String 如何在R数据帧中将多个字符列合并为一个列

我正在处理人口普查数据，我需要将四个字符的列组合成一个列

例如：

LOGRECNO STATE COUNTY  TRACT BLOCK
    60    01    001  021100  1053
    61    01    001  021100  1054
    62    01    001  021100  1055
    63    01    001  021100  1056
    64    01    001  021100  1057
    65    01    001  021100  1058

我想创建一个新列，将STATE、COUNTY、TRACT和BLOCK的字符串添加到一个字符串中。例如：

LOGRECNO STATE COUNTY  TRACT BLOCK  BLOCKID
    60    01    001  021100  1053   01001021101053
    61    01    001  021100  1054   01001021101054
    62    01    001  021100  1055   01001021101055
    63    01    001  021100  1056   01001021101056
    64    01    001  021100  1057   01001021101057
    65    01    001  021100  1058   01001021101058

我试过：

AL_Blocks$BLOCK_ID<- paste(c(AL_Blocks$STATE, AL_Blocks$County, AL_Blocks$TRACT,    AL_Blocks$BLOCK), collapse = "")

---

AL_Blocks$BLOCK_ID您可以使用
do.call
和
paste0
。尝试：

AL_Blocks$BLOCK_ID <- do.call(paste0, AL_Block[c("STATE", "COUNTY", "TRACT", "BLOCK")])


您还可以使用“tidyr”中的
unite
，如下所示：

library(tidyr)
library(dplyr)
AL_Blocks %>% 
  unite(BLOCK_ID, STATE, COUNTY, TRACT, BLOCK, sep = "", remove = FALSE)
#   LOGRECNO        BLOCK_ID STATE COUNTY  TRACT BLOCK
# 1       60 010010211001053    01    001 021100  1053
# 2       61 010010211001054    01    001 021100  1054
# 3       62 010010211001055    01    001 021100  1055
# 4       63 010010211001056    01    001 021100  1056
# 5       64 010010211001057    01    001 021100  1057
# 6       65 010010211001058    01    001 021100  1058

其中提供的“铝块”如下所示：

AL_Blocks <- structure(list(LOGRECNO = c("60", "61", "62", "63", "64", "65"), 
    STATE = c("01", "01", "01", "01", "01", "01"), COUNTY = c("001", "001", 
    "001", "001", "001", "001"), TRACT = c("021100", "021100", "021100", 
    "021100", "021100", "021100"), BLOCK = c("1053", "1054", "1055", "1056",
    "1057", "1058")), .Names = c("LOGRECNO", "STATE", "COUNTY", "TRACT", 
    "BLOCK"), class = "data.frame", row.names = c(NA, -6L))

AL_块试试这个：

AL_Blocks$BLOCK_ID<- with(AL_Blocks, paste0(STATE, COUNTY, TRACT, BLOCK))

AL_Blocks$BLOCK_ID或者试试这个

DF$BLOCKID <-
  paste(DF$LOGRECNO, DF$STATE, DF$COUNTY, 
        DF$TRACT, DF$BLOCK, sep = "")

DF$BLOCKID你也可以试试这个

AL_Blocks <- transform(All_Blocks, BLOCKID = paste(STATE,COUNTY,
                       TRACT, BLOCK, sep = "")

AL_Blocks您可以使用
tidyverse
软件包：

DF %>% unite(new_var, STATE, COUNTY, TRACT, BLOCK)

您可以使用任何指定的“字符串分隔符”（不一定是字符分隔符）写入和读取文本文件。当数据几乎具有所有端子符号时，这在许多情况下非常有用，因此，没有1个符号可用作分隔符。以下是读写函数的示例：

写出特殊分隔符文本：
writeSepText我有80列，有没有办法像[2:82]那样传递列名，这样会让我的生活更轻松？@kRazzyR，这个解决方案适用于我的54列。数据（iris）iris$full
AL_Blocks <- transform(All_Blocks, BLOCKID = paste(STATE,COUNTY,
                       TRACT, BLOCK, sep = "")

DF %>% unite(new_var, STATE, COUNTY, TRACT, BLOCK)

writeSepText <- function(df, fileName, separator) {
    con <- file(fileName)
    data <- apply(df, 1, paste, collapse = separator)
    # data
    data <- writeLines(data, con)
    close(con)
    return
}

writeSepText(df=as.data.frame(Titanic), fileName="/Users/user/break_sep.txt", separator="<break>")

readSepText <- function(fileName, separator) {
    data <- readLines(con <- file(fileName))
    close(con)
    records <- sapply(data, strsplit, split=separator)
    dataFrame <- data.frame(t(sapply(records,c)))
    rownames(dataFrame) <- 1: nrow(dataFrame)
    return(as.data.frame(dataFrame,stringsAsFactors = FALSE))
}

df <- readSepText(fileName="/Users/user/break_sep.txt", separator="<break>"); df