轻松替换R中的多个单词；str_replace_all给出两个对象长度不相等的错误

我试图使用str_replace_all将许多不同的值（即“Mod”、“M2”、“M3”、“conceptor”）替换为一个一致的字符串（即“版主：”）。我用多个不同的类别来做这件事，我想避免写下每个唯一的值，因为有很多

因此，我制作了一个TIBLE，它包含了我想要标准化的所有唯一值，并将其读入，然后拉出每一列（有5列，但为了简单起见，只显示了2列），将它们制成向量：

speak_names <- read_csv("speak_names.csv")
speak_namesMisc <- dplyr::pull(speak_names, Misc)
speak_namesMod <- dplyr::pull(speak_names, Moderator)

我正在使用的数据帧是16244行，如果这对模式或替换有任何影响的话。我陷入困境，试图找出为什么这不起作用和/或另一个解决方案，不涉及键入向量中的每个字符元素

谢谢大家!

library('dplyr') # load the dplyr package
library('stringr') # load the stringr package

#下面是我自己的数据集示例，可以回答您的问题

dput（）

我的数据

abc<-as.data.frame(
structure(list(Name = c("ME-9_ 005", "ME-9_ 004", "ME-9_ 003", 
                        "ME-9_ 002", "ME-9_ 001", "ME-9_ 000", "ME-8_ 005", "ME-8_ 004", 
                        "ME-8_ 003", "ME-8_ 002", "ME-8_ 001", "ME-8_ 000", "ME-7_ 005", 
                        "ME-7_ 004", "ME-7_ 003", "ME-7_ 002", "ME-7_ 001", "ME-7_ 000"
), Mg = c(0.411058647473409, 0.361611969040526, 0.435757145931429, 
          0.36656632349025, 0.312782034685408, 0.357913661160629, 0.414639893651842, 
          0.460992875568015, 0.554803107534663, 0.418743792959099, 0.499114614445091, 
          0.475374442706501, 0.564660334010035, 0.502678818989733, 0.417617035801997, 
          0.488463005872639, 0.484776757286094, 0.424850010858818),
Al = c(0.575667101719941,  0.586351493923602, 0.574053324307634, 0.628497798862674, 0.552234153060378, 
       0.580547408629286, 1.05746950789483, 1.07094531357244, 1.11340157804305, 
       1.03043684466386, 1.02899468191215, 1.07222457991059, 1.5276908007952, 
       1.66549994904359, 1.43287302441973, 1.37434198093964, 1.55835986529032, 
       1.66902429579112), 
Si = c(0.495188340689301, 0.513374456164654, 
       0.51809643007659, 0.569128515813393, 0.542590350648068, 0.516673370168739, 
       1.72437228079744, 1.59076392020817, 1.77327433861292, 1.76671780355934, 
       1.60625706442694, 1.92449284567535, 3.27248599245035, 3.23739024834759, 
       2.84115179036218, 2.51112086010829, 2.98829002803169, 2.93347114563903
), 
P = c(0.222881184902066, 0.258237982165306, 0.230235867213535, 
      0.262379290809071, 0.230438623604524, 0.238615393939999, 0.260241811918024, 
      0.238785817517132, 0.248589968755681, 0.248270048794532, 0.272489046130942, 
      0.266707140244041, 0.25935282543278, 0.258801008935983, 0.250692297246152, 
      0.246890941447243, 0.277698144829677, 0.274197618349091)), 
row.names = c(NA, 
              -18L), class = c("tbl_df", "tbl", "data.frame")))

但对于你的具体问题，你应该这样做

---

我希望这有帮助

我不明白为什么

Misc

的长度是2，而

Mod

的长度是28。它们不应该是一样的吗？您还可以发布什么

dput（head（speak_name））

返回？我不知道这些数据是什么样子的。它们的长度可以不等，但可以重复。。

atas_clean$speaker <- str_replace_all(atas_clean$speaker, speak_namesMod, 
Mod)

Warning message:
In stri_replace_all_regex(string, pattern, fix_replacement(replacement),  :
longer object length is not a multiple of shorter object length

identical(length(speak_namesMod), length(Mod))

library('dplyr') # load the dplyr package
library('stringr') # load the stringr package

abc<-as.data.frame(
structure(list(Name = c("ME-9_ 005", "ME-9_ 004", "ME-9_ 003", 
                        "ME-9_ 002", "ME-9_ 001", "ME-9_ 000", "ME-8_ 005", "ME-8_ 004", 
                        "ME-8_ 003", "ME-8_ 002", "ME-8_ 001", "ME-8_ 000", "ME-7_ 005", 
                        "ME-7_ 004", "ME-7_ 003", "ME-7_ 002", "ME-7_ 001", "ME-7_ 000"
), Mg = c(0.411058647473409, 0.361611969040526, 0.435757145931429, 
          0.36656632349025, 0.312782034685408, 0.357913661160629, 0.414639893651842, 
          0.460992875568015, 0.554803107534663, 0.418743792959099, 0.499114614445091, 
          0.475374442706501, 0.564660334010035, 0.502678818989733, 0.417617035801997, 
          0.488463005872639, 0.484776757286094, 0.424850010858818),
Al = c(0.575667101719941,  0.586351493923602, 0.574053324307634, 0.628497798862674, 0.552234153060378, 
       0.580547408629286, 1.05746950789483, 1.07094531357244, 1.11340157804305, 
       1.03043684466386, 1.02899468191215, 1.07222457991059, 1.5276908007952, 
       1.66549994904359, 1.43287302441973, 1.37434198093964, 1.55835986529032, 
       1.66902429579112), 
Si = c(0.495188340689301, 0.513374456164654, 
       0.51809643007659, 0.569128515813393, 0.542590350648068, 0.516673370168739, 
       1.72437228079744, 1.59076392020817, 1.77327433861292, 1.76671780355934, 
       1.60625706442694, 1.92449284567535, 3.27248599245035, 3.23739024834759, 
       2.84115179036218, 2.51112086010829, 2.98829002803169, 2.93347114563903
), 
P = c(0.222881184902066, 0.258237982165306, 0.230235867213535, 
      0.262379290809071, 0.230438623604524, 0.238615393939999, 0.260241811918024, 
      0.238785817517132, 0.248589968755681, 0.248270048794532, 0.272489046130942, 
      0.266707140244041, 0.25935282543278, 0.258801008935983, 0.250692297246152, 
      0.246890941447243, 0.277698144829677, 0.274197618349091)), 
row.names = c(NA, 
              -18L), class = c("tbl_df", "tbl", "data.frame")))

head(abc,10)

abc$Name <- str_replace_all(
  abc$Name, # column we want to search
  c("001" = "","002" = "","003" = "","004" = "","005" = "","000" = "",
    "-" = " ","_" = "") # each string schould be matched with a replacement
)

head(abc,10)