logistic cannot be applied to numeric column 0
ERRR on field: _loss_by_col: Loss function Logistic cannot be applied to numeric column 1
ERRR on field: _loss_by_col: Loss function Logistic cannot be applied to numeric column 6

如果有人能告诉我我做错了什么，我将不胜感激。