CODEWITHSUNDEEP
rimportdelimited
frog11
frog11

Reputation: 38

Reading non delimited text file into R

I have a large set of Data that is in an non delimited format that I am trying to import into R. The data set comes with a Column Locations file that includes a row number, the column name, and the character position of the variable. Is there an existing package for handling this type of data? If not, how can it be done?

Final Code I used to parse the widths from the Column Locations file and use them to read the Data file:

ColumnNames_Download <- function(){
 if(file.exists("ANES_ColumnNames.txt")){
      columnNames <- read_delim("ANES_ColumnNames.txt", delim = " ")
 } else{
      download.file(ANES_ColNamesURL, "ANES_ColumnNames.txt", mode = "wb")
      columnNames <- read_delim("ANES_ColumnNames.txt", delim = " ")
 }
 return(columnNames)

}

ColumnWidths <- function(columnNames){
 columnNames_list <- columnNames$File
 columnNames_listSub <- gsub(pattern = "-", replacement = ":",
                           x = columnNames_list)
 columnNames_split <- strsplit(columnNames_listSub, split = ":")
 columnWidth <- vector()
 for (i in seq_along(columnNames_split)){
      if (length(columnNames_split[[i]]) > 1){
           columnWidth <- append(columnWidth,c(as.numeric(
                          columnNames_split[[i]][2]) - 
                          as.numeric(columnNames_split[[i]][1]) + 1))
      } else{
           columnWidth <- append(columnWidth,c(1))

      }

 }

}

Data_Download <- function(Width){
 read_fwf("ANES_Data.txt",fwf_widths(Width))

}

Upvotes: 1

Views: 3595

Answers (1)

James Theobald
James Theobald

Reputation: 121

If your file is saved as a text file (.txt), then you may use read.csv() and set sep = " " as follows:

col.loc <- read.csv("filename.txt", sep = " ")

# > head(col.loc)
#   Writing       COL  File
# 1      1)  VERSION:  1-28
# 2      2)  VCF0004: 29-32
# 3      3)  VCF0006: 33-36
# 4      4) VCF0006A: 37-44
# 5      5)  VCF0009: 45-59
# 6      6) VCF0009A: 60-74

The data from any column can be saved into vector by selection with the $:

file <- col.loc$File

# > file
# [1] 1-28      29-32     33-36     37-44     45-59     60-74     75-89     90-104    105-119   120-134   135       136       137      
# [14] 138       139       140       141       142       143       144       145       146       147       148       149       150      
# [27] 151       152       153       154       155       156       157-158   159       160       161       162       163       164      
# [40] 165       166       167-169   170       171       172       173       174       175       176       177       178       179      
# [53] 180-182   183-185   186-188   189-191   192-193   194-195   196       197       198-199   200-201   202       203-204   205      
# [66] 206       207       208       209-211   212       213       214       215-217   218-220   221       222       223       224      
# [79] 225       226       227       228       229       230       231       232       233       234       235-237   238       239-241  
# [92] 242-244   245       246       247       248       249       250-251   252       253-255   256       257-258   259-260   261-262  
# [105] 263-264   265       266       267       268-271   272-274   275-279   280-284   285-286   287-288   289-290   291-292   293-294
# [118] 295-296   297-298   299-300   301-302   303-304   305-306   307-308   309-310   311-312   313-314   315-316   317-318   319-320  
# [131] 321-322   323-324   325-326   327-328   329-330   331-332   333-334   335-336   337-338   339-340   341-342   343-344   345-346

That will create a new factor vector that can be modified to a character vector as follows:

file.char <- as.character(file)

Since the new vector is a character vector you can use gsub() to replace all dashes (-) with any other punctuation you want. I chose to replace with a colon (:). Use gsub() as follows:

file.char.gsub <- gsub(pattern = "-", replacement = ":", x = file.char)

# > file.char.gsub
# [1] "1:28"      "29:32"     "33:36"     "37:44"     "45:59"     "60:74"     "75:89"     "90:104"    "105:119"   "120:134"   "135"      
# [12] "136"       "137"       "138"       "139"       "140"       "141"       "142"       "143"       "144"       "145"       "146"      
# [23] "147"       "148"       "149"       "150"       "151"       "152"       "153"       "154"       "155"       "156"       "157:158"  
# [34] "159"       "160"       "161"       "162"       "163"       "164"       "165"       "166"       "167:169"   "170"       "171"      
# [45] "172"       "173"       "174"       "175"       "176"       "177"       "178"       "179"       "180:182"   "183:185"   "186:188"  
# [56] "189:191"   "192:193"   "194:195"   "196"       "197"       "198:199"   "200:201"   "202"       "203:204"   "205"       "206"      
# [67] "207"       "208"       "209:211"   "212"       "213"       "214"       "215:217"   "218:220"   "221"       "222"       "223"      
# [78] "224"       "225"       "226"       "227"       "228"       "229"       "230"       "231"       "232"       "233"       "234"      
# [89] "235:237"   "238"       "239:241"   "242:244"   "245"       "246"       "247"       "248"       "249"       "250:251"   "252"      
# [100] "253:255"   "256"       "257:258"   "259:260"   "261:262"   "263:264"   "265"       "266"       "267"       "268:271"   "272:274"  
# [111] "275:279"   "280:284"   "285:286"   "287:288"   "289:290"   "291:292"   "293:294"   "295:296"   "297:298"   "299:300"   "301:302"  
# [122] "303:304"   "305:306"   "307:308"   "309:310"   "311:312"   "313:314"   "315:316"   "317:318"   "319:320"   "321:322"   "323:324"

Upvotes: 1

Related Questions