从R中的字符串中提取子字符串和数字

Question

I have several strings, following are some examples.

rfoutputtablep7q10000t20000c100
rfoutputtablep7q1000t20000c100
svmLinear2outputtablep7q20000t20000c100
svmLinear2outputtablep7q5000t20000c100

I want to make a data frame with columns: algorithm , p , q , t , and c and extract the values from these strings. So the stuff before "outputtable" is the algorithm , the number after "p" is the value of p , number after "q" is the value of q , etc.

How can this data frame be created?

Answer 1

Using base R only.

res <- do.call(rbind, strsplit(y, 'outputtable|p|q|t|c'))
res <- as.data.frame(res[, -2])
res[-1] <- lapply(res[-1], function(x) as.numeric(as.character(x)))
names(res) <- c("algorithm", "p", "q", "t", "c")
res
#   algorithm p     q     t   c
#1         rf 7 10000 20000 100
#2         rf 7  1000 20000 100
#3 svmLinear2 7 20000 20000 100
#4 svmLinear2 7  5000 20000 100

DATA.

y <- scan(text = '"rfoutputtablep7q10000t20000c100"
"rfoutputtablep7q1000t20000c100"
"svmLinear2outputtablep7q20000t20000c100"
"svmLinear2outputtablep7q5000t20000c100"',
what = character())

Answer 2

library(stringr)
myd = c("p", "q", "t", "c")
data.frame(sapply(myd, function(a) str_extract(str_extract(x, paste0(a, "\\d+")), "\\d+")))
#  p     q     t   c
#1 7 10000 20000 100
#2 7  1000 20000 100
#3 7 20000 20000 100
#4 7  5000 20000 100

#For first column
substr(x, 1, unlist(gregexpr("outputtable", x)) - 1)
#[1] "rf"         "rf"         "svmLinear2" "svmLinear2"

DATA

x = c("rfoutputtablep7q10000t20000c100", "rfoutputtablep7q1000t20000c100", 
"svmLinear2outputtablep7q20000t20000c100", "svmLinear2outputtablep7q5000t20000c100")

Answer 3

Use a positive look-ahead to get the algorithm:

gsub("^(\\w+)(?=outputtable).*", "\\1", string, perl=TRUE)

Live example: https://regex101.com/r/7vDK1x/2

A positive look-behind for p, q, t, and c (replace p with the other letters in (?<=p) .

gsub(".*?(?<=q)(\\d+).*", "\\1", a, perl=TRUE)

Answer 4

Here another solution using stringi package. Check the benchmarks comparing all solutions proposed so far. stringi is slightly faster than base R, but is, of course, a bit more complicated if you seek a simple solution. Hence, depending on your preference for speed or simplicity either is good. However, stringi offers more flexibility for more complex cases. (Note, the benchmarks are not perfectly comparable since we have all used slighlty different approaches for setting up the data.frame and converting types.)

UPDATE: In response to the comment of Rui Barradas I have updated the code to my answer. (i) I have proposed a function using the stringi approach including conversion of columns to numeric, hence, for the full task as I would do it. (ii) Furthermore, I have added benchmarks so that all approaches proposed so far (also in comments) are included. In order to achieve a halfway fair comparison I have modified the proposed approaches, so that the ouput is the same. I have skipped conversion of columns to numeric for the comparison, in particular, and made the commands similarly concise by avoiding interim assignments, etc.

It seems that stringi is still the fastest.

Please correct me, if I have overseen anything concerning a fair comparison (especially the stringr solution might be improved codewise, I guess, but I am not so familiar with the package, therefore, I kept the proposed solution).

library(stringi)
library(stringr)
library(microbenchmark)

strings <- c("rfoutputtablep7q10000t20000c100",
              "rfoutputtablep7q1000t20000c100",
             "svmLinear2outputtablep7q20000t20000c100",
             "svmLinear2outputtablep7q5000t20000c100")


split_to_df <- function(string, splititems, colidschar, firstcolname, replsplit_tonames) {

   data <- as.data.frame(do.call(rbind
                                ,stri_split_regex(strings, paste(splititems, collapse = "|")))
                        ,stringsAsFactors = FALSE)
   names(data) <- c(firstcolname, stri_replace_all_regex(splititems, replsplit_tonames, ""))
   numericcols <- setdiff(1:ncol(data), colidschar)
   data[,numericcols] <- lapply(data[,numericcols], as.numeric)
   return(data)

}

stringi_approach_complete <- function() {

  df <- split_to_df(string = strings
                    ,splititems = c("outputtablep(?=\\d)", "q(?=\\d)", "t(?=\\d)", "c(?=\\d)")
                    ,colidschar = 1
                    ,firstcolname = "A"
                    ,replsplit_tonames = "\\(.*\\)|outputtable")
  # class(df$p)
  # [1] "numeric"
  # A p     q     t   c
  # 1         rf 7 10000 20000 100
  # 2         rf 7  1000 20000 100
  # 3 svmLinear2 7 20000 20000 100
  # 4 svmLinear2 7  5000 20000 100

}


stringi_approach_compare <- function() {

  data <- as.data.frame(do.call(rbind, stri_split_regex(strings, c("outputtable|p(?=\\d)|q(?=\\d)|t(?=\\d)|c(?=\\d)"))))
  names(data) <- c("A", "p", "q", "t", "c")
  #class(data$p)
  #[1] "factor"
  #data
  # A p     q     t   c
  # 1         rf 7 10000 20000 100
  # 2         rf 7  1000 20000 100
  # 3 svmLinear2 7 20000 20000 100
  # 4 svmLinear2 7  5000 20000 100

}


stringr_approach <- function() {

  res <- data.frame(p = str_extract(str_extract(strings, "p\\d+"), "\\d+"),
                    q = str_extract(str_extract(strings, "q\\d+"), "\\d+"),
                    t = str_extract(str_extract(strings, "t\\d+"), "\\d+"),
                    c = str_extract(str_extract(strings, "c\\d+"), "\\d+"))
  #class(res$p)
  #[1] "factor"
  #res
  # p     q     t   c
  # 1 7 10000 20000 100
  # 2 7  1000 20000 100
  # 3 7 20000 20000 100
  # 4 7  5000 20000 100

}

base_approach1 <- function() {

  res <- do.call(rbind, strsplit(strings, 'outputtable|p|q|t|c'))
  res <- as.data.frame(res[, -2])
  names(res) <- c("A", "p", "q", "t", "c")
  #class(res$p)
  #[1] "factor"
  #res[-1] <- lapply(res[-1], function(x) as.numeric(as.character(x)))
  #res
  #           A p     q     t   c
  #1         rf 7 10000 20000 100
  #2         rf 7  1000 20000 100
  #3 svmLinear2 7 20000 20000 100
  #4 svmLinear2 7  5000 20000 100


}

base_approach2 <- function() {

  df <- setNames(data.frame(do.call(rbind, strsplit(strings, 'outputtable\\D|p|q|t|c'))), c("A", "p", "q", "t", "c"))
  #class(df$p)
  #[1] "factor"
  #df
  # A p     q     t   c
  # 1         rf 7 10000 20000 100
  # 2         rf 7  1000 20000 100
  # 3 svmLinear2 7 20000 20000 100
  # 4 svmLinear2 7  5000 20000 100

}



microbenchmark(
  base_approach1(),
  base_approach2(),
  stringi_approach_compare(),
  stringr_approach(),
  stringi_approach_complete()

)

# Unit: microseconds
#         expr                 min       lq     mean   median       uq       max neval
# base_approach1()            260.139 273.3635 337.1985 285.6005 298.2330  5280.152   100
# base_approach2()            352.906 362.1820 461.8205 374.8140 391.9850  4645.791   100
# stringi_approach_compare()  280.667 297.8380 312.8426 307.3125 319.1545   654.098   100
# stringr_approach()          849.499 867.6570 956.7596 886.2100 923.7115  5651.609   100
# stringi_approach_complete() 319.747 333.9580 461.5521 346.7870 369.0900 10985.052   100