Question

我需要一种快速而简洁的方法将数据帧中的字符串文字拆分为一组列。我们说我有这个数据框

data <- data.frame(id=c(1,2,3), tok1=c("a, b, c", "a, a, d", "b, d, e"), tok2=c("alpha|bravo", "alpha|charlie", "tango|tango|delta") )

（请注意列中不同的分隔符）

字符串列的数量通常是事先不知道的（如果我没有其他选择，我可以尝试发现整套案例）

我需要两个数据框：

tok1.occurrences:
    +----+---+---+---+---+---+
    | id | a | b | c | d | e | 
    +----+---+---+---+---+---+
    |  1 | 1 | 1 | 1 | 0 | 0 |
    |  2 | 2 | 0 | 0 | 1 | 0 |
    |  3 | 0 | 1 | 0 | 1 | 1 |
    +----+---+---+---+---+---+

tok2.occurrences:
    +----+-------+-------+---------+-------+-------+
    | id | alpha | bravo | charlie | delta | tango | 
    +----+-------+-------+---------+-------+-------+
    |  1 |   1   |   1   |    0    |   0   |   0   |
    |  2 |   1   |   0   |    1    |   0   |   0   |
    |  3 |   0   |   0   |    0    |   1   |   2   |
    +----+-------+-------+---------+-------+-------+

我尝试使用这种语法：

tok1.f = factor(data$tok1)
dummies <- model.matrix(~tok1.f)

这最终导致了一个不完整的解决方案。它正确地创建了我的虚拟变量，但没有（显然）与分隔符分开。

我知道我可以使用＆＃39; tm＆＃39;用于查找文档术语矩阵的包，但对于这种简单的标记化来说似乎太过分了。有更直接的方式吗？

Answer 1

我能想到的最简单的事情就是将my cSplit function与dcast.data.table结合使用，如下所示：

library(splitstackshape)
dcast.data.table(cSplit(data, "tok1", ", ", "long"), 
                 id ~ tok1, value.var = "tok1", 
                 fun.aggregate = length)
#    id a b c d e
# 1:  1 1 1 1 0 0
# 2:  2 2 0 0 1 0
# 3:  3 0 1 0 1 1

dcast.data.table(cSplit(data, "tok2", "|", "long"), 
                 id ~ tok2, value.var = "tok2", 
                 fun.aggregate = length)
#    id alpha bravo charlie delta tango
# 1:  1     1     1       0     0     0
# 2:  2     1     0       1     0     0
# 3:  3     0     0       0     1     2

修改：已更新为library(splitstackshape)，因为cSplit现已成为该软件包的一部分。

Answer 2

如果您不介意（暂时）使用data.table，这可能对您有用：

library(data.table)

data <- data.frame(id=c(1,2,3), 
                   tok1=c("a, b, c", "a, a, d", "b, d, e"), 
                   tok2=c("alpha|bravo", "alpha|charlie", "tango|tango|delta"))

splitCols <- function(col_name, data) {

  # strsplit needs strings

  data[, col_name] <- as.character(data[, col_name])

  # make a list of single row data frames from the tabulation
  # of each of items from the split column

  tokens <- lapply(strsplit(data[, col_name], "[^[:alnum:]]+"), function(x) {
    tab <- table(x)
    setNames(rbind.data.frame(as.numeric(tab)), names(tab))
  })

  # use data.table's rbindlist, filling in missing values

  rbl <- rbindlist(tokens, fill=TRUE)

  # 0 out the NA's

  rbl[is.na(rbl)] <- 0

  # add the "id" column

  cbind(id=data$id, rbl)

}

lapply(names(data)[-1], splitCols, data)

## [[1]]
##    id a b c d e
## 1:  1 1 1 1 0 0
## 2:  2 2 0 0 1 0
## 3:  3 0 1 0 1 1
## 
## [[2]]
##    id alpha bravo charlie delta tango
## 1:  1     1     1       0     0     0
## 2:  2     1     0       1     0     0
## 3:  3     0     0       0     1     2

您最终会得到一个数据框列表，然后您可以根据需要进行处理。

Answer 3

您可以使用stringr包，如下所示：

require(stringr)

test_data <- data.frame(id=c(1,2,3), tok1=c("a, b, c", "a, a, d", "b, d, e"), tok2=c("alpha|bravo", "alpha|charlie", "tango|tango|delta") )

#conversion to character class and uniform delimeter as ","
test_data$tok1<-as.character(test_data$tok1)
test_data$tok1<-gsub(" ","",test_data$tok1)
test_data$tok2=gsub("\\|",",",as.character(test_data$tok2))

#Unique list of elements for each column
tok1.uniq=sort(unique(unlist(strsplit(as.character(test_data$tok1),","))))
tok2.uniq=sort(unique(unlist(strsplit(as.character(test_data$tok2),","))))

#Token count for each column

#In each row of token, find the count of characters using str_count from stringr package

第一栏：

tok1.occurances=do.call(cbind,lapply(tok1.uniq,function(x) {

DF=data.frame(do.call(rbind,lapply(test_data$tok1,function(y,z=x) str_count(y,z))))
colnames(DF) = x
return(DF)

}
))

#Add ID number as column
tok1.occurances=data.frame(id=as.numeric(row.names(tok1.occurances)),tok1.occurances,stringsAsFactors=FALSE)


# > tok1.occurances
# id a b c d e
#  1 1 1 1 0 0
#  2 2 0 0 1 0
#  3 0 1 0 1 1

第二栏：

tok2.occurances=do.call(cbind,lapply(tok2.uniq,function(x) {

DF=data.frame(do.call(rbind,lapply(test_data$tok2,function(y,z=x) str_count(y,z))))
colnames(DF) = x
return(DF)

}
))

tok2.occurances=data.frame(id=as.numeric(row.names(tok2.occurances)),tok2.occurances,stringsAsFactors=FALSE)


# > tok2.occurances
# id alpha bravo charlie delta tango
#  1     1     1       0     0     0
#  2     1     0       1     0     0
#  3     0     0       0     1     2

将分隔的字符串拆分为R数据帧中的不同列

3 个答案: