我使用recipes包开发了一个自定义步骤，以便将其包含在一些caret模型中。在我的新步骤上应用prep和bake时，一切正常。但是，当我尝试在caret::train中包含未准备的食谱时，我得到了以下错误：“错误：未选择任何变量或项”。欢迎任何建议。可重现的示例和会话信息如下：
# 加载库packs <- c("tidyverse", "caret", "e1071", "wavelets", "recipes")InstIfNec<-function (pack) { if (!do.call(require,as.list(pack))) { do.call(install.packages,as.list(pack)) } do.call(require,as.list(pack)) }lapply(packs, InstIfNec)# 获取数据data(biomass)biomass<-select(biomass, -dataset, -sample)# 定义自定义预处理算法HaarTransform<-function(DF1) { w<-function(k) { s1=dwt(k, filter="haar") return (s1@V[[1]]) } Smt=as.matrix(DF1) Smt=t(base::apply(Smt,1,w)) return (data.frame(Smt))}# 创建自定义步骤函数step_Haar_new<-function(terms=NULL, role=NA, trained=FALSE, skip=FALSE, columns=NULL) { step(subclass="Haar", terms=terms, role=role, trained=trained, skip=skip, columns=columns)}step_Haar<-function(recipe, ..., role=NA, trained=FALSE, skip=FALSE, columns=NULL) { terms=ellipse_check(...) add_step(recipe, step_Haar_new(terms=terms, role=role, trained=trained, skip=skip, columns=columns))}prep.step_Haar <- function(x, training, info = NULL, ...) { col_names<-terms_select(terms = x$terms, info = info) step_Haar_new(terms = x$terms, role = x$role, trained = TRUE, skip = x$skip, columns=col_names)}bake.step_Haar <- function(object, new_data, ...) { new_data<-HaarTransform(dplyr::select(new_data, object$columns)) as_tibble(new_data)}# 测试食谱函数Haar_recipe<-recipe(carbon ~ ., biomass) %>% step_Haar(all_predictors()) Haar_recipe%>% prep(biomass) %>% bake(biomass) # 一切正常# 拟合caret模型fit <- caret::train(Haar_recipe, data=biomass, method="svmLinear") # 错误：未选择任何变量或项。R会话：
R version 3.4.4 (2018-03-15)Platform: x86_64-w64-mingw32/x64 (64-bit)Running under: Windows 7 x64 (build 7601) Service Pack 1Matrix products: defaultlocale:[1] LC_COLLATE=French_France.1252 LC_CTYPE=French_France.1252 LC_MONETARY=French_France.1252[4] LC_NUMERIC=C LC_TIME=French_France.1252attached base packages:[1] stats graphics grDevices utils datasets methods baseother attached packages:[1] recipes_0.1.4 wavelets_0.3-0.1 e1071_1.7-0.1 caret_6.0-81 lattice_0.20-38[6] forcats_0.4.0 stringr_1.4.0 dplyr_0.8.0.1 purrr_0.3.1 readr_1.3.1[11] tidyr_0.8.3 tibble_2.0.1 ggplot2_3.1.0 tidyverse_1.2.1loaded via a namespace (and not attached):[1] Rcpp_1.0.0 lubridate_1.7.4 class_7.3-15 utf8_1.1.4 assertthat_0.2.0[6] ipred_0.9-8 foreach_1.4.4 R6_2.4.0 cellranger_1.1.0 plyr_1.8.4[11] backports_1.1.3 stats4_3.4.4 httr_1.4.0 pillar_1.3.1 rlang_0.3.1[16] lazyeval_0.2.1 readxl_1.3.0 rstudioapi_0.9.0 data.table_1.12.0 kernlab_0.9-27[21] rpart_4.1-13 Matrix_1.2-15 splines_3.4.4 gower_0.2.0 munsell_0.5.0[26] broom_0.5.1 compiler_3.4.4 modelr_0.1.4 pkgconfig_2.0.2 nnet_7.3-12[31] tidyselect_0.2.5 prodlim_2018.04.18 codetools_0.2-16 fansi_0.4.0 crayon_1.3.4[36] withr_2.1.2 MASS_7.3-51.1 ModelMetrics_1.2.2 grid_3.4.4 nlme_3.1-137[41] jsonlite_1.6 gtable_0.2.0 magrittr_1.5 scales_1.0.0 cli_1.0.1[46] stringi_1.3.1 reshape2_1.4.3 timeDate_3043.102 xml2_1.2.0 generics_0.0.2[51] lava_1.6.5 iterators_1.0.10 tools_3.4.4 glue_1.3.0 hms_0.4.2[56] survival_2.43-3 yaml_2.2.0 colorspace_1.4-0 rvest_0.3.2 haven_2.1.0回答：
存在几个问题：
- 步骤现在需要一个新的参数（称为
id）（参见此处） - 你的bake步骤只保存了预测变量（并删除了结果列）
以下是可用的代码：
packs <- c("tidyverse", "caret", "e1071", "wavelets", "recipes")InstIfNec<-function (pack) { if (!do.call(require,as.list(pack))) { do.call(install.packages,as.list(pack)) } do.call(require,as.list(pack)) }lapply(packs, InstIfNec)# 获取数据data(biomass)biomass <- select(biomass,-dataset,-sample)# 定义自定义预处理算法HaarTransform <- function(DF1) { w <- function(k) { s1 = dwt(k, filter = "haar") return (s1@V[[1]]) } Smt = as.matrix(DF1) Smt = t(base::apply(Smt, 1, w)) return (data.frame(Smt))}# 创建自定义步骤函数step_Haar_new <- function(terms, role, trained, skip, columns, id) { step(subclass = "Haar", terms = terms, role = role, trained = trained, skip = skip, columns = columns, id = id)}step_Haar<-function(recipe, ..., role = "predictor", trained = FALSE, skip = FALSE, columns = NULL, id = rand_id("Harr")) { terms = ellipse_check(...) add_step(recipe, step_Haar_new(terms = terms, role = role, trained = trained, skip = skip, columns = columns, id = id))}prep.step_Haar <- function(x, training, info = NULL, ...) { col_names <- terms_select(terms = x$terms, info = info) step_Haar_new( terms = x$terms, role = x$role, trained = TRUE, skip = x$skip, columns = col_names, id = x$id )}bake.step_Haar <- function(object, new_data, ...) { predictors <- HaarTransform(dplyr::select(new_data, object$columns)) new_data[, object$columns] <- NULL bind_cols(new_data, predictors)}# 测试食谱函数Haar_recipe<-recipe(carbon ~ ., biomass) %>% step_Haar(all_predictors()) # 拟合caret模型fit <- caret::train(Haar_recipe, data = biomass, method = "svmLinear") 