Question

Does anyone has any idea about importing the below data into R in an appropriate form? I tried strsplit function as: test <- strsplit(test,"[[:space:]]+") where test is the name of the file including the following messy data. Somehow I ended up with only one character variable. I would like to have eight different variable in appropriate form. Could you please help me?

Black Eagles    01/12 - 12/11   1500 W  7.0 420 48  Away +3
Blue State  02/18 - 04/21   1293 L  8.0 490 48  Home +1
Hawks   01/13 - 02/17   1028 L  4.0 46  460 Away
New Apple   09/23 - 11/23   563 L   3.0 470 47  Home +2
Black White 07/05 - 09/26   713 L   5.2 500 45  Home +4
PBO 10/24 - 10/30   1495 L  1.9 47  410 Away

Answer 1

How is this?

> nicelyFormatted
     [,1]           [,2]    [,3]    [,4]   [,5] [,6]  [,7]  [,8]  [,9]   [,10]
[1,] "Black Eagles" "01/12" "12/11" "1500" "W"  "7.0" "420" "48"  "Away" "+3" 
[2,] "Blue State"   "02/18" "04/21" "1293" "L"  "8.0" "490" "48"  "Home" "+1" 
[3,] "Hawks"        "01/13" "02/17" "1028" "L"  "4.0" "46"  "460" "Away" NA   
[4,] "New Apple"    "09/23" "11/23" "563"  "L"  "3.0" "470" "47"  "Home" "+2" 
[5,] "Black White"  "07/05" "09/26" "713"  "L"  "5.2" "500" "45"  "Home" "+4" 
[6,] "PBO"          "10/24" "10/30" "1495" "L"  "1.9" "47"  "410" "Away" NA   

---

Here is the code that was used to get the above table:

library(stringr)

# Open Connection to file
pathToFile <- path.expand("~/path/to/file/myfile.txt")
f <- file(pathToFile, "rb")  

# Read in lines
rawText <- readLines(f)


# Find the dahses
dsh <- str_locate_all(rawText, " - ")

# Splice, using the dashes as a guide
lng <- length(rawText)
spliced <- sapply(1:lng, function(i) 
  spliceOnDash(rawText[[i]], dsh[[c(i, 1)]], dsh[[c(i, 2)]])
)

# make it purtty
nicelyFormatted <- formatNicely(spliced)
nicelyFormatted


#-------------------#
#    FUNCTIONS      #
#-------------------#


spliceOnDash <- function(strn, start, end)  {

  # split around the date
  pre <- substr(strn, 1, start-6)
  dates <- substr(strn, start-5, end+5)
  post <- substr(strn, end+6, str_length(strn))

  # Clean up
  pre <- str_trim(pre)

  # replace all double spaces with single spaces
  while(str_detect(post, "  ")) {
    post <- str_replace_all(str_trim(post), "  ", " ")    
  }

  # splice on space
  post <- str_split(post, " ")

  # if dates are one field, remove this next line
  dates <- str_split(dates, " - ")

  # return
  c(unlist(pre), unlist(dates), unlist(post))
}

# Function to clean up the list into a nice table
formatNicely <- function(spliced)  {
  lngst <- max(sapply(spliced, length))
  t(sapply(spliced, function(x)  
      if(length(x) < lngst) c(x, rep(NA, lngst-length(x))) else x ))
}