【发布时间】：2018-11-12 20:26:34
【问题描述】：
我需要从分组列表中读取一堆文件，并根据组将它们组合（来自同一组的文件将具有相同的列，因此可以使用bind_rows() 减少。
当我通过purrr::map() 函数时，我似乎无法掌握数据的变化情况，因为我不断收到警告说我不能在原子向量上使用$。
我要做的第一件事是按组进行拆分，以便获得一个列表，其中包含我想在每个组中读取的文件列表。然后我使用 map 遍历该列表中的每个项目，并使用第二个 map 遍历每个子列表上的行以读取文件。然而，在那个级别上发生了一些事情，它不再像对待顶级的单个组一样对待数据。
（无法在地图函数中调试和查看我的环境确实是理解机制的一个问题。）
require(tidyverse)
#> Loading required package: tidyverse
x <- structure(list(survey = c("adm2014", "adm2015", "adm2016", "eap2008",
"eap2009", "eap2011", "eap2012", "eap2013", "eap2014", "eap2015",
"eap2016", "ef2008a", "ef2008b", "ef2008c", "ef2008cp", "ef2008d",
"ef2009a", "ef2009b", "ef2009c", "ef2009d", "ef2010a", "ef2010b",
"ef2010c", "ef2010cp", "ef2010d", "ef2011a", "ef2011b", "ef2011c",
"ef2011d", "ef2012a", "ef2012b", "ef2012c", "ef2012cp", "ef2012d",
"ef2013a", "ef2013b", "ef2013c", "ef2013d", "ef2014a", "ef2014b",
"ef2014c", "ef2014cp", "ef2014d", "ef2015a", "ef2015b", "ef2015c",
"ef2015d", "ef2016a", "ef2016b", "ef2016c", "ef2016cp", "ef2016d",
"efest2008", "efest2009", "effy2008", "effy2009", "effy2010",
"effy2011", "effy2012", "effy2013", "effy2014", "effy2015", "effy2016",
"effy2017", "efia2008", "efia2009", "efia2011", "efia2012", "efia2013",
"efia2014", "efia2015", "efia2016", "efia2017", "f0708_f1a",
"f0708_f2", "f0708_f3", "f0809_f1a", "f0809_f2", "f0809_f3",
"f0910_f1a", "f0910_f2", "f0910_f3", "f1011_f1a", "f1011_f2",
"f1011_f3", "f1112_f1a", "f1112_f2", "f1112_f3", "f1213_f1a",
"f1213_f2", "f1213_f3", "f1314_f1a", "f1314_f2", "f1314_f3",
"f1415_f1a", "f1415_f2", "f1415_f3", "f1516_f1a", "f1516_f2",
"f1516_f3", "gr2008", "gr2008_l2", "gr2009", "gr2009_l2", "gr200_08",
"gr200_09", "gr200_10", "gr200_11", "gr200_12", "gr200_13", "gr200_14",
"gr200_15", "gr200_16", "gr2010", "gr2010_l2", "gr2011", "gr2011_l2",
"gr2012", "gr2012_l2", "gr2013", "gr2013_l2", "gr2014", "gr2014_l2",
"gr2015", "gr2015_l2", "gr2016", "gr2016_l2", "hd2008", "hd2009",
"hd2010", "hd2011", "hd2012", "hd2013", "hd2014", "hd2015", "hd2017",
"ic2008", "ic2008_ay", "ic2008_py", "ic2009", "ic2009_ay", "ic2009_py",
"ic2010", "ic2010_ay", "ic2010_py", "ic2011", "ic2011_ay", "ic2011_py",
"ic2012", "ic2012_ay", "ic2012_py", "ic2013", "ic2013_ay", "ic2013_py",
"ic2014", "ic2014_ay", "ic2014_py", "ic2015", "ic2015_ay", "ic2015_py",
"ic2016", "ic2016_ay", "ic2016_py", "ic2017", "ic2017_ay", "ic2017_py",
"s2008_abd", "s2008_cn", "s2008_f", "s2008_g", "s2009_abd", "s2009_cn",
"s2009_f", "s2009_g", "s2010_abd", "s2010_cn", "s2010_f", "s2010_g",
"s2011_abd", "s2011_cn", "s2011_f", "s2011_g", "sal2008_a", "sal2008_a_lt9",
"sal2008_b", "sal2008_faculty", "sal2009_a", "sal2009_a_lt9",
"sal2009_b", "sal2009_faculty", "sal2010_a", "sal2010_a_lt9",
"sal2010_b", "sal2010_faculty", "sal2011_a", "sal2011_a_lt9",
"sal2011_faculty"), survgroup = c("adm", "adm", "adm", "eap",
"eap", "eap", "eap", "eap", "eap", "eap", "eap", "efa", "efb",
"efc", "efcp", "efd", "efa", "efb", "efc", "efd", "efa", "efb",
"efc", "efcp", "efd", "efa", "efb", "efc", "efd", "efa", "efb",
"efc", "efcp", "efd", "efa", "efb", "efc", "efd", "efa", "efb",
"efc", "efcp", "efd", "efa", "efb", "efc", "efd", "efa", "efb",
"efc", "efcp", "efd", "efest", "efest", "effy", "effy", "effy",
"effy", "effy", "effy", "effy", "effy", "effy", "effy", "efia",
"efia", "efia", "efia", "efia", "efia", "efia", "efia", "efia",
"f_f1a", "f_f2", "f_f3", "f_f1a", "f_f2", "f_f3", "f_f1a", "f_f2",
"f_f3", "f_f1a", "f_f2", "f_f3", "f_f1a", "f_f2", "f_f3", "f_f1a",
"f_f2", "f_f3", "f_f1a", "f_f2", "f_f3", "f_f1a", "f_f2", "f_f3",
"f_f1a", "f_f2", "f_f3", "gr", "gr_l2", "gr", "gr_l2", "gr_08",
"gr_09", "gr_10", "gr_11", "gr_12", "gr_13", "gr_14", "gr_15",
"gr_16", "gr", "gr_l2", "gr", "gr_l2", "gr", "gr_l2", "gr", "gr_l2",
"gr", "gr_l2", "gr", "gr_l2", "gr", "gr_l2", "hd", "hd", "hd",
"hd", "hd", "hd", "hd", "hd", "hd", "ic", "ic_ay", "ic_py", "ic",
"ic_ay", "ic_py", "ic", "ic_ay", "ic_py", "ic", "ic_ay", "ic_py",
"ic", "ic_ay", "ic_py", "ic", "ic_ay", "ic_py", "ic", "ic_ay",
"ic_py", "ic", "ic_ay", "ic_py", "ic", "ic_ay", "ic_py", "ic",
"ic_ay", "ic_py", "s_abd", "s_cn", "s_f", "s_g", "s_abd", "s_cn",
"s_f", "s_g", "s_abd", "s_cn", "s_f", "s_g", "s_abd", "s_cn",
"s_f", "s_g", "sal_a", "sal_a_lt9", "sal_b", "sal_faculty", "sal_a",
"sal_a_lt9", "sal_b", "sal_faculty", "sal_a", "sal_a_lt9", "sal_b",
"sal_faculty", "sal_a", "sal_a_lt9", "sal_faculty")), class = c("tbl_df",
"tbl", "data.frame"), row.names = c(NA, -197L))
x %>%
split(.$survgroup) %>%
map(function(currentgroup) {
#currentgroup should now be a tibble of each group.
currentgroup %>%
map(function(singlesurvey) { #singlesurvey should be each row in the group
x <- read_csv(path_expand(paste0("~data/IPEDS/API Pulls/datadownloaded/", singlesurvey$survey, ".csv")))
}) %>% bind_rows()
})
#> Error in path_expand(paste0("~data/IPEDS/API Pulls/datadownloaded/", singlesurvey$survey, : could not find function "path_expand"
由reprex package (v0.2.1) 于 2018 年 11 月 12 日创建
【问题讨论】：
-
path.expand而不是path_expand也许？ -
from package
fs: path_expand() 与 base::path.expand() 在 Windows 主目录的解释上不同。特别是 path_expand() 使用在 USERPROFILE 环境变量中设置的路径，如果未设置，则使用 HOMEDRIVE/HOMEPATH。 -
有趣！更智能的文件/路径管理......肯定会检查这个包